E-Bibliothek Gesundheitskompetenz des DNGK
Fachliteratur Artificial Intelligence / Künstliche Intelligenz
Hier finden Sie die in der Datenbank des DNGK eingestellten Fachartikel zum Thema – geordnet nach Datum der Publikation (aktuellste zuerst).
6298796
4UVUVQXJ
1
chicago-fullnote-bibliography
50
date
desc
title
11157
https://gesundheitskompetenz.online/wp-content/plugins/zotpress/
%7B%22status%22%3A%22success%22%2C%22updateneeded%22%3Afalse%2C%22instance%22%3Afalse%2C%22meta%22%3A%7B%22request_last%22%3A100%2C%22request_next%22%3A50%2C%22used_cache%22%3Atrue%7D%2C%22data%22%3A%5B%7B%22key%22%3A%224P5487JB%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Zhou%20et%20al.%22%2C%22parsedDate%22%3A%222025-06%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BZhou%2C%20Mi%2C%20Yun%20Pan%2C%20Yuye%20Zhang%2C%20Xiaomei%20Song%2C%20and%20Youbin%20Zhou.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40107040%5C%2F%26%23039%3B%26gt%3BEvaluating%20AI-generated%20patient%20education%20materials%20for%20spinal%20surgeries%3A%20Comparative%20analysis%20of%20readability%20and%20DISCERN%20quality%20across%20ChatGPT%20and%20deepseek%20models%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BInternational%20Journal%20of%20Medical%20Informatics%26lt%3B%5C%2Fi%26gt%3B%20198%20%28June%202025%29%3A%20105871.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.ijmedinf.2025.105871.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Evaluating%20AI-generated%20patient%20education%20materials%20for%20spinal%20surgeries%3A%20Comparative%20analysis%20of%20readability%20and%20DISCERN%20quality%20across%20ChatGPT%20and%20deepseek%20models%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Mi%22%2C%22lastName%22%3A%22Zhou%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yun%22%2C%22lastName%22%3A%22Pan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yuye%22%2C%22lastName%22%3A%22Zhang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xiaomei%22%2C%22lastName%22%3A%22Song%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Youbin%22%2C%22lastName%22%3A%22Zhou%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20Access%20to%20patient-centered%20health%20information%20is%20essential%20for%20informed%20decision-making.%20However%2C%20online%20medical%20resources%20vary%20in%20quality%20and%20often%20fail%20to%20accommodate%20differing%20degrees%20of%20health%20literacy.%20This%20issue%20is%20particularly%20evident%20in%20surgical%20contexts%2C%20where%20complex%20terminology%20obstructs%20patient%20comprehension.%20With%20the%20increasing%20reliance%20on%20AI%20models%20for%20supplementary%20medical%20information%2C%20the%20reliability%20and%20readability%20of%20AI-generated%20content%20require%20thorough%20evaluation.%5CnOBJECTIVE%3A%20This%20study%20aimed%20to%20evaluate%20four%20natural%20language%20processing%20models-ChatGPT-4o%2C%20ChatGPT-o3%20mini%2C%20DeepSeek-V3%2C%20and%20DeepSeek-R1-in%20generating%20patient%20education%20materials%20for%20three%20common%20spinal%20surgeries%3A%20lumbar%20discectomy%2C%20spinal%20fusion%2C%20and%20decompressive%20laminectomy.%20Information%20quality%20was%20evaluated%20using%20the%20DISCERN%20score%2C%20and%20readability%20was%20assessed%20through%20Flesch-Kincaid%20indices.%5CnRESULTS%3A%20DeepSeek-R1%20produced%20the%20most%20readable%20responses%2C%20with%20Flesch-Kincaid%20Grade%20Level%20%28FKGL%29%20scores%20ranging%20from%207.2%20to%209.0%2C%20succeeded%20by%20ChatGPT-4o.%20In%20contrast%2C%20ChatGPT-o3%20exhibited%20the%20lowest%20readability%20%28FKGL%5Cu00a0%26gt%3B%5Cu00a010.4%29.%20The%20DISCERN%20scores%20for%20all%20AI%20models%20were%20below%2060%2C%20classifying%20the%20information%20quality%20as%20%26quot%3Bfair%2C%26quot%3B%20primarily%20due%20to%20insufficient%20cited%20references.%5CnCONCLUSION%3A%20All%20models%20achieved%20merely%20a%20%26quot%3Bfair%26quot%3B%20quality%20rating%2C%20underscoring%20the%20necessity%20for%20improvements%20in%20citation%20practices%2C%20and%20personalization.%20Nonetheless%2C%20DeepSeek-R1%20and%20ChatGPT-4o%20generated%20more%20readable%20surgical%20information%20than%20ChatGPT-o3.%20Given%20that%20enhanced%20readability%20can%20improve%20patient%20engagement%2C%20reduce%20anxiety%2C%20and%20contribute%20to%20better%20surgical%20outcomes%2C%20these%20two%20models%20should%20be%20prioritized%20for%20assisting%20patients%20in%20the%20clinical.%5CnLIMITATION%20%26amp%3B%20FUTURE%20DIRECTION%3A%20This%20study%20is%20limited%20by%20the%20rapid%20evolution%20of%20AI%20models%2C%20its%20exclusive%20focus%20on%20spinal%20surgery%20education%2C%20and%20the%20absence%20of%20real-world%20patient%20feedback%2C%20which%20may%20affect%20the%20generalizability%20and%20long-term%20applicability%20of%20the%20findings.%20Future%20research%20ought%20to%20explore%20interactive%2C%20multimodal%20approaches%20and%20incorporate%20patient%20feedback%20to%20ensure%20that%20AI-generated%20health%20information%20is%20accurate%2C%20accessible%2C%20and%20facilitates%20informed%20healthcare%20decisions.%22%2C%22date%22%3A%222025-06%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1016%5C%2Fj.ijmedinf.2025.105871%22%2C%22ISSN%22%3A%221872-8243%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40107040%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T09%3A15%3A16Z%22%7D%7D%2C%7B%22key%22%3A%22ELF7TWVZ%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Bracey%20et%20al.%22%2C%22parsedDate%22%3A%222025-05-15%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BBracey%2C%20Solomon%2C%20Nasif%20Bhuiyan%2C%20Amelia%20Pietropaolo%2C%20and%20Bhaskar%20Somani.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fjournals.lww.com%5C%2Fco-urology%5C%2Fabstract%5C%2F9900%5C%2Fexploring_the_impact_of_artificial.253.aspx%26%23039%3B%26gt%3BExploring%20the%20impact%20of%20artificial%20intelligence-enabled%20decision%20aids%20in%20improving%20patient%20inclusivity%2C%20empowerment%2C%20and%20education%20in%20urology%3A%20a%20systematic%20review%20by%20EAU%20endourology%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BCurrent%20Opinion%20in%20Urology%26lt%3B%5C%2Fi%26gt%3B%2C%20May%2015%2C%202025.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1097%5C%2FMOU.0000000000001301.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Exploring%20the%20impact%20of%20artificial%20intelligence-enabled%20decision%20aids%20in%20improving%20patient%20inclusivity%2C%20empowerment%2C%20and%20education%20in%20urology%3A%20a%20systematic%20review%20by%20EAU%20endourology%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Solomon%22%2C%22lastName%22%3A%22Bracey%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nasif%22%2C%22lastName%22%3A%22Bhuiyan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Amelia%22%2C%22lastName%22%3A%22Pietropaolo%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bhaskar%22%2C%22lastName%22%3A%22Somani%22%7D%5D%2C%22abstractNote%22%3A%22PURPOSE%20OF%20REVIEW%3A%20The%20implementation%20of%20artificial%20intelligence%20%28AI%29%20in%20urology%20has%20the%20potential%20to%20enhance%20patient%20outcomes%20through%20the%20provision%20of%20intelligent%20tools%2C%20such%20as%20AI-enabled%20decision%20aids%20%28AIDAs%29%2C%20which%20can%20support%20personalized%20care.%20The%20objective%20of%20this%20systematic%20review%20is%20to%20determine%20the%20role%20of%20AIDAs%20in%20educating%20and%20empowering%20patients%2C%20particularly%20those%20from%20underrepresented%20populations.%5CnRECENT%20FINDINGS%3A%20We%20conducted%20a%20comprehensive%20systematic%20review%20following%20PRISMA%20guidelines%20to%20explore%20the%20potential%20for%20AIDAs%20to%20address%20healthcare%20inequalities%20and%20promote%20patient%20education%20and%20empowerment.%20From%201078%20abstracts%20screened%2C%2021%20articles%20were%20suitable%20for%20inclusion%2C%20all%20of%20which%20utilized%20chatbots.%20Three%20main%20themes%20of%20studies%20were%20identified.%20Fourteen%20studies%20focused%20on%20enhancing%20patient%20education%2C%20four%20studies%20investigated%20whether%20chatbots%20can%20improve%20the%20accessibility%20of%20urological%20literature%20and%20three%20studies%20explored%20chatbots%20role%20in%20providing%20lifestyle%20guidance.%20While%20chatbots%20demonstrated%20great%20potential%20as%20educational%20and%20lifestyle%20support%20tools%2C%20current%20research%20found%20mixed%20accuracy%20and%20a%20tendency%20for%20them%20to%20produce%20unreliable%20information.%20In%20terms%20of%20accessibility%2C%20chatbots%20were%20able%20to%20effectively%20enhance%20readability%20and%20translate%20literature%2C%20potentially%20bridging%20language%2C%20and%20literacy%20barriers.%5CnSUMMARY%3A%20Through%20chatbots%2C%20AIDAs%20show%20strong%20potential%20to%20enhance%20urological%20education%20and%20empower%20underrepresented%20communities.%20However%2C%20chatbots%20must%20show%20greater%20consistency%20in%20accuracy%20before%20they%20can%20be%20confidently%20relied%20upon%20in%20clinical%20contexts.%20Further%20research%20evaluating%20chatbots%26%23039%3B%20efficacy%20in%20clinical%20settings%2C%20especially%20with%20underrepresented%20groups%2C%20would%20enable%20greater%20understanding%20of%20their%20role%20in%20improving%20patient%20inclusivity%2C%20empowerment%2C%20and%20education.%22%2C%22date%22%3A%222025-05-15%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1097%5C%2FMOU.0000000000001301%22%2C%22ISSN%22%3A%221473-6586%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fjournals.lww.com%5C%2Fco-urology%5C%2Fabstract%5C%2F9900%5C%2Fexploring_the_impact_of_artificial.253.aspx%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T07%3A29%3A17Z%22%7D%7D%2C%7B%22key%22%3A%22YJK63C5X%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Frey%20et%20al.%22%2C%22parsedDate%22%3A%222025-05-15%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BFrey%2C%20Nicolas%2C%20Louis%20Agha-Mir-Salim%2C%20Elena%20Hinz%2C%20Akira-Sebastian%20Poncette%2C%20and%20Felix%20Balzer.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Febooks.iospress.nl%5C%2Fdoi%5C%2F10.3233%5C%2FSHTI250336%26%23039%3B%26gt%3BAssessing%20Healthcare%20Stakeholder%20Understanding%20of%20Machine%20Learning%20Documentation%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BStudies%20in%20Health%20Technology%20and%20Informatics%26lt%3B%5C%2Fi%26gt%3B%20327%20%28May%2015%2C%202025%29%3A%20318%5Cu201322.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.3233%5C%2FSHTI250336.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Assessing%20Healthcare%20Stakeholder%20Understanding%20of%20Machine%20Learning%20Documentation%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nicolas%22%2C%22lastName%22%3A%22Frey%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Louis%22%2C%22lastName%22%3A%22Agha-Mir-Salim%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Elena%22%2C%22lastName%22%3A%22Hinz%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Akira-Sebastian%22%2C%22lastName%22%3A%22Poncette%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Felix%22%2C%22lastName%22%3A%22Balzer%22%7D%5D%2C%22abstractNote%22%3A%22Artificial%20Intelligence%20%28AI%29%20has%20significantly%20advanced%20clinical%20decision%20support%20systems%20in%20healthcare%2C%20particularly%20using%20Machine%20Learning%20%28ML%29%20models.%20However%2C%20the%20technical%20nature%20of%20current%20ML%20model%20documentation%20often%20leads%20to%20lack%20of%20comprehension%20among%20healthcare%20stakeholders.%20This%20study%20assessed%20the%20understanding%20of%20ML%20model%20documentation%20for%20a%20sepsis%20prediction%20model%20during%20an%20interdisciplinary%20workshop%20with%2024%20participants.%20Results%20showed%20that%20participants%20had%20moderate%20AI%20literacy%20%28mean%20score%3A%2040.13%20out%20of%2065%29%20and%20that%20on%20average%2065%25%20of%20the%20model%20documentation%20was%20understood.%20Key%20barriers%20to%20understanding%20included%20technical%20jargon%2C%20unexplained%20abbreviations%2C%20lack%20of%20contextual%20clarity%2C%20and%20dense%20data%20presentation%2C%20which%20impacted%20usability.%20Participants%20recommended%20the%20use%20of%20simplified%20language%2C%20clear%20explanations%2C%20and%20visual%20aids%20to%20enhance%20clarity%20and%20facilitate%20integration%20into%20clinical%20workflows.%22%2C%22date%22%3A%222025-05-15%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.3233%5C%2FSHTI250336%22%2C%22ISSN%22%3A%221879-8365%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Febooks.iospress.nl%5C%2Fdoi%5C%2F10.3233%5C%2FSHTI250336%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T07%3A22%3A29Z%22%7D%7D%2C%7B%22key%22%3A%224NGPFEY6%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Heizmann%20et%20al.%22%2C%22parsedDate%22%3A%222025-05-15%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BHeizmann%2C%20Carolin%2C%20Patricia%20Gleim%2C%20and%20Philipp%20Kellmeyer.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Febooks.iospress.nl%5C%2Fdoi%5C%2F10.3233%5C%2FSHTI250340%26%23039%3B%26gt%3BParticipatory%20Co-Creation%20of%20an%20AI-Supported%20Patient%20Information%20System%3A%20A%20Multi-Method%20Qualitative%20Study%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BStudies%20in%20Health%20Technology%20and%20Informatics%26lt%3B%5C%2Fi%26gt%3B%20327%20%28May%2015%2C%202025%29%3A%20338%5Cu201342.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.3233%5C%2FSHTI250340.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Participatory%20Co-Creation%20of%20an%20AI-Supported%20Patient%20Information%20System%3A%20A%20Multi-Method%20Qualitative%20Study%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Carolin%22%2C%22lastName%22%3A%22Heizmann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Patricia%22%2C%22lastName%22%3A%22Gleim%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Philipp%22%2C%22lastName%22%3A%22Kellmeyer%22%7D%5D%2C%22abstractNote%22%3A%22In%20radiology%20and%20other%20medical%20fields%2C%20informed%20consent%20often%20rely%20on%20paper-based%20forms%2C%20which%20can%20overwhelm%20patients%20with%20complex%20terminology.%20These%20forms%20are%20also%20resource-intensive.%20The%20KIPA%20project%20addresses%20these%20challenges%20by%20developing%20an%20AI-assisted%20patient%20information%20system%20to%20streamline%20the%20consent%20process%2C%20improve%20patient%20understanding%2C%20and%20reduce%20healthcare%20workload.%20The%20KIPA%20system%20uses%20natural%20language%20processing%20%28NLP%29%20to%20provide%20real-time%2C%20accessible%20explanations%2C%20answer%20questions%2C%20and%20support%20informed%20consent.%20KIPA%20follows%20an%20%26%23039%3Bethics-by-design%26%23039%3B%20approach%2C%20integrating%20user%20feedback%20to%20align%20with%20patient%20and%20clinician%20needs.%20Interviews%20and%20usability%20testing%20identified%20requirements%2C%20such%20as%20simplified%20language%20and%20support%20for%20varying%20digital%20literacy.%20The%20study%20presented%20here%20explores%20the%20participatory%20co-creation%20of%20the%20KIPA%20system%2C%20focusing%20on%20improving%20informed%20consent%20in%20radiology%20through%20a%20multi-method%20qualitative%20approach.%20Preliminary%20results%20suggest%20that%20KIPA%20improves%20patient%20engagement%20and%20reduces%20insecurities%20by%20providing%20proactive%20guidance%20and%20tailored%20information.%20Future%20work%20will%20extend%20testing%20to%20other%20stakeholders%20and%20assess%20the%20impact%20of%20the%20system%20on%20clinical%20workflow.%22%2C%22date%22%3A%222025-05-15%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.3233%5C%2FSHTI250340%22%2C%22ISSN%22%3A%221879-8365%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Febooks.iospress.nl%5C%2Fdoi%5C%2F10.3233%5C%2FSHTI250340%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T07%3A21%3A36Z%22%7D%7D%2C%7B%22key%22%3A%22RWWZ8WNB%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Turner%20et%20al.%22%2C%22parsedDate%22%3A%222025-05-15%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BTurner%2C%20Jonathan%2C%20Damon%20Berry%2C%20Julie%20Doyle%2C%20Harish%20Kambampati%2C%20Orla%20Moran%2C%20Suzanne%20Smith%2C%20Michael%20Wilson%2C%20and%20Dympna%20O%26%23039%3BSullivan.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Febooks.iospress.nl%5C%2Fdoi%5C%2F10.3233%5C%2FSHTI250489%26%23039%3B%26gt%3BImproving%20the%20Readability%20of%20Dementia%20Information%20Documents%20Using%20ChatGPT%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BStudies%20in%20Health%20Technology%20and%20Informatics%26lt%3B%5C%2Fi%26gt%3B%20327%20%28May%2015%2C%202025%29%3A%20880%5Cu201381.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.3233%5C%2FSHTI250489.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Improving%20the%20Readability%20of%20Dementia%20Information%20Documents%20Using%20ChatGPT%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jonathan%22%2C%22lastName%22%3A%22Turner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Damon%22%2C%22lastName%22%3A%22Berry%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Julie%22%2C%22lastName%22%3A%22Doyle%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Harish%22%2C%22lastName%22%3A%22Kambampati%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Orla%22%2C%22lastName%22%3A%22Moran%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Suzanne%22%2C%22lastName%22%3A%22Smith%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%22%2C%22lastName%22%3A%22Wilson%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dympna%22%2C%22lastName%22%3A%22O%27Sullivan%22%7D%5D%2C%22abstractNote%22%3A%22There%20is%20much%20information%20available%20on%20dementia%2C%20but%20information%20may%20not%20be%20written%20at%20an%20appropriate%20level%20for%20a%20lay%20reader.%20One%20aim%20of%20the%20CoDESIGN%20project%20is%20to%20simplify%20information%20available%20for%20those%20who%20have%20lower%20levels%20of%20literacy.%20We%20investigate%20the%20potential%20to%20simplify%20documents%20to%20reflect%20the%20literacy%20abilities%20of%20the%20reader.%20We%20report%20on%20the%20ability%20of%20ChatGPT%20to%20modify%20documents%20to%20such%20target%20reading%20levels%20while%20retaining%20the%20accuracy%20and%20completeness%20of%20the%20documents%2C%20while%20avoiding%20the%20introduction%20of%20errors.%20Results%20suggest%20that%20human%20supervision%20is%20required%20before%20documents%20can%20be%20made%20available%20to%20readers.%22%2C%22date%22%3A%222025-05-15%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.3233%5C%2FSHTI250489%22%2C%22ISSN%22%3A%221879-8365%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Febooks.iospress.nl%5C%2Fdoi%5C%2F10.3233%5C%2FSHTI250489%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-20T10%3A46%3A07Z%22%7D%7D%2C%7B%22key%22%3A%2278BNJ5MX%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Schmiedmayer%20et%20al.%22%2C%22parsedDate%22%3A%222025-05-14%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BSchmiedmayer%2C%20Paul%2C%20Adrit%20Rao%2C%20Philipp%20Zagar%2C%20Lauren%20Aalami%2C%20Vishnu%20Ravi%2C%20Aydin%20Zahedivash%2C%20Dong-Han%20Yao%2C%20Arash%20Fereydooni%2C%20and%20Oliver%20Aalami.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fwww.jacc.org%5C%2Fdoi%5C%2F10.1016%5C%2Fj.jacadv.2025.101780%26%23039%3B%26gt%3BLLMonFHIR%3A%20A%20Physician-Validated%2C%20Large%20Language%20Model-Based%20Mobile%20Application%20for%20Querying%20Patient%20Electronic%20Health%20Data%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BJACC.%20Advances%26lt%3B%5C%2Fi%26gt%3B%204%2C%20no.%206%20Pt%201%20%28May%2014%2C%202025%29%3A%20101780.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.jacadv.2025.101780.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22LLMonFHIR%3A%20A%20Physician-Validated%2C%20Large%20Language%20Model-Based%20Mobile%20Application%20for%20Querying%20Patient%20Electronic%20Health%20Data%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Paul%22%2C%22lastName%22%3A%22Schmiedmayer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Adrit%22%2C%22lastName%22%3A%22Rao%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Philipp%22%2C%22lastName%22%3A%22Zagar%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lauren%22%2C%22lastName%22%3A%22Aalami%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Vishnu%22%2C%22lastName%22%3A%22Ravi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Aydin%22%2C%22lastName%22%3A%22Zahedivash%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dong-Han%22%2C%22lastName%22%3A%22Yao%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Arash%22%2C%22lastName%22%3A%22Fereydooni%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Oliver%22%2C%22lastName%22%3A%22Aalami%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20To%20improve%20healthcare%20quality%20and%20empower%20patients%2C%20federal%20legislation%20requires%20nationwide%20interoperability%20of%20electronic%20health%20records%20%28EHRs%29%20through%20Fast%20Healthcare%20Interoperability%20Resources%20%28FHIR%29%20application%20programming%20interfaces.%20Nevertheless%2C%20key%20barriers%20to%20patient%20EHR%20access-limited%20functionality%2C%20English%2C%20and%20health%20literacy-persist%2C%20impeding%20equitable%20access%20to%20these%20benefits.%5CnOBJECTIVES%3A%20This%20study%20aimed%20to%20develop%20and%20evaluate%20a%20digital%20health%20solution%20to%20address%20barriers%20preventing%20patient%20engagement%20with%20personal%20health%20information%2C%20focusing%20on%20individuals%20managing%20chronic%20cardiovascular%20conditions.%5CnMETHODS%3A%20We%20present%20LLMonFHIR%2C%20an%20open-source%20mobile%20application%20that%20uses%20large%20language%20models%20%28LLMs%29%20to%20allow%20users%20to%20%26quot%3Binteract%26quot%3B%20with%20their%20health%20records%20at%20any%20degree%20of%20complexity%2C%20in%20various%20languages%2C%20and%20with%20bidirectional%20text-to-speech%20functionality.%20In%20a%20pilot%20evaluation%2C%20physicians%20assessed%20LLMonFHIR%20responses%20to%20queries%20on%206%20SyntheticMass%20FHIR%20patient%20datasets%2C%20rating%20accuracy%2C%20understandability%2C%20and%20relevance%20on%20a%205-point%20Likert%20scale.%5CnRESULTS%3A%20A%20total%20of%20210%20LLMonFHIR%20responses%20were%20evaluated%20by%20physicians%2C%20receiving%20high%20median%20scores%20for%20accuracy%20%285%5C%2F5%29%2C%20understandability%20%285%5C%2F5%29%2C%20and%20relevance%20%285%5C%2F5%29.%20Challenges%20summarizing%20health%20conditions%20and%20retrieving%20lab%20results%20were%20noted%2C%20with%20variability%20in%20responses%20and%20occasional%20omissions%20underscoring%20the%20need%20for%20precise%20preprocessing%20of%20data.%5CnCONCLUSIONS%3A%20LLMonFHIR%26%23039%3Bs%20ability%20to%20generate%20responses%20in%20multiple%20languages%20and%20at%20varying%20levels%20of%20complexity%2C%20along%20with%20its%20bidirectional%20text-to-speech%20functionality%2C%20give%20it%20the%20potential%20to%20empower%20individuals%20with%20limited%20functionality%2C%20English%2C%20and%20health%20literacy%20to%20access%20the%20benefits%20of%20patient-accessible%20EHRs.%22%2C%22date%22%3A%222025-05-14%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1016%5C%2Fj.jacadv.2025.101780%22%2C%22ISSN%22%3A%222772-963X%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fwww.jacc.org%5C%2Fdoi%5C%2F10.1016%5C%2Fj.jacadv.2025.101780%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T07%3A27%3A35Z%22%7D%7D%2C%7B%22key%22%3A%22EE7JLN8T%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Wieben%20et%20al.%22%2C%22parsedDate%22%3A%222025-05-08%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BWieben%2C%20Ann%2C%20Linsey%20Steege%2C%20Roger%20Brown%2C%20and%20Andrea%20Gilmore-Bykovskyi.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fjournals.lww.com%5C%2Fcinjournal%5C%2Fabstract%5C%2F9900%5C%2Fexamining_the_impact_of_interface_design_and_nurse.346.aspx%26%23039%3B%26gt%3BExamining%20the%20Impact%20of%20Interface%20Design%20and%20Nurse%20Characteristics%20on%20Satisfaction%20With%20Machine%20Learning%20Decision%20Support%20Explanations%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BComputers%2C%20Informatics%2C%20Nursing%3A%20CIN%26lt%3B%5C%2Fi%26gt%3B%2C%20May%208%2C%202025.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1097%5C%2FCIN.0000000000001323.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Examining%20the%20Impact%20of%20Interface%20Design%20and%20Nurse%20Characteristics%20on%20Satisfaction%20With%20Machine%20Learning%20Decision%20Support%20Explanations%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ann%22%2C%22lastName%22%3A%22Wieben%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Linsey%22%2C%22lastName%22%3A%22Steege%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Roger%22%2C%22lastName%22%3A%22Brown%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Andrea%22%2C%22lastName%22%3A%22Gilmore-Bykovskyi%22%7D%5D%2C%22abstractNote%22%3A%22Machine%20learning%20has%20the%20potential%20to%20drive%20the%20next%20generation%20of%20clinical%20decision%20support%20systems%20by%20identifying%20patterns%20in%20health%20data%20to%20enhance%20efficiency%20and%20safety.%20Explanatory%20information%20is%20intended%20to%20help%20clinicians%20understand%20the%20outputs%20of%20these%20complex%20systems.%20No%20studies%20have%20evaluated%20associations%20between%20display%20design%20strategies%20or%20nurse%20characteristics%20and%20nurse%20satisfaction%20with%20machine%20learning%20explanatory%20information.%20This%20gap%20leaves%20much%20unknown%20about%20designing%20explanatory%20displays%20that%20meet%20nurses%26%23039%3B%20information%20needs%2C%20supporting%20effective%20use%20and%20adoption%20in%20practice%20settings.%20To%20address%20this%2C%20we%20aimed%20to%20describe%20nurses%26%23039%3B%20satisfaction%20with%20explanatory%20information%20displays%20for%20machine%20learning%20clinical%20decision%20support%2C%20examine%20associations%20between%20the%20format%20and%20complexity%20of%20explanatory%20information%20and%20nurse%20satisfaction%2C%20and%20investigate%20the%20influence%20of%20nurse%20characteristics%2C%20such%20as%20numeracy%20and%20graphical%20literacy%2C%20on%20satisfaction.%20Our%20findings%20indicate%20that%20local%20feature-based%20explanatory%20information%20may%20not%20satisfy%20nurses%26%23039%3B%20information%20needs%2C%20and%20that%20nurse%20age%2C%20artificial%20intelligence%20training%20level%2C%20and%20numeracy%20influence%20preferences.%20We%20found%20no%20significant%20effects%20of%20the%20format%20or%20complexity%20of%20explanatory%20displays%20on%20satisfaction.%20These%20insights%20into%20the%20usability%20of%20machine%20learning%20clinical%20decision%20support%20for%20nurses%20can%20inform%20the%20design%20of%20more%20effective%20displays.%22%2C%22date%22%3A%222025-05-08%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1097%5C%2FCIN.0000000000001323%22%2C%22ISSN%22%3A%221538-9774%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fjournals.lww.com%5C%2Fcinjournal%5C%2Fabstract%5C%2F9900%5C%2Fexamining_the_impact_of_interface_design_and_nurse.346.aspx%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T07%3A31%3A24Z%22%7D%7D%2C%7B%22key%22%3A%226Q8DMNQM%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Gavai%20and%20van%20Hillegersberg%22%2C%22parsedDate%22%3A%222025-05-06%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BGavai%2C%20Anand%20K.%2C%20and%20Jos%20van%20Hillegersberg.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40327647%5C%2F%26%23039%3B%26gt%3BAI-driven%20personalized%20nutrition%3A%20RAG-based%20digital%20health%20solution%20for%20obesity%20and%20type%202%20diabetes%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BPLOS%20Digital%20Health%26lt%3B%5C%2Fi%26gt%3B%204%2C%20no.%205%20%28May%206%2C%202025%29%3A%20e0000758.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1371%5C%2Fjournal.pdig.0000758.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22AI-driven%20personalized%20nutrition%3A%20RAG-based%20digital%20health%20solution%20for%20obesity%20and%20type%202%20diabetes%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Anand%20K.%22%2C%22lastName%22%3A%22Gavai%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jos%22%2C%22lastName%22%3A%22van%20Hillegersberg%22%7D%5D%2C%22abstractNote%22%3A%22Effective%20management%20of%20obesity%20and%20type%202%20diabetes%20is%20a%20major%20global%20public%20health%20challenge%20that%20requires%20evidence-based%2C%20scalable%20personalized%20nutrition%20solutions.%20Here%2C%20we%20present%20an%20artificial%20intelligence%20%28AI%29%20driven%20dietary%20recommendation%20system%20that%20generates%20personalized%20smoothie%20recipes%20while%20prioritizing%20health%20outcomes%20and%20environmental%20sustainability.%20A%20key%20feature%20of%20the%20system%20is%20the%20%26quot%3Bvirtual%20nutritionist%26quot%3B%2C%20an%20iterative%20validation%20framework%20that%20dynamically%20refines%20recipes%20to%20meet%20predefined%20nutritional%20and%20sustainability%20criteria.%20The%20system%20integrates%20dietary%20guidelines%20from%20the%20National%20Institute%20for%20Public%20Health%20and%20the%20Environment%20%28RIVM%29%2C%20EUFIC%2C%20USDA%20FoodData%20Central%2C%20and%20the%20American%20Diabetes%20Association%20with%20retrieval-augmented%20generation%20%28RAG%29%20to%20deliver%20evidence-based%20recommendations.%20By%20aligning%20with%20the%20United%20Nations%20Sustainable%20Development%20Goals%20%28SDGs%29%2C%20the%20system%20promotes%20plant-based%2C%20seasonal%2C%20and%20locally%20sourced%20ingredients%20to%20reduce%20environmental%20impact.%20We%20leverage%20explainable%20AI%20%28XAI%29%20to%20enhance%20user%20engagement%20through%20clear%20explanations%20of%20ingredient%20benefits%20and%20interactive%20features%2C%20improving%20comprehension%20across%20varying%20health%20literacy%20levels.%20Using%20zero-shot%20and%20few-shot%20learning%20techniques%2C%20the%20system%20adapts%20to%20user%20inputs%20while%20maintaining%20privacy%20through%20local%20deployment%20of%20the%20LLaMA3%20model.%20In%20evaluating%201%2C000%20recipes%2C%20the%20system%20achieved%2080.1%25%20adherence%20to%20health%20guidelines%20meeting%20targets%20for%20calories%2C%20fiber%2C%20and%20fats%20and%2092%25%20compliance%20with%20sustainability%20criteria%2C%20emphasizing%20seasonal%20and%20locally%20sourced%20ingredients.%20A%20prototype%20web%20application%20enables%20real-time%2C%20personalized%20recommendations%2C%20bridging%20the%20gap%20between%20AI-driven%20insights%20and%20clinical%20dietary%20management.%20This%20research%20underscores%20the%20potential%20of%20AI-driven%20precision%20nutrition%20to%20revolutionize%20chronic%20disease%20management%20by%20improving%20dietary%20adherence%2C%20enhancing%20health%20literacy%2C%20and%20offering%20a%20scalable%2C%20adaptable%20solution%20for%20clinical%20workflows%2C%20telehealth%20platforms%2C%20and%20public%20health%20initiatives%2C%20with%20the%20potential%20to%20significantly%20alleviate%20the%20global%20healthcare%20burden.%22%2C%22date%22%3A%222025-05-06%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1371%5C%2Fjournal.pdig.0000758%22%2C%22ISSN%22%3A%222767-3170%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40327647%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%22WLMB9RCY%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T08%3A36%3A15Z%22%7D%7D%2C%7B%22key%22%3A%22HG7RFPVK%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Dontchos%20et%20al.%22%2C%22parsedDate%22%3A%222025-05-06%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BDontchos%2C%20Brian%20N.%2C%20Katerina%20Dodelzon%2C%20Sonya%20Bhole%2C%20Christine%20E.%20Edmonds%2C%20Lisa%20A.%20Mullen%2C%20Jay%20R.%20Parikh%2C%20Carolyn%20P.%20Daly%2C%20James%20A.%20Epling%2C%20Soren%20Christensen%2C%20and%20Lars%20J.%20Grimm.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fwww.jacr.org%5C%2Farticle%5C%2FS1546-1440%2825%2900268-6%5C%2Fabstract%26%23039%3B%26gt%3BOpinions%20and%20preferences%20regarding%20artificial%20intelligence%20use%20in%20healthcare%20delivery%3A%20results%20from%20a%20national%20multi-site%20survey%20of%20breast%20imaging%20patients%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BJournal%20of%20the%20American%20College%20of%20Radiology%3A%20JACR%26lt%3B%5C%2Fi%26gt%3B%2C%20May%206%2C%202025%2C%20S1546-1440%2825%2900268-6.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.jacr.2025.05.001.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Opinions%20and%20preferences%20regarding%20artificial%20intelligence%20use%20in%20healthcare%20delivery%3A%20results%20from%20a%20national%20multi-site%20survey%20of%20breast%20imaging%20patients%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Brian%20N.%22%2C%22lastName%22%3A%22Dontchos%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Katerina%22%2C%22lastName%22%3A%22Dodelzon%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sonya%22%2C%22lastName%22%3A%22Bhole%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Christine%20E.%22%2C%22lastName%22%3A%22Edmonds%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lisa%20A.%22%2C%22lastName%22%3A%22Mullen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jay%20R.%22%2C%22lastName%22%3A%22Parikh%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Carolyn%20P.%22%2C%22lastName%22%3A%22Daly%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22James%20A.%22%2C%22lastName%22%3A%22Epling%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Soren%22%2C%22lastName%22%3A%22Christensen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lars%20J.%22%2C%22lastName%22%3A%22Grimm%22%7D%5D%2C%22abstractNote%22%3A%22OBJECTIVE%3A%20Artificial%20intelligence%20%28AI%29%20utilization%20is%20growing%2C%20but%20patient%20perceptions%20of%20AI%20are%20unclear.%20Our%20objective%20was%20to%20understand%20patient%20perceptions%20of%20AI%20through%20a%20multi-site%20survey%20of%20breast%20imaging%20patients.%5CnMETHODS%3A%20A%2036-question%20survey%20was%20distributed%20to%20eight%20US%20practices%20%286%20academic%2C%202%20non-academic%29%20from%20October%202023%20through%20October%202024.%20This%20manuscript%20analyzes%20a%20subset%20of%20questions%20from%20the%20survey%20addressing%20digital%20health%20literacy%20and%20attitudes%20towards%20AI%20in%20medicine%20and%20breast%20imaging%20specifically.%20Multivariable%20analysis%20compared%20responses%20by%20respondent%20demographics.%5CnRESULTS%3A%20A%20total%20of%203%2C532%20surveys%20were%20collected%20%28response%20rate%3A%2069.9%25%2C%203%2C532%5C%2F5053%29.%20Median%20respondent%20age%20was%2055%20years%20%28IQR%2020%29.%20Most%20respondents%20were%20White%20%2873.0%25%2C%202579%5C%2F3532%29%20and%20had%20completed%20college%20%2877.3%25%2C%202732%5C%2F3532%29.%20Overall%2C%20respondents%20were%20undecided%20%28range%3A%2043.2%25-50.8%25%29%20regarding%20questions%20about%20general%20perceptions%20of%20AI%20in%20healthcare.%20Respondents%20with%20higher%20electronic%20health%20literacy%2C%20more%20education%2C%20and%20younger%20age%20were%20significantly%20more%20likely%20to%20consider%20it%20useful%20to%20use%20utilize%20AI%20for%20aiding%20medical%20tasks%20%28all%20p%26lt%3B0.001%29.%20In%20contrast%2C%20respondents%20with%20lower%20electronic%20health%20literacy%20and%20less%20education%20were%20significantly%20more%20likely%20to%20indicate%20it%20was%20a%20bad%20idea%20for%20AI%20to%20perform%20medical%20tasks%20%28p%26lt%3B0.001%29.%20Non-White%20patients%20were%20more%20likely%20to%20express%20concerns%20that%20AI%20will%20not%20work%20as%20well%20for%20some%20groups%20compared%20to%20others%20%28p%26lt%3B0.05%29.%20Overall%2C%20favorable%20opinions%20of%20AI%20use%20for%20medical%20tasks%20were%20associated%20with%20younger%20age%2C%20more%20education%2C%20and%20higher%20electronic%20health%20literacy.%5CnDISCUSSION%3A%20As%20AI%20is%20increasingly%20implemented%20into%20clinical%20workflows%2C%20it%20is%20important%20to%20educate%20patients%20and%20provide%20transparency%20to%20build%20patient%20understanding%20and%20trust.%22%2C%22date%22%3A%222025-05-06%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1016%5C%2Fj.jacr.2025.05.001%22%2C%22ISSN%22%3A%221558-349X%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fwww.jacr.org%5C%2Farticle%5C%2FS1546-1440%2825%2900268-6%5C%2Fabstract%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T07%3A34%3A14Z%22%7D%7D%2C%7B%22key%22%3A%22T5AWZ8NB%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Liu%20et%20al.%22%2C%22parsedDate%22%3A%222025-05-05%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BLiu%2C%20Sizuo%2C%20Yufen%20Lin%2C%20Runze%20Yan%2C%20Zhiyuan%20Wang%2C%20Delgersuren%20Bold%2C%20and%20Xiao%20Hu.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40324958%5C%2F%26%23039%3B%26gt%3BLeveraging%20Artificial%20Intelligence%20for%20Digital%20Symptom%20Management%20in%20Oncology%3A%20The%20Development%20of%20CRCWeb%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BJMIR%20Cancer%26lt%3B%5C%2Fi%26gt%3B%2C%20May%205%2C%202025.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.2196%5C%2F68516.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Leveraging%20Artificial%20Intelligence%20for%20Digital%20Symptom%20Management%20in%20Oncology%3A%20The%20Development%20of%20CRCWeb%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sizuo%22%2C%22lastName%22%3A%22Liu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yufen%22%2C%22lastName%22%3A%22Lin%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Runze%22%2C%22lastName%22%3A%22Yan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Zhiyuan%22%2C%22lastName%22%3A%22Wang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Delgersuren%22%2C%22lastName%22%3A%22Bold%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xiao%22%2C%22lastName%22%3A%22Hu%22%7D%5D%2C%22abstractNote%22%3A%22UNSTRUCTURED%3A%20Digital%20health%20interventions%20offer%20promise%20for%20scalable%20and%20accessible%20healthcare%2C%20but%20access%20is%20still%20limited%20by%20some%20participatory%20challenges%2C%20especially%20for%20disadvantaged%20families%20facing%20limited%20health%20literacy%2C%20language%20barriers%2C%20low%20income%2C%20or%20living%20in%20marginalized%20areas.%20These%20issues%20are%20particularly%20pronounced%20for%20colorectal%20cancer%20%28CRC%29%20patients%2C%20who%20often%20experience%20distressing%20symptoms%20and%20struggle%20with%20educational%20materials%20due%20to%20complex%20jargon%2C%20fatigue%2C%20or%20reading%20level%20mismatches.%20To%20address%20these%20issues%2C%20we%20developed%20and%20assessed%20the%20feasibility%20of%20a%20digital%20health%20platform%2C%20CRCWeb%2C%20to%20improve%20the%20accessibility%20of%20educational%20resources%20on%20symptom%20management%20for%20disadvantaged%20CRC%20patients%20and%20their%20caregivers%20facing%20limited%20health%20literacy%20or%20low%20income.%20CRCWeb%20was%20developed%20through%20a%20stakeholder-centered%20participatory%20design%20approach.%20Two-phase%20semi-structured%20interviews%20with%20patients%2C%20caregivers%2C%20and%20oncology%20experts%20informed%20the%20iterative%20design%20process.%20From%20the%20interviews%2C%20we%20developed%20the%20following%20five%20key%20design%20principles%3A%20user-friendly%20navigation%2C%20multimedia%20integration%2C%20concise%20and%20clear%20content%2C%20enhanced%20accessibility%20for%20individuals%20with%20vision%20and%20reading%20disabilities%2C%20and%20scalability%20for%20future%20content%20expansion.%20Initial%20feedback%20from%20iterative%20stakeholder%20engagements%20confirmed%20high%20user%20satisfaction%2C%20with%20participants%20rating%20CRCWeb%20an%20average%20of%203.98%20out%20of%205%20on%20the%20post-intervention%20survey.%20Additionally%2C%20using%20GenAI%20tools%2C%20including%20large%20language%20models%20%28LLMs%29%20like%20ChatGPT%20and%20multimedia%20generation%20tools%20such%20as%20Pictory%2C%20complex%20healthcare%20guidelines%20were%20transformed%20into%20concise%2C%20easily%20comprehensible%20multimedia%20content%2C%20and%20made%20accessible%20through%20CRCWeb.%20User%20engagement%20was%20notably%20higher%20among%20disadvantaged%20participants%20with%20limited%20health%20literacy%20or%20low%20income%2C%20who%20logged%20into%20the%20platform%202.52%20times%20more%20frequently%20than%20non-disadvantaged%20participants.%20The%20structured%20development%20approach%20of%20CRCWeb%20demonstrates%20that%20GenAI-powered%20multimedia%20interventions%20can%20effectively%20address%20healthcare%20accessibility%20barriers%20faced%20by%20disadvantaged%20CRC%20patients%20and%20caregivers%20with%20limited%20health%20literacy%20or%20low%20income.%20This%20structured%20approach%20highlights%20how%20digital%20innovations%20can%20enhance%20healthcare.%5CnINTERNATIONAL%20REGISTERED%20REPORT%3A%20RR2-10.2196%5C%2F48499.%22%2C%22date%22%3A%222025-05-05%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.2196%5C%2F68516%22%2C%22ISSN%22%3A%222369-1999%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40324958%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T07%3A38%3A03Z%22%7D%7D%2C%7B%22key%22%3A%22KQ5KCIRA%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Zeiler%20et%20al.%22%2C%22parsedDate%22%3A%222025-05-05%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BZeiler%2C%20Michael%2C%20Sandra%20V%26%23xF6%3Bgl%2C%20Ursula%20Prinz%2C%20Nino%20Werner%2C%20Gudrun%20Wagner%2C%20Andreas%20Karwautz%2C%20Natalie%20Zeller%2C%20Lorenz%20Ackermann%2C%20and%20Karin%20Waldherr.%20%26%23x201C%3BGame%20Design%2C%20Effectiveness%2C%20and%20Implementation%20of%20Serious%20Games%20Promoting%20Aspects%20of%20Mental%20Health%20Literacy%20Among%20Children%20and%20Adolescents%3A%20Systematic%20Review.%26%23x201D%3B%20%26lt%3Bi%26gt%3BJMIR%20Mental%20Health%26lt%3B%5C%2Fi%26gt%3B%2012%20%28May%205%2C%202025%29%3A%20e67418.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.2196%5C%2F67418%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.2196%5C%2F67418%26lt%3B%5C%2Fa%26gt%3B.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Game%20Design%2C%20Effectiveness%2C%20and%20Implementation%20of%20Serious%20Games%20Promoting%20Aspects%20of%20Mental%20Health%20Literacy%20Among%20Children%20and%20Adolescents%3A%20Systematic%20Review%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%22%2C%22lastName%22%3A%22Zeiler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sandra%22%2C%22lastName%22%3A%22V%5Cu00f6gl%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ursula%22%2C%22lastName%22%3A%22Prinz%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nino%22%2C%22lastName%22%3A%22Werner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gudrun%22%2C%22lastName%22%3A%22Wagner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Andreas%22%2C%22lastName%22%3A%22Karwautz%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Natalie%22%2C%22lastName%22%3A%22Zeller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lorenz%22%2C%22lastName%22%3A%22Ackermann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Karin%22%2C%22lastName%22%3A%22Waldherr%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20The%20effects%20of%20traditional%20health-promoting%20and%20preventive%20interventions%20in%20mental%20health%20and%20mental%20health%20literacy%20are%20often%20attenuated%20by%20low%20adherence%20and%20user%20engagement.%20Gamified%20approaches%20such%20as%20serious%20games%20%28SGs%29%20may%20be%20useful%20to%20reach%20and%20engage%20youth%20for%20mental%20health%20prevention%20and%20promotion.%5CnOBJECTIVE%3A%20This%20study%20aims%20to%20systematically%20review%20the%20literature%20on%20SGs%20designed%20to%20promote%20aspects%20of%20mental%20health%20literacy%20among%20adolescents%20aged%2010%20to%2014%20years%2C%20focusing%20on%20game%20design%20characteristics%20and%20the%20evaluation%20of%20user%20engagement%2C%20as%20well%20as%20efficacy%2C%20effectiveness%2C%20and%20implementation-related%20factors.%5CnMETHODS%3A%20We%20searched%20PubMed%2C%20Scopus%2C%20and%20PsycINFO%20for%20original%20studies%2C%20intervention%20development%20studies%2C%20and%20study%20protocols%20that%20described%20the%20development%2C%20characteristics%2C%20and%20evaluation%20of%20SG%20interventions%20promoting%20aspects%20of%20mental%20health%20literacy%20among%20adolescents%20aged%2010%20to%2014%20years.%20We%20included%20SGs%20developed%20for%20both%20universal%20and%20selected%20prevention.%20Using%20the%20co.LAB%20framework%2C%20which%20considers%20aspects%20of%20learning%20design%2C%20game%20mechanics%2C%20and%20game%20design%2C%20we%20coded%20the%20design%20elements%20of%20the%20SGs%20described%20in%20the%20studies.%20We%20coded%20the%20characteristics%20of%20the%20evaluation%20studies%3B%20indicators%20of%20efficacy%2C%20effectiveness%2C%20and%20user%20engagement%3B%20and%20factors%20potentially%20fostering%20or%20hindering%20the%20reach%2C%20efficacy%20and%20effectiveness%2C%20organizational%20adoption%2C%20implementation%2C%20and%20maintenance%20of%20the%20SGs.%5CnRESULTS%3A%20We%20retrieved%201454%20records%20through%20database%20searches%20and%20other%20sources.%20Of%20these%2C%2036%20%282.48%25%29%20studies%20describing%2017%20distinct%20SGs%20were%20included%20in%20the%20review.%20Most%20of%20the%20SGs%20%2814%5C%2F17%2C%2082%25%29%20were%20targeted%20to%20a%20universal%20population%20of%20youth%2C%20with%20learning%20objectives%20mainly%20focusing%20on%20how%20to%20obtain%20and%20maintain%20good%20mental%20health%20and%20on%20enhancing%20help-seeking%20efficacy.%20All%20SGs%20were%20single-player%20games%2C%20and%20many%20%287%5C%2F17%2C%2041%25%29%20were%20embedded%20within%20a%20wider%20pedagogical%20scenario.%20Diverse%20game%20mechanics%20and%20game%20elements%20%28eg%2C%20minigames%20and%20quizzes%29%20were%20used%20to%20foster%20user%20engagement.%20Most%20of%20the%20SGs%20%2812%5C%2F17%2C%2071%25%29%20featured%20an%20overarching%20storyline%20resembling%20real-world%20scenarios%2C%20fictional%20scenarios%2C%20or%20a%20combination%20of%20both.%20The%20evaluation%20studies%20provided%20evidence%20for%20the%20short-term%20efficacy%20and%20effectiveness%20of%20SGs%20in%20improving%20aspects%20of%20mental%20health%20literacy%20as%20well%20as%20their%20feasibility.%20However%2C%20the%20evidence%20was%20mostly%20based%20on%20small%20samples%2C%20and%20user%20adherence%20was%20sometimes%20low.%5CnCONCLUSIONS%3A%20The%20results%20of%20this%20review%20may%20inform%20the%20future%20development%20and%20implementation%20of%20SGs%20for%20adolescents.%20Intervention%20co-design%2C%20the%20involvement%20of%20facilitators%20%28eg%2C%20teachers%29%2C%20and%20the%20use%20of%20diverse%20game%20mechanics%20and%20customization%20to%20meet%20the%20needs%20of%20diverse%20users%20are%20examples%20of%20elements%20that%20may%20promote%20intervention%20success.%20Although%20there%20is%20promising%20evidence%20for%20the%20efficacy%20and%20effectiveness%20of%20SGs%20for%20promoting%20mental%20health%20literacy%20in%20youth%2C%20there%20is%20a%20need%20for%20more%20rigorously%20planned%20studies%2C%20including%20randomized%20controlled%20trials%20and%20real-world%20evaluations%2C%20that%20involve%20follow-up%20measures%20and%20the%20assessment%20of%20in-game%20performance%20alongside%20self-reports.%22%2C%22date%22%3A%222025-05-05%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.2196%5C%2F67418%22%2C%22ISSN%22%3A%222368-7959%22%2C%22url%22%3A%22%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%22T28GHHN8%22%2C%224UVUVQXJ%22%2C%22KNNQITEB%22%5D%2C%22dateModified%22%3A%222025-05-17T20%3A48%3A26Z%22%7D%7D%2C%7B%22key%22%3A%22VER8J56Z%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Kelly%20et%20al.%22%2C%22parsedDate%22%3A%222025-05-05%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BKelly%2C%20Anthony%2C%20Eoin%20Noctor%2C%20Laura%20Ryan%2C%20and%20Pepijn%20van%20de%20Ven.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fwww.jmir.org%5C%2F2025%5C%2F1%5C%2Fe70131%26%23039%3B%26gt%3BThe%20Effectiveness%20of%20a%20Custom%20AI%20Chatbot%20for%20Type%202%20Diabetes%20Mellitus%20Health%20Literacy%3A%20Development%20and%20Evaluation%20Study%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BJournal%20of%20Medical%20Internet%20Research%26lt%3B%5C%2Fi%26gt%3B%2027%20%28May%205%2C%202025%29%3A%20e70131.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.2196%5C%2F70131.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22The%20Effectiveness%20of%20a%20Custom%20AI%20Chatbot%20for%20Type%202%20Diabetes%20Mellitus%20Health%20Literacy%3A%20Development%20and%20Evaluation%20Study%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Anthony%22%2C%22lastName%22%3A%22Kelly%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Eoin%22%2C%22lastName%22%3A%22Noctor%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Laura%22%2C%22lastName%22%3A%22Ryan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pepijn%22%2C%22lastName%22%3A%22van%20de%20Ven%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20People%20living%20with%20chronic%20diseases%20are%20increasingly%20seeking%20health%20information%20online.%20For%20individuals%20with%20diabetes%2C%20traditional%20educational%20materials%20often%20lack%20reliability%20and%20fail%20to%20engage%20or%20empower%20them%20effectively.%20Innovative%20approaches%20such%20as%20retrieval-augmented%20generation%20%28RAG%29%20powered%20by%20large%20language%20models%20have%20the%20potential%20to%20enhance%20health%20literacy%20by%20delivering%20interactive%2C%20medically%20accurate%2C%20and%20user-focused%20resources%20based%20on%20trusted%20sources.%5CnOBJECTIVE%3A%20This%20study%20aimed%20to%20evaluate%20the%20effectiveness%20of%20a%20custom%20RAG-based%20artificial%20intelligence%20chatbot%20designed%20to%20improve%20health%20literacy%20on%20type%202%20diabetes%20mellitus%20%28T2DM%29%20by%20sourcing%20information%20from%20validated%20reference%20documents%20and%20attributing%20sources.%5CnMETHODS%3A%20A%20T2DM%20chatbot%20was%20developed%20using%20a%20fixed%20prompt%20and%20reference%20documents.%20Two%20evaluations%20were%20performed%3A%20%281%29%20a%20curated%20set%20of%2044%20questions%20assessed%20by%20specialists%20for%20appropriateness%20%28appropriate%2C%20partly%20appropriate%2C%20or%20inappropriate%29%20and%20source%20attribution%20%28matched%2C%20partly%20matched%2C%20unmatched%2C%20or%20general%20knowledge%29%20and%20%282%29%20a%20simulated%20consultation%20of%2016%20queries%20reflecting%20a%20typical%20patient%26%23039%3Bs%20concerns.%5CnRESULTS%3A%20Of%20the%2044%20evaluated%20questions%2C%2032%20%2873%25%29%20responses%20cited%20reference%20documents%2C%20and%2012%20%2827%25%29%20were%20attributed%20to%20general%20knowledge.%20Among%20the%2032%20sourced%20responses%2C%2030%20%2894%25%29%20were%20deemed%20fully%20appropriate%2C%20with%20the%20remaining%202%20%286%25%29%20being%20deemed%20partly%20appropriate.%20Of%20the%2012%20general%20knowledge%20responses%2C%201%20%288%25%29%20was%20inappropriate.%20In%20the%2016-question%20simulated%20consultation%2C%20all%20responses%20%28100%25%29%20were%20fully%20appropriate%20and%20sourced%20from%20the%20reference%20documents.%5CnCONCLUSIONS%3A%20A%20RAG-based%20large%20language%20model%20chatbot%20can%20deliver%20contextually%20appropriate%2C%20empathetic%2C%20and%20clinically%20credible%20responses%20to%20T2DM%20queries.%20By%20consistently%20citing%20trusted%20sources%20and%20notifying%20users%20when%20relying%20on%20general%20knowledge%2C%20this%20approach%20enhances%20transparency%20and%20trust.%20The%20findings%20have%20relevance%20for%20health%20educators%2C%20highlighting%20that%20patient-centric%20reference%20documents-structured%20to%20address%20frequent%20patient%20questions-are%20particularly%20effective.%20Moreover%2C%20instances%20in%20which%20the%20chatbot%20signals%20that%20it%20has%20drawn%20on%20general%20knowledge%20can%20provide%20opportunities%20for%20health%20educators%20to%20refine%20and%20expand%20their%20materials%2C%20ensuring%20that%20more%20future%20queries%20are%20answered%20from%20trusted%20sources.%20The%20findings%20suggest%20that%20such%20chatbots%20may%20support%20patient%20education%2C%20promote%20self-management%2C%20and%20be%20readily%20adapted%20to%20other%20health%20contexts.%22%2C%22date%22%3A%222025-05-05%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.2196%5C%2F70131%22%2C%22ISSN%22%3A%221438-8871%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fwww.jmir.org%5C%2F2025%5C%2F1%5C%2Fe70131%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-20T11%3A04%3A32Z%22%7D%7D%2C%7B%22key%22%3A%22X32HKCB7%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Berger-Estilita%20et%20al.%22%2C%22parsedDate%22%3A%222025-05-04%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BBerger-Estilita%2C%20Joana%2C%20Mia%20Gisselbaek%2C%20Arnout%20Devos%2C%20Albert%20Chan%2C%20Pier%20Luigi%20Ingrassia%2C%20Basak%20Ceyda%20Meco%2C%20Odmara%20L.%20Barreto%20Chang%2C%20et%20al.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40320548%5C%2F%26%23039%3B%26gt%3BAI%20and%20inclusion%20in%20simulation%20education%20and%20leadership%3A%20a%20global%20cross-sectional%20evaluation%20of%20diversity%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BAdvances%20in%20Simulation%20%28London%2C%20England%29%26lt%3B%5C%2Fi%26gt%3B%2010%2C%20no.%201%20%28May%204%2C%202025%29%3A%2026.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1186%5C%2Fs41077-025-00355-1.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22AI%20and%20inclusion%20in%20simulation%20education%20and%20leadership%3A%20a%20global%20cross-sectional%20evaluation%20of%20diversity%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Joana%22%2C%22lastName%22%3A%22Berger-Estilita%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Mia%22%2C%22lastName%22%3A%22Gisselbaek%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Arnout%22%2C%22lastName%22%3A%22Devos%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Albert%22%2C%22lastName%22%3A%22Chan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pier%20Luigi%22%2C%22lastName%22%3A%22Ingrassia%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Basak%20Ceyda%22%2C%22lastName%22%3A%22Meco%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Odmara%20L.%20Barreto%22%2C%22lastName%22%3A%22Chang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Georges%20L.%22%2C%22lastName%22%3A%22Savoldelli%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Francisco%20Maio%22%2C%22lastName%22%3A%22Matos%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Peter%22%2C%22lastName%22%3A%22Dieckmann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Doris%22%2C%22lastName%22%3A%22%5Cu00d8stergaard%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sarah%22%2C%22lastName%22%3A%22Saxena%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20Simulation-based%20medical%20education%20%28SBME%29%20is%20a%20critical%20training%20tool%20in%20healthcare%2C%20shaping%20learners%26%23039%3B%20skills%2C%20professional%20identities%2C%20and%20inclusivity.%20Leadership%20demographics%20in%20SBME%2C%20including%20age%2C%20gender%2C%20race%5C%2Fethnicity%2C%20and%20medical%20specialties%2C%20influence%20program%20design%20and%20learner%20outcomes.%20Artificial%20intelligence%20%28AI%29%20platforms%20increasingly%20generate%20demographic%20data%2C%20but%20their%20biases%20may%20perpetuate%20inequities%20in%20representation.%20This%20study%20evaluated%20the%20demographic%20profiles%20of%20simulation%20instructors%20and%20heads%20of%20simulation%20labs%20generated%20by%20three%20AI%20platforms-ChatGPT%2C%20Gemini%2C%20and%20Claude-across%20nine%20global%20locations.%5CnMETHODS%3A%20A%20global%20cross-sectional%20study%20was%20conducted%20over%205%5Cu00a0days%20%28November%202024%29.%20Standardized%20English%20prompts%20were%20used%20to%20generate%20demographic%20profiles%20of%20simulation%20instructors%20and%20heads%20of%20simulation%20labs%20from%20ChatGPT%2C%20Gemini%2C%20and%20Claude.%20Outputs%20included%20age%2C%20gender%2C%20race%5C%2Fethnicity%2C%20and%20medical%20specialty%20data%20for%202014%20instructors%20and%201880%20lab%20heads.%20Statistical%20analyses%20included%20ANOVA%20for%20continuous%20variables%20and%20chi-square%20tests%20for%20categorical%20data%2C%20with%20Bonferroni%20corrections%20for%20multiple%20comparisons%3A%20P%20significant%5Cu2009%26lt%3B%5Cu20090.05.%5CnRESULTS%3A%20Significant%20demographic%20differences%20were%20observed%20among%20AI%20platforms.%20Claude%20profiles%20depicted%20older%20heads%20of%20simulation%20labs%20%28mean%3A%2057%5Cu00a0years%29%20compared%20to%20instructors%20%28mean%3A%2041%5Cu00a0years%29%2C%20while%20ChatGPT%20and%20Gemini%20showed%20smaller%20age%20gaps.%20Gender%20representation%20varied%2C%20with%20ChatGPT%20and%20Gemini%20generating%20balanced%20profiles%2C%20while%20Claude%20showed%20a%20male%20predominance%20%2863.5%25%29%20among%20lab%20heads.%20ChatGPT%20and%20Gemini%20outputs%20reflected%20greater%20racial%20diversity%2C%20with%20up%20to%2024.4%25%20Black%20and%2020.6%25%20Hispanic%5C%2FLatin%20representation%2C%20while%20Claude%20predominantly%20featured%20White%20profiles%20%2847.8%25%29.%20Specialty%20preferences%20also%20differed%2C%20with%20Claude%20favoring%20anesthesiology%20and%20surgery%2C%20whereas%20ChatGPT%20and%20Gemini%20offered%20broader%20interdisciplinary%20representation.%5CnCONCLUSIONS%3A%20AI-generated%20demographic%20profiles%20of%20SBME%20leadership%20reveal%20biases%20that%20may%20reinforce%20inequities%20in%20healthcare%20education.%20ChatGPT%20and%20Gemini%20demonstrated%20broader%20diversity%20in%20age%2C%20gender%2C%20and%20race%2C%20while%20Claude%20skewed%20towards%20older%2C%20White%2C%20and%20male%20profiles%2C%20particularly%20for%20leadership%20roles.%20Addressing%20these%20biases%20through%20ethical%20AI%20development%2C%20enhanced%20AI%20literacy%2C%20and%20promoting%20diverse%20leadership%20in%20SBME%20are%20essential%20to%20fostering%20equitable%20and%20inclusive%20training%20environments.%5CnTRIAL%20REGISTRATION%3A%20Not%20applicable.%20This%20study%20exclusively%20used%20AI-generated%20synthetic%20data.%22%2C%22date%22%3A%222025-05-04%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1186%5C%2Fs41077-025-00355-1%22%2C%22ISSN%22%3A%222059-0628%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40320548%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T07%3A40%3A34Z%22%7D%7D%2C%7B%22key%22%3A%22AH258GPH%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Agaoglu%20et%20al.%22%2C%22parsedDate%22%3A%222025-05-02%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BAgaoglu%2C%20Ferhat%20Onur%2C%20Murat%20Bas%2C%20Sinan%20Tarsuslu%2C%20Lokman%20Onur%20Ekinci%2C%20and%20Nihat%20Bugra%20Agaoglu.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40316954%5C%2F%26%23039%3B%26gt%3BThe%20mediating%20digital%20literacy%20and%20the%20moderating%20role%20of%20academic%20support%20in%20the%20relationship%20between%20artificial%20intelligence%20usage%20and%20creative%20thinking%20in%20nursing%20students%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BBMC%20Nursing%26lt%3B%5C%2Fi%26gt%3B%2024%2C%20no.%201%20%28May%202%2C%202025%29%3A%20484.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1186%5C%2Fs12912-025-03128-3.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22The%20mediating%20digital%20literacy%20and%20the%20moderating%20role%20of%20academic%20support%20in%20the%20relationship%20between%20artificial%20intelligence%20usage%20and%20creative%20thinking%20in%20nursing%20students%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ferhat%20Onur%22%2C%22lastName%22%3A%22Agaoglu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Murat%22%2C%22lastName%22%3A%22Bas%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sinan%22%2C%22lastName%22%3A%22Tarsuslu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lokman%20Onur%22%2C%22lastName%22%3A%22Ekinci%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nihat%20Bugra%22%2C%22lastName%22%3A%22Agaoglu%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20Artificial%20intelligence%20can%20be%20an%20important%20tool%20in%20developing%20creative%20thinking%20while%20supporting%20individualized%20learning%20and%20problem-solving%20skills%20in%20educational%20processes.%20However%2C%20the%20effect%20of%20artificial%20intelligence%20on%20creative%20thinking%20may%20differ%20depending%20on%20factors%20such%20as%20students%26%23039%3B%20digital%20literacy%20level%20and%20the%20academic%20support%20they%20receive.%20In%20this%20context%2C%20how%20artificial%20intelligence%20can%20encourage%20creative%20thinking%20in%20educational%20processes%20and%20how%20this%20process%20is%20shaped%20by%20digital%20literacy%20and%20academic%20support%20stands%20out%20as%20an%20issue%20to%20be%20investigated.%5CnPURPOSE%3A%20This%20study%20artificial%20intelligence%20to%20determine%20the%20effect%20of%20artificial%20intelligence%20use%20on%20creative%20thinking%20skills%20in%20nursing%20students%2C%20the%20mediating%20role%20of%20digital%20literacy%20in%20this%20effect%2C%20and%20the%20situational%20mediating%20effect%20of%20academic%20support.%5CnMETHOD%3A%20This%20cross-sectional%20and%20descriptive%20correlational%20study%20was%20conducted%20with%20426%20nursing%20students%20from%20three%20universities%20in%20different%20regions%20of%20Turkey%20during%20the%20fall%20semester%20of%202024-2025.%20Simple%20random%20sampling%20method%20was%20used.%20Data%20were%20collected%20through%20demographic%20information%20form%20and%20four%20valid%20and%20reliable%20scales.%5CnRESULT%3A%20Research%20findings%20show%20that%20using%20artificial%20intelligence%20substantially%20and%20significantly%20affects%20Creative%20Thinking%20%28%5Cu03b2%5Cu2009%3D%5Cu20090.70%2C%20p%5Cu2009%26lt%3B%5Cu20090.001%29.%20Digital%20literacy%20plays%20mediating%20role%20in%20this%20relationship%2C%20indirectly%20strengthening%20the%20effect%20of%20artificial%20intelligence%20use%20on%20creative%20thinking%20%28%5Cu03b2%5Cu2009%3D%5Cu20090.422%2C%20LLCI%5Cu2009%3D%5Cu20090.357%2C%20ULCI%5Cu2009%3D%5Cu20090.490%29.%20As%20a%20moderating%20factor%20of%20this%20relationship%2C%20the%20academic%20support%20creates%20a%20more%20limited%20effect%20at%20low%20levels%20of%20academic%20support%20%28Effect%5Cu2009%3D%5Cu20090.224%29.%20At%20the%20same%20time%2C%20it%20maximizes%20this%20effect%20at%20high%20levels%20of%20support%20%28Effect%5Cu2009%3D%5Cu20090.298%29.%5CnCONCLUSION%3A%20The%20effect%20of%20artificial%20intelligence%20use%20on%20Creative%20Thinking%20is%20significantly%20strengthened%20by%20the%20mediating%20role%20of%20digital%20literacy%20and%20the%20moderating%20role%20of%20academic%20support.%20These%20findings%20suggest%20that%20developing%20digital%20skills%20and%20strengthening%20academic%20support%20mechanisms%20are%20critical%20to%20integrating%20artificial%20intelligence%20technologies%20into%20educational%20processes.%22%2C%22date%22%3A%222025-05-02%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1186%5C%2Fs12912-025-03128-3%22%2C%22ISSN%22%3A%221472-6955%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40316954%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%226DCTQ3Z4%22%2C%224UVUVQXJ%22%2C%22ZSSYT9DV%22%5D%2C%22dateModified%22%3A%222025-05-21T07%3A44%3A23Z%22%7D%7D%2C%7B%22key%22%3A%22J9XDC6QX%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Wang%20et%20al.%22%2C%22parsedDate%22%3A%222025-05-02%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BWang%2C%20Bo%2C%20Cecilie%20Katrine%20Gr%5Cu00f8nvik%2C%20Karen%20Fortuna%2C%20Trude%20Eines%2C%20Ingunn%20Mundal%2C%20and%20Marianne%20Storm.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40326646%5C%2F%26%23039%3B%26gt%3BWhat%20Is%20in%20There%20for%20Artificial%20Intelligence%20to%20Support%20Mental%20Health%20Care%20for%20Persons%20with%20Serious%20Mental%20Illness%3F%20Opportunities%20and%20Challenges%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BStudies%20in%20Health%20Technology%20and%20Informatics%26lt%3B%5C%2Fi%26gt%3B%20325%20%28May%202%2C%202025%29%3A%208%5Cu201315.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.3233%5C%2FSHTI250208.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22What%20Is%20in%20There%20for%20Artificial%20Intelligence%20to%20Support%20Mental%20Health%20Care%20for%20Persons%20with%20Serious%20Mental%20Illness%3F%20Opportunities%20and%20Challenges%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bo%22%2C%22lastName%22%3A%22Wang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Cecilie%20Katrine%22%2C%22lastName%22%3A%22Gr%5Cu00f8nvik%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Karen%22%2C%22lastName%22%3A%22Fortuna%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Trude%22%2C%22lastName%22%3A%22Eines%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ingunn%22%2C%22lastName%22%3A%22Mundal%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marianne%22%2C%22lastName%22%3A%22Storm%22%7D%5D%2C%22abstractNote%22%3A%22Artificial%20intelligence%20%28AI%29%20holds%20potential%20to%20support%20persons%20with%20serious%20mental%20illness%2C%20but%20evidence%20remains%20limited.%20To%20explore%20opportunities%20and%20challenges%20there%2C%20we%20conducted%20qualitative%20interviews%20with%20multiple%20Norwegian%20mental%20health%20stakeholders.%20Data%20was%20analyzed%20using%20thematic%20analysis%20and%20sentiment%20analysis.%20Twenty-two%20informants%20shared%20their%20opinions%2C%20with%20half%20expressing%20moderately%20negative%20sentiments.%20Findings%20suggest%20AI%20can%20optimize%20mental%20health%20service%20delivery%20and%20encourage%20a%20flexible%20approach%20to%20recovery.%20However%2C%20AI%26%23039%3Bs%20ability%20to%20provide%20emotional%20support%20may%20inadvertently%20worsen%20isolation%2C%20highlighting%20the%20need%20for%20a%20more%20holistic%20approach%20to%20human%20oversight%20and%20personal%20adaptation.%20Enhancing%20AI%20literacy%20and%20gathering%20more%20evidence%20from%20both%20persons%20and%20service%20providers%20is%20essential%20for%20future%20development.%22%2C%22date%22%3A%222025-05-02%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.3233%5C%2FSHTI250208%22%2C%22ISSN%22%3A%221879-8365%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40326646%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T07%3A37%3A02Z%22%7D%7D%2C%7B%22key%22%3A%22WEL8T9JH%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Nickel%20et%20al.%22%2C%22parsedDate%22%3A%222025-05%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BNickel%2C%20Brooke%2C%20Julie%20Ayre%2C%20M.%20Luke%20Marinovich%2C%20David%20P.%20Smith%2C%20Karen%20Chiam%2C%20Christoph%20I.%20Lee%2C%20Timothy%20J.%20Wilt%2C%20Melody%20Taba%2C%20Kirsten%20McCaffery%2C%20and%20Nehmat%20Houssami.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F39862490%5C%2F%26%23039%3B%26gt%3BAre%20AI%20chatbots%20concordant%20with%20evidence-based%20cancer%20screening%20recommendations%3F%26lt%3B%5C%2Fa%26gt%3B%26quot%3B%20%26lt%3Bi%26gt%3BPatient%20Education%20and%20Counseling%26lt%3B%5C%2Fi%26gt%3B%20134%20%28May%202025%29%3A%20108677.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.pec.2025.108677.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Are%20AI%20chatbots%20concordant%20with%20evidence-based%20cancer%20screening%20recommendations%3F%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Brooke%22%2C%22lastName%22%3A%22Nickel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Julie%22%2C%22lastName%22%3A%22Ayre%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22M.%20Luke%22%2C%22lastName%22%3A%22Marinovich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22David%20P.%22%2C%22lastName%22%3A%22Smith%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Karen%22%2C%22lastName%22%3A%22Chiam%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Christoph%20I.%22%2C%22lastName%22%3A%22Lee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Timothy%20J.%22%2C%22lastName%22%3A%22Wilt%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Melody%22%2C%22lastName%22%3A%22Taba%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kirsten%22%2C%22lastName%22%3A%22McCaffery%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nehmat%22%2C%22lastName%22%3A%22Houssami%22%7D%5D%2C%22abstractNote%22%3A%22OBJECTIVE%3A%20This%20study%20aimed%20to%20assess%20whether%20information%20from%20AI%20chatbots%20on%20benefits%20and%20harms%20of%20breast%20and%20prostate%20cancer%20screening%20were%20concordant%20with%20evidence-based%20cancer%20screening%20recommendations.%5CnMETHODS%3A%20Seven%20unique%20prompts%20%28four%20breast%20cancer%3B%20three%20prostate%20cancer%29%20were%20presented%20to%20ChatGPT%20in%20March%202024.%20A%20total%20of%2060%20criteria%20%2830%20breast%3B%2030%20prostate%29%20were%20used%20to%20assess%20the%20concordance%20of%20information.%20Concordance%20was%20scored%20between%200%20and%202%20against%20the%20United%20States%20Preventive%20Services%20Task%20Force%20%28USPSTF%29%20breast%20and%20prostate%20cancer%20screening%20recommendations%20independently%20by%20international%20cancer%20screening%20experts.%5CnRESULTS%3A%2043%20of%2060%20%2871.7%5Cu202f%25%29%20criteria%20were%20completely%20concordant%2C%203%20%285%5Cu202f%25%29%20were%20moderately%20concordant%20and%2014%20%2823.3%5Cu202f%25%29%20were%20not%20concordant%20or%20not%20present%2C%20with%20most%20of%20the%20non-concordant%20criteria%20%289%20of%2014%2C%2064.3%20%25%29%20being%20from%20prompts%20for%20the%20oldest%20age%20groups.%20ChatGPT%20hallucinations%20%28i.e.%2C%20completely%20made%20up%2C%20non-sensical%20or%20irrelevant%20information%29%20were%20found%20in%209%20of%2060%20criteria%20%2815%5Cu202f%25%29.%5CnCONCLUSIONS%3A%20ChatGPT%20provided%20information%20mostly%20concordant%20with%20USPSTF%20breast%20and%20prostate%20cancer%20screening%20recommendations%2C%20however%2C%20important%20gaps%20exist.%20These%20findings%20provide%20insights%20into%20the%20role%20of%20AI%20to%20communicate%20cancer%20screening%20benefits%20and%20harms%20and%20hold%20increased%20relevance%20for%20periods%20of%20guideline%20change.%5CnPRACTICE%20IMPLICATIONS%3A%20AI%20generated%20information%20on%20cancer%20screening%20should%20be%20taken%20in%20conjunction%20with%20official%20screening%20recommendations%20and%5C%2For%20information%20from%20clinicians.%22%2C%22date%22%3A%222025-05%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1016%5C%2Fj.pec.2025.108677%22%2C%22ISSN%22%3A%221873-5134%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F39862490%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T09%3A40%3A34Z%22%7D%7D%2C%7B%22key%22%3A%22VZFT8GQM%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Weber%20et%20al.%22%2C%22parsedDate%22%3A%222025-05%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BWeber%2C%20V.%2C%20A.%20Truelove%2C%20S.%20S.%20Gohari%2C%20L.%20A.%20Wynne%2C%20R.%20J.%20Kearns%2C%20and%20J.%20E.%20O%26%23039%3BCarroll.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40174427%5C%2F%26%23039%3B%26gt%3BOnline%20patient%20information%20on%20labour%20epidural%20analgesia%20provided%20by%20UK%20National%20Health%20Services%20hospitals%3A%20assessment%20of%20readability%20and%20improvement%20of%20readability%20standards%20using%20ChatGPT%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BInternational%20Journal%20of%20Obstetric%20Anesthesia%26lt%3B%5C%2Fi%26gt%3B%2062%20%28May%202025%29%3A%20104344.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.ijoa.2025.104344.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Online%20patient%20information%20on%20labour%20epidural%20analgesia%20provided%20by%20UK%20National%20Health%20Services%20hospitals%3A%20assessment%20of%20readability%20and%20improvement%20of%20readability%20standards%20using%20ChatGPT%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22V.%22%2C%22lastName%22%3A%22Weber%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22A.%22%2C%22lastName%22%3A%22Truelove%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22S.%20S.%22%2C%22lastName%22%3A%22Gohari%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22L.%20A.%22%2C%22lastName%22%3A%22Wynne%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22R.%20J.%22%2C%22lastName%22%3A%22Kearns%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22J.%20E.%22%2C%22lastName%22%3A%22O%27Carroll%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20Labour%20epidurals%20are%20considered%20the%20gold%20standard%20for%20labour%20analgesia%20in%20pregnant%20patients.%20Inequities%20in%20health%20literacy%20levels%20can%20negatively%20impact%20understanding%20of%20online%20patient%20education%20materials%2C%20potentially%20affecting%20uptake%20of%20labour%20epidural%20analgesia.%20Generative%20artificial%20technology%20such%20as%20ChatGPT%20may%20be%20able%20to%20improve%20readability%20of%20patient%20information%20materials.%5CnOBJECTIVES%3A%20Firstly%2C%20to%20assess%20the%20readability%20of%20available%20online%20materials%20on%20labour%20epidurals%20in%20the%20United%20Kingdom%20%28UK%29.%20Secondly%2C%20to%20evaluate%20the%20ability%20of%20generative%20artificial%20technology%20to%20improve%20readability.%5CnMETHODS%3A%20All%20UK%20public%20hospitals%26%23039%3B%20websites%20performing%20obstetric%20anaesthesia%20were%20searched%20for%20patient%20education%20materials%20relating%20to%20labour%20epidurals.%20A%20readability%20assessment%20was%20conducted%20using%20three%20readability%20scoring%20systems.%20ChatGPT%20was%20used%20to%20rewrite%20content%20of%20online%20patient%20information%20material%20on%20labour%20epidural%20analgesia%20to%20be%20understandable%20by%20an%20individual%20with%20the%20health%20literacy%20level%20of%20an%2011-year-old%20%28sixth%20grade%29.%5CnRESULTS%3A%20A%20total%20of%2061.6%25%20of%20UK%20hospitals%20provided%20some%20form%20of%20online%20patient%20education%20materials%20on%20labour%20analgesia%20and%20epidurals%2C%2014.5%25%20and%2023.2%25%20of%20the%20texts%2C%20met%20the%20target%20readability%20in%20two%20commonly%20used%20readability%20scores%2C%20respectively.%20The%20mean%20grade%20%288.4%20%5Cu00b1%202.1%29%20did%20not%20meet%20target%20readability%20levels.%20After%20AI-modification%2C%2024.6%25%20and%2027.5%25%20of%20the%20texts%20met%20targets%20using%20the%20same%20metrics%2C%20with%20the%20mean%20grade%20%287.7%20%5Cu00b1%201.2%29%20decreasing%20significantly%20%28P%20%26lt%3B0.001%29%2C%20but%20still%20not%20meeting%20the%20target%20level.%5CnCONCLUSION%3A%20Online%20patient-information%20on%20labour%20epidural%20analgesia%20frequently%20exceeds%20the%20recommended%20sixth%20grade%20reading%20level.%20ChatGPT%20can%20be%20used%20to%20enhance%20readability%20but%20also%20fails%20to%20meet%20recommended%20health%20literacy%20standards.%22%2C%22date%22%3A%222025-05%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1016%5C%2Fj.ijoa.2025.104344%22%2C%22ISSN%22%3A%221532-3374%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40174427%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T09%3A07%3A21Z%22%7D%7D%2C%7B%22key%22%3A%22ZSQFN3E5%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Tripathi%20et%20al.%22%2C%22parsedDate%22%3A%222025-04-29%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BTripathi%2C%20Satvik%2C%20Dana%20Alkhulaifat%2C%20Meghana%20Muppuri%2C%20Ameena%20Elahi%2C%20and%20Farouk%20Dako.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40204164%5C%2F%26%23039%3B%26gt%3BLarge%20Language%20Models%20for%20Global%20Health%20Clinics%3A%20Opportunities%20and%20Challenges%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BJournal%20of%20the%20American%20College%20of%20Radiology%3A%20JACR%26lt%3B%5C%2Fi%26gt%3B%2C%20April%2029%2C%202025%2C%20S1546-1440%2825%2900205-4.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.jacr.2025.04.007.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Large%20Language%20Models%20for%20Global%20Health%20Clinics%3A%20Opportunities%20and%20Challenges%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Satvik%22%2C%22lastName%22%3A%22Tripathi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dana%22%2C%22lastName%22%3A%22Alkhulaifat%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Meghana%22%2C%22lastName%22%3A%22Muppuri%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ameena%22%2C%22lastName%22%3A%22Elahi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Farouk%22%2C%22lastName%22%3A%22Dako%22%7D%5D%2C%22abstractNote%22%3A%22Large%20language%20models%20%28LLMs%29%20have%20emerged%20as%20a%20new%20wave%20of%20artificial%20intelligence%2C%20and%20their%20applications%20could%20emerge%20as%20a%20pivotal%20resource%20capable%20of%20reshaping%20health%20care%20communication%2C%20research%2C%20and%20informed%20decision-making%20processes.%20These%20models%20offer%20unprecedented%20potential%20to%20swiftly%20disseminate%20critical%20health%20information%20and%20transcend%20linguistic%20barriers.%20However%2C%20their%20integration%20into%20health%20care%20systems%20presents%20formidable%20challenges%2C%20including%20inherent%20biases%20in%20training%20data%2C%20privacy%20vulnerabilities%2C%20and%20disparities%20in%20digital%20literacy.%20Despite%20these%20obstacles%2C%20LLMs%20possess%20unparalleled%20analytic%20prowess%20to%20inform%20evidence-based%20health%20care%20policies%20and%20clinical%20practices.%20Addressing%20these%20challenges%20necessitates%20the%20formulation%20of%20robust%20ethical%20frameworks%2C%20bias%20mitigation%20strategies%2C%20and%20educational%20initiatives%20to%20ensure%20equitable%20access%20to%20health%20care%20resources%20globally.%20By%20navigating%20these%20complexities%20with%20meticulous%20attention%20and%20foresight%2C%20LLMs%20stand%20poised%20to%20catalyze%20substantial%20advancements%20in%20global%20health%20outcomes%2C%20promoting%20health%20equity%20and%20improving%20population%20health%20worldwide.%22%2C%22date%22%3A%222025-04-29%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1016%5C%2Fj.jacr.2025.04.007%22%2C%22ISSN%22%3A%221558-349X%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40204164%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T09%3A00%3A56Z%22%7D%7D%2C%7B%22key%22%3A%22YGJAUCRD%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22P%5Cu00e9rez-Esteve%20et%20al.%22%2C%22parsedDate%22%3A%222025-04-28%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BP%5Cu00e9rez-Esteve%2C%20Clara%2C%20Mercedes%20Guilabert%2C%20Valerie%20Matarredona%2C%20Einav%20Srulovici%2C%20Susanna%20Tella%2C%20Reinhard%20Strametz%2C%20and%20Jos%5Cu00e9%20Joaqu%5Cu00edn%20Mira.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40294407%5C%2F%26%23039%3B%26gt%3BAI%20in%20Home%20Care-Evaluation%20of%20Large%20Language%20Models%20for%20Future%20Training%20of%20Informal%20Caregivers%3A%20Observational%20Comparative%20Case%20Study%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BJournal%20of%20Medical%20Internet%20Research%26lt%3B%5C%2Fi%26gt%3B%2027%20%28April%2028%2C%202025%29%3A%20e70703.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.2196%5C%2F70703.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22AI%20in%20Home%20Care-Evaluation%20of%20Large%20Language%20Models%20for%20Future%20Training%20of%20Informal%20Caregivers%3A%20Observational%20Comparative%20Case%20Study%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Clara%22%2C%22lastName%22%3A%22P%5Cu00e9rez-Esteve%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Mercedes%22%2C%22lastName%22%3A%22Guilabert%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Valerie%22%2C%22lastName%22%3A%22Matarredona%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Einav%22%2C%22lastName%22%3A%22Srulovici%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Susanna%22%2C%22lastName%22%3A%22Tella%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Reinhard%22%2C%22lastName%22%3A%22Strametz%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jos%5Cu00e9%20Joaqu%5Cu00edn%22%2C%22lastName%22%3A%22Mira%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20The%20aging%20population%20presents%20an%20accomplishment%20for%20society%20but%20also%20poses%20significant%20challenges%20for%20governments%2C%20health%20care%20systems%2C%20and%20caregivers.%20Elevated%20rates%20of%20functional%20limitations%20among%20older%20adults%2C%20primarily%20caused%20by%20chronic%20conditions%2C%20necessitate%20adequate%20and%20safe%20care%2C%20including%20in-home%20settings.%20Traditionally%2C%20informal%20caregiver%20training%20has%20relied%20on%20verbal%20and%20written%20instructions.%20However%2C%20the%20advent%20of%20digital%20resources%20has%20introduced%20videos%20and%20interactive%20platforms%2C%20offering%20more%20accessible%20and%20effective%20training.%20Large%20language%20models%20%28LLMs%29%20have%20emerged%20as%20potential%20tools%20for%20personalized%20information%20delivery.%20While%20LLMs%20exhibit%20the%20capacity%20to%20mimic%20clinical%20reasoning%20and%20support%20decision-making%2C%20their%20potential%20to%20serve%20as%20alternatives%20to%20evidence-based%20professional%20instruction%20remains%20unexplored.%5CnOBJECTIVE%3A%20We%20aimed%20to%20evaluate%20the%20appropriateness%20of%20home%20care%20instructions%20generated%20by%20LLMs%20%28including%20GPTs%29%20in%20comparison%20to%20a%20professional%20gold%20standard.%20Furthermore%2C%20it%20seeks%20to%20identify%20specific%20domains%20where%20LLMs%20show%20the%20most%20promise%20and%20where%20improvements%20are%20necessary%20to%20optimize%20their%20reliability%20for%20caregiver%20training.%5CnMETHODS%3A%20An%20observational%2C%20comparative%20case%20study%20evaluated%203%20LLMs-GPT-3.5%2C%20GPT-4o%2C%20and%20Microsoft%20Copilot-in%2010%20home%20care%20scenarios.%20A%20rubric%20assessed%20the%20models%20against%20a%20reference%20standard%20%28gold%20standard%29%20created%20by%20health%20care%20professionals.%20Independent%20reviewers%20evaluated%20variables%20including%20specificity%2C%20clarity%2C%20and%20self-efficacy.%20In%20addition%20to%20comparing%20each%20LLM%20to%20the%20gold%20standard%2C%20the%20models%20were%20also%20compared%20against%20each%20other%20across%20all%20study%20domains%20to%20identify%20relative%20strengths%20and%20weaknesses.%20Statistical%20analyses%20compared%20LLMs%20performance%20to%20the%20gold%20standard%20to%20ensure%20consistency%20and%20validity%2C%20as%20well%20as%20to%20analyze%20differences%20between%20LLMs%20across%20all%20evaluated%20domains.%5CnRESULTS%3A%20The%20study%20revealed%20that%20while%20no%20LLM%20achieved%20the%20precision%20of%20the%20professional%20gold%20standard%2C%20GPT-4o%20outperformed%20GPT-3.5%2C%20and%20Copilot%20in%20specificity%20%284.6%20vs%203.7%20and%203.6%29%2C%20clarity%20%284.8%20vs%204.1%20and%203.9%29%2C%20and%20self-efficacy%20%284.6%20vs%203.8%20and%203.4%29.%20However%2C%20the%20models%20exhibited%20significant%20limitations%2C%20with%20GPT-4o%20and%20Copilot%20omitting%20relevant%20details%20in%2060%25%20%286%5C%2F10%29%20of%20the%20cases%2C%20and%20GPT-3.5%20doing%20so%20in%2080%25%20%288%5C%2F10%29.%20When%20compared%20to%20the%20gold%20standard%2C%20only%2010%25%20%282%5C%2F20%29%20of%20GPT-4o%20responses%20were%20rated%20as%20equally%20specific%2C%2020%25%20%284%5C%2F20%29%20included%20comparable%20practical%20advice%2C%20and%20just%205%25%20%281%5C%2F20%29%20provided%20a%20justification%20as%20detailed%20as%20professional%20guidance.%20Furthermore%2C%20error%20frequency%20did%20not%20differ%20significantly%20across%20models%20%28P%3D.65%29%2C%20though%20Copilot%20had%20the%20highest%20rate%20of%20incorrect%20information%20%2820%25%2C%202%5C%2F10%20vs%2010%25%2C%201%5C%2F10%20for%20GPT-4o%20and%200%25%2C%200%5C%2F0%20for%20GPT-3.5%29.%5CnCONCLUSIONS%3A%20LLMs%2C%20particularly%20GPT-4o%20subscription-based%2C%20show%20potential%20as%20tools%20for%20training%20informal%20caregivers%20by%20providing%20tailored%20guidance%20and%20reducing%20errors.%20Although%20not%20yet%20surpassing%20professional%20instruction%20quality%2C%20these%20models%20offer%20a%20flexible%20and%20accessible%20alternative%20that%20could%20enhance%20home%20safety%20and%20care%20quality.%20Further%20research%20is%20necessary%20to%20address%20limitations%20and%20optimize%20their%20performance.%20Future%20implementation%20of%20LLMs%20may%20alleviate%20health%20care%20system%20burdens%20by%20reducing%20common%20caregiver%20errors.%22%2C%22date%22%3A%222025-04-28%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.2196%5C%2F70703%22%2C%22ISSN%22%3A%221438-8871%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40294407%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T07%3A49%3A07Z%22%7D%7D%2C%7B%22key%22%3A%229TTBTJLY%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Chokkakula%20et%20al.%22%2C%22parsedDate%22%3A%222025-04-28%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BChokkakula%2C%20Santosh%2C%20Siomui%20Chong%2C%20Bing%20Yang%2C%20Hong%20Jiang%2C%20Juan%20Yu%2C%20Ruiqin%20Han%2C%20Idress%20Hamad%20Attitalla%2C%20Chengliang%20Yin%2C%20and%20Shuyao%20Zhang.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpmc.ncbi.nlm.nih.gov%5C%2Farticles%5C%2FPMC12079582%5C%2F%26%23039%3B%26gt%3BQuantum%20leap%20in%20medical%20mentorship%3A%20exploring%20ChatGPT%26%23039%3Bs%20transition%20from%20textbooks%20to%20terabytes%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BFrontiers%20in%20Medicine%26lt%3B%5C%2Fi%26gt%3B%2012%20%28April%2028%2C%202025%29%3A%201517981.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.3389%5C%2Ffmed.2025.1517981.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Quantum%20leap%20in%20medical%20mentorship%3A%20exploring%20ChatGPT%27s%20transition%20from%20textbooks%20to%20terabytes%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Santosh%22%2C%22lastName%22%3A%22Chokkakula%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Siomui%22%2C%22lastName%22%3A%22Chong%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bing%22%2C%22lastName%22%3A%22Yang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hong%22%2C%22lastName%22%3A%22Jiang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Juan%22%2C%22lastName%22%3A%22Yu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ruiqin%22%2C%22lastName%22%3A%22Han%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Idress%20Hamad%22%2C%22lastName%22%3A%22Attitalla%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Chengliang%22%2C%22lastName%22%3A%22Yin%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shuyao%22%2C%22lastName%22%3A%22Zhang%22%7D%5D%2C%22abstractNote%22%3A%22ChatGPT%2C%20an%20advanced%20AI%20language%20model%2C%20presents%20a%20transformative%20opportunity%20in%20several%20fields%20including%20the%20medical%20education.%20This%20article%20examines%20the%20integration%20of%20ChatGPT%20into%20healthcare%20learning%20environments%2C%20exploring%20its%20potential%20to%20revolutionize%20knowledge%20acquisition%2C%20personalize%20education%2C%20support%20curriculum%20development%2C%20and%20enhance%20clinical%20reasoning.%20The%20AI%26%23039%3Bs%20ability%20to%20swiftly%20access%20and%20synthesize%20medical%20information%20across%20various%20specialties%20offers%20significant%20value%20to%20students%20and%20professionals%20alike.%20It%20provides%20rapid%20answers%20to%20queries%20on%20medical%20theories%2C%20treatment%20guidelines%2C%20and%20diagnostic%20methods%2C%20potentially%20accelerating%20the%20learning%20curve.%20The%20paper%20emphasizes%20the%20necessity%20of%20verifying%20ChatGPT%26%23039%3Bs%20outputs%20against%20authoritative%20medical%20sources.%20A%20key%20advantage%20highlighted%20is%20the%20AI%26%23039%3Bs%20capacity%20to%20tailor%20learning%20experiences%20by%20assessing%20individual%20needs%2C%20accommodating%20diverse%20learning%20styles%2C%20and%20offering%20personalized%20feedback.%20The%20article%20also%20considers%20ChatGPT%26%23039%3Bs%20role%20in%20shaping%20curricula%20and%20assessment%20techniques%2C%20suggesting%20that%20educators%20may%20need%20to%20adapt%20their%20methods%20to%20incorporate%20AI-driven%20learning%20tools.%20Additionally%2C%20it%20explores%20how%20ChatGPT%20could%20bolster%20clinical%20problem-solving%20through%20AI-powered%20simulations%2C%20fostering%20critical%20thinking%20and%20diagnostic%20acumen%20among%20students.%20While%20recognizing%20ChatGPT%26%23039%3Bs%20transformative%20potential%20in%20medical%20education%2C%20the%20article%20stresses%20the%20importance%20of%20thoughtful%20implementation%2C%20continuous%20validation%2C%20and%20the%20establishment%20of%20protocols%20to%20ensure%20its%20responsible%20and%20effective%20application%20in%20healthcare%20education%20settings.%22%2C%22date%22%3A%222025-04-28%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.3389%5C%2Ffmed.2025.1517981%22%2C%22ISSN%22%3A%222296-858X%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpmc.ncbi.nlm.nih.gov%5C%2Farticles%5C%2FPMC12079582%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T08%3A37%3A59Z%22%7D%7D%2C%7B%22key%22%3A%22ESG6LQT7%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22H%5Cu00f8j%20et%20al.%22%2C%22parsedDate%22%3A%222025-04-26%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BH%5Cu00f8j%2C%20Simon%2C%20Vibeke%20Backer%2C%20Charlotte%20Suppli%20Ulrik%2C%20Torben%20Sigsgaard%2C%20and%20Howraman%20Meteran.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40257390%5C%2F%26%23039%3B%26gt%3BArtificial%20intelligence%20in%20asthma%20health%20literacy%3A%20a%20comparative%20analysis%20of%20ChatGPT%20versus%20Gemini%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BThe%20Journal%20of%20Asthma%3A%20Official%20Journal%20of%20the%20Association%20for%20the%20Care%20of%20Asthma%26lt%3B%5C%2Fi%26gt%3B%2C%20April%2026%2C%202025%2C%201%5Cu20137.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1080%5C%2F02770903.2025.2495729.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Artificial%20intelligence%20in%20asthma%20health%20literacy%3A%20a%20comparative%20analysis%20of%20ChatGPT%20versus%20Gemini%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Simon%22%2C%22lastName%22%3A%22H%5Cu00f8j%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Vibeke%22%2C%22lastName%22%3A%22Backer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Charlotte%20Suppli%22%2C%22lastName%22%3A%22Ulrik%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Torben%22%2C%22lastName%22%3A%22Sigsgaard%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Howraman%22%2C%22lastName%22%3A%22Meteran%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20Asthma%20is%20a%20complex%20and%20heterogeneous%20chronic%20disease%20affecting%20over%20300%20million%20individuals%20worldwide.%20Despite%20advances%20in%20pharmacotherapy%2C%20poor%20disease%20control%20remains%20a%20major%20challenge%2C%20necessitating%20innovative%20approaches%20to%20patient%20education%20and%20self-management.%20Artificial%20intelligence%20driven%20chatbots%2C%20such%20as%20ChatGPT%20and%20Gemini%2C%20have%20the%20potential%20to%20enhance%20asthma%20care%20by%20providing%20real-time%2C%20evidence-based%20information.%20As%20asthma%20management%20moves%20toward%20personalized%20medicine%2C%20AI%20could%20support%20individualized%20education%20and%20treatment%20guidance.%20However%2C%20concerns%20remain%20regarding%20the%20accuracy%20and%20reliability%20of%20AI-generated%20medical%20content.%5CnOBJECTIVE%3A%20This%20study%20evaluated%20the%20accuracy%20of%20ChatGPT%20%28version%204.0%29%20and%20Gemini%20%28version%201.2%29%20in%20providing%20asthma-related%20health%20information%20using%20the%20Patient-completed%20Asthma%20Knowledge%20Questionnaire%2C%20a%20validated%20asthma%20literacy%20tool.%5CnMETHODS%3A%20A%20cross-sectional%20study%20was%20conducted%20in%20which%20both%20AI%20models%20answered%2054%20standardized%20asthma-related%20items.%20Responses%20were%20classified%20as%20correct%20or%20incorrect%20based%20on%20alignment%20with%20validated%20clinical%20knowledge.%20Accuracy%20was%20assessed%20using%20descriptive%20statistics%2C%20Cohen%26%23039%3Bs%20kappa%20for%20inter-model%20agreement%2C%20and%20chi-square%20tests%20for%20comparative%20performance.%5CnRESULTS%3A%20ChatGPT%20achieved%20an%20accuracy%20of%2096.3%25%20%2852%5C%2F54%20correct%3B%2095%25%20CI%3A%2087.5%25-99.0%25%29%2C%20while%20Gemini%20scored%2092.6%25%20%2850%5C%2F54%20correct%3B%2095%25%20CI%3A%2082.5%25-97.1%25%29%2C%20with%20no%20statistically%20significant%20difference%20%28p%5Cu2009%3D%5Cu20090.67%29.%20Cohen%26%23039%3Bs%20kappa%20demonstrated%20near-perfect%20agreement%20for%20ChatGPT%20%28%5Cu03ba%5Cu2009%3D%5Cu20090.91%29%20and%20strong%20agreement%20for%20Gemini%20%28%5Cu03ba%5Cu2009%3D%5Cu20090.82%29.%5CnCONCLUSION%3A%20ChatGPT%20and%20Gemini%20demonstrated%20high%20accuracy%20in%20delivering%20asthma-related%20health%20information%2C%20supporting%20their%20potential%20as%20adjunct%20tools%20for%20patient%20education.%20AI%20models%20could%20potentially%20play%20a%20role%20in%20personalized%20asthma%20management%20by%20providing%20tailored%20treatment%20guidance%20and%20improving%20patient%20engagement.%22%2C%22date%22%3A%222025-04-26%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1080%5C%2F02770903.2025.2495729%22%2C%22ISSN%22%3A%221532-4303%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40257390%5C%2F%22%2C%22collections%22%3A%5B%227NLACL24%22%2C%2246NNKHWR%22%2C%222G8YLGV7%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T08%3A47%3A00Z%22%7D%7D%2C%7B%22key%22%3A%22DBI34TEU%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Buchgraber-Schnalzer%20et%20al.%22%2C%22parsedDate%22%3A%222025-04-24%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BBuchgraber-Schnalzer%2C%20Bianca%2C%20Marco%20Tilli%2C%20Rupert%20Beinhauer%2C%20Waltraud%20Jelinek-Krickl%2C%20Raphaele%20Raab%2C%20Klaus%20Lichtenegger%2C%20Michael%20Hammer%2C%20Gernot%20Reishofer%2C%20and%20Helmut%20Ritschl.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40270398%5C%2F%26%23039%3B%26gt%3BcMOOC%20Recommendations%20to%20Enhance%20AI%20Literacy%20Among%20Healthcare%20Professionals%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BStudies%20in%20Health%20Technology%20and%20Informatics%26lt%3B%5C%2Fi%26gt%3B%20324%20%28April%2024%2C%202025%29%3A%20135%5Cu201340.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.3233%5C%2FSHTI250174.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22cMOOC%20Recommendations%20to%20Enhance%20AI%20Literacy%20Among%20Healthcare%20Professionals%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bianca%22%2C%22lastName%22%3A%22Buchgraber-Schnalzer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marco%22%2C%22lastName%22%3A%22Tilli%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rupert%22%2C%22lastName%22%3A%22Beinhauer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Waltraud%22%2C%22lastName%22%3A%22Jelinek-Krickl%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Raphaele%22%2C%22lastName%22%3A%22Raab%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%22%2C%22lastName%22%3A%22Lichtenegger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%22%2C%22lastName%22%3A%22Hammer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gernot%22%2C%22lastName%22%3A%22Reishofer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Helmut%22%2C%22lastName%22%3A%22Ritschl%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20Applications%20of%20artificial%20intelligence%20%28AI%29%20are%20finding%20their%20way%20into%20many%20areas%20of%20society%2C%20including%20healthcare%20and%20show%20their%20potential%20in%20this%20domain.%20To%20evaluate%20these%20new%20technologies%20and%20use%20them%20wisely%2C%20healthcare%20professionals%20need%20to%20integrate%20AI%20literacy%20into%20their%20curricula%20in%20a%20meaningful%20way%2C%20as%20they%20do%20in%20other%20academic%20fields.%5CnOBJECTIVES%3A%20The%20aim%20of%20this%20paper%20is%20to%20share%20initial%20experiences%20in%20the%20didactic%20implementation%20of%20an%20online%20course%20in%20health%20professions%20education%20that%20is%20designed%20to%20strengthen%20the%20healthcare%20community%20in%20acquiring%20AI%20competences%20and%20enable%20ethical%20and%20legal%20discussion%20regarding%20AI.%20Based%20on%20these%20experiences%2C%20recommendations%20will%20be%20derived.%5CnMETHODS%3A%20The%20course%20was%20designed%20and%20developed%20based%20on%20a%20comprehensive%20requirements%20analysis%20and%20tested%20in%20a%20two-stage%20evaluation.%5CnRESULT%3A%20The%20key%20factors%20for%20creating%20the%20online%20course%20were%20identified%20and%20recommendations%20and%20strategies%20to%20enhance%20AI%20literacy%20are%20given.%5CnCONCLUSION%3A%20Online%20training%20courses%20offer%20the%20possibility%20to%20integrate%20AI%20literacy%20aspects%20into%20healthcare%20professionals%26%23039%3B%20education.%20Future%20work%20should%20focus%20on%20further%20evaluation.%22%2C%22date%22%3A%222025-04-24%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.3233%5C%2FSHTI250174%22%2C%22ISSN%22%3A%221879-8365%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40270398%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%22SPWXRLZV%22%2C%22ZKMQLZWF%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T08%3A43%3A22Z%22%7D%7D%2C%7B%22key%22%3A%22AU5DBSPN%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Ding%20et%20al.%22%2C%22parsedDate%22%3A%222025-04-24%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BDing%2C%20Dan%2C%20Lindsey%20Morris%2C%20Gina%20Novario%2C%20Andrea%20Fairman%2C%20Kacey%20Roehrich%2C%20Palma%20Foschi%20Walko%2C%20and%20Jessica%20Boateng.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40272873%5C%2F%26%23039%3B%26gt%3BMainstream%20Smart%20Home%20Technology-Based%20Intervention%20to%20Enhance%20Functional%20Independence%20in%20Individuals%20With%20Complex%20Physical%20Disabilities%3A%20Single-Group%20Pre-Post%20Feasibility%20Study%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BJMIR%20Rehabilitation%20and%20Assistive%20Technologies%26lt%3B%5C%2Fi%26gt%3B%2012%20%28April%2024%2C%202025%29%3A%20e70855.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.2196%5C%2F70855.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Mainstream%20Smart%20Home%20Technology-Based%20Intervention%20to%20Enhance%20Functional%20Independence%20in%20Individuals%20With%20Complex%20Physical%20Disabilities%3A%20Single-Group%20Pre-Post%20Feasibility%20Study%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dan%22%2C%22lastName%22%3A%22Ding%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lindsey%22%2C%22lastName%22%3A%22Morris%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gina%22%2C%22lastName%22%3A%22Novario%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Andrea%22%2C%22lastName%22%3A%22Fairman%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kacey%22%2C%22lastName%22%3A%22Roehrich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Palma%22%2C%22lastName%22%3A%22Foschi%20Walko%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jessica%22%2C%22lastName%22%3A%22Boateng%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20Mainstream%20smart%20home%20technologies%20%28MSHTs%29%2C%20such%20as%20home%20automation%20devices%20and%20smart%20speakers%2C%20are%20becoming%20more%20powerful%2C%20affordable%2C%20and%20integrated%20into%20daily%20life.%20While%20not%20designed%20for%20individuals%20with%20disabilities%2C%20MSHT%20has%20the%20potential%20to%20serve%20as%20assistive%20technology%20to%20enhance%20their%20independence%20and%20participation.%5CnOBJECTIVE%3A%20The%20study%20aims%20to%20describe%20a%20comprehensive%20MSHT-based%20intervention%20named%20ASSIST%20%28Autonomy%2C%20Safety%2C%20and%20Social%20Integration%20via%20Smart%20Technologies%29%20and%20evaluate%20its%20feasibility%20in%20enhancing%20the%20functional%20independence%20of%20individuals%20with%20complex%20physical%20disabilities.%5CnMETHODS%3A%20ASSIST%20is%20a%20time-limited%20intervention%20with%20a%20design%20based%20on%20the%20human%20activity%20assistive%20technology%20model%2C%20emphasizing%20client-centered%20goals%20and%20prioritizing%20individual%20needs.%20The%20intervention%20follows%20a%20structured%20assistive%20technology%20service%20delivery%20process%20that%20includes%202%20assessment%20sessions%20to%20determine%20technology%20recommendations%2C%20installation%20and%20setup%20of%20the%20recommended%20technology%2C%20and%20up%20to%208%20training%20sessions.%20An%20occupational%20therapist%20led%20the%20intervention%2C%20supported%20by%20a%20contractor%20and%20a%20technologist.%20Feasibility%20was%20evaluated%20through%20several%20measures%3A%20%281%29%20the%20ASSIST%20Functional%20Performance%20Index%2C%20which%20quantifies%20the%20number%20of%20tasks%20transitioned%20from%20requiring%20assistance%20to%20independent%20completion%20and%20from%20higher%20levels%20of%20assistance%20or%20effort%20to%20lower%20levels%3B%20%282%29%20pre-%20and%20postintervention%20measures%20of%20perceived%20task%20performance%20and%20satisfaction%20using%20a%2010-point%20scale%3B%20%283%29%20the%20number%20and%20types%20of%20tasks%20successfully%20addressed%2C%20along%20with%20the%20costs%20of%20devices%20and%20installation%20services%3B%20and%20%284%29%20training%20effectiveness%20using%20the%20Goal%20Attainment%20Scale%20%28GAS%29.%5CnRESULTS%3A%20In%20total%2C%2017%20powered%20wheelchair%20users%20with%20complex%20physical%20disabilities%20completed%20the%20study%20with%20100%25%20session%20attendance.%20Across%20participants%2C%20127%20tasks%20were%20addressed%2C%20with%202%20to%2010%20tasks%20at%20an%20average%20cost%20of%20US%20%243308%20%28SD%20US%20%241192%29%20per%20participant.%20Of%20these%20tasks%2C%2095%20%2874.8%25%29%20transitioned%20from%20requiring%20partial%20or%20complete%20assistance%20to%20independent%20completion%2C%20while%2024%20%2818.9%25%29%20either%20improved%20from%20requiring%20complete%20to%20partial%20assistance%20or%2C%20if%20originally%20performed%20independently%2C%20required%20reduced%20effort.%20Only%208%20%286.3%25%29%20tasks%20showed%20no%20changes.%20All%20training%20goals%2C%20except%20for%202%2C%20were%20achieved%20at%20or%20above%20the%20expected%20level%2C%20with%20a%20baseline%20average%20GAS%20score%20of%2022.6%20%28SD%203.5%29%20and%20a%20posttraining%20average%20GAS%20score%20of%2077.2%20%28SD%204.5%29.%20Perceived%20task%20performance%20and%20satisfaction%20showed%20significant%20improvement%2C%20with%20performance%20score%20increasing%20from%20a%20baseline%20mean%20of%202.6%20%28SD%201.2%29%20to%208.8%20%28SD%201.0%3B%20P%26lt%3B.001%29%20and%20satisfaction%20score%20rising%20from%20an%20average%20of%202.9%20%28SD%201.3%29%20to%209.0%20%28SD%200.9%3B%20P%26lt%3B.001%29.%5CnCONCLUSIONS%3A%20The%20ASSIST%20intervention%20demonstrated%20the%20immediate%20benefits%20of%20enhancing%20functional%20independence%20and%20satisfaction%20with%20MSHT%20among%20individuals%20with%20complex%20physical%20disabilities.%20While%20MSHT%20shows%20promise%20in%20addressing%20daily%20living%20needs%20at%20lower%20costs%2C%20barriers%20such%20as%20digital%20literacy%2C%20device%20setup%2C%20and%20caregiver%20involvement%20remain.%20Future%20work%20should%20focus%20on%20scalable%20models%2C%20caregiver%20engagement%2C%20and%20sustainable%20solutions%20for%20real-world%20implementation.%22%2C%22date%22%3A%222025-04-24%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.2196%5C%2F70855%22%2C%22ISSN%22%3A%222369-2529%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40272873%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%22ZXT3TN9W%22%2C%22V9ETKJCU%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T07%3A54%3A49Z%22%7D%7D%2C%7B%22key%22%3A%22UCH3GI9D%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Lindb%5Cu00e4ck%20et%20al.%22%2C%22parsedDate%22%3A%222025-04-24%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BLindb%5Cu00e4ck%2C%20Yvonne%2C%20Karin%20Schr%5Cu00f6der%2C%20Torkel%20Engstr%5Cu00f6m%2C%20Karin%20Valeskog%2C%20and%20Sofi%20Sonesson.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40275241%5C%2F%26%23039%3B%26gt%3BGenerative%20artificial%20intelligence%20in%20physiotherapy%20education%3A%20great%20potential%20amidst%20challenges-%20a%20qualitative%20interview%20study%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BBMC%20Medical%20Education%26lt%3B%5C%2Fi%26gt%3B%2025%2C%20no.%201%20%28April%2024%2C%202025%29%3A%20603.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1186%5C%2Fs12909-025-07106-w.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Generative%20artificial%20intelligence%20in%20physiotherapy%20education%3A%20great%20potential%20amidst%20challenges-%20a%20qualitative%20interview%20study%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yvonne%22%2C%22lastName%22%3A%22Lindb%5Cu00e4ck%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Karin%22%2C%22lastName%22%3A%22Schr%5Cu00f6der%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Torkel%22%2C%22lastName%22%3A%22Engstr%5Cu00f6m%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Karin%22%2C%22lastName%22%3A%22Valeskog%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sofi%22%2C%22lastName%22%3A%22Sonesson%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20Generative%20Artificial%20Intelligence%20%28GAI%29%20has%20significantly%20impacted%20education%20at%20all%20levels%2C%20including%20health%20professional%20education.%20Understanding%20students%26%23039%3B%20experiences%20is%20essential%20to%20enhancing%20AI%20literacy%2C%20adapting%20education%20to%20GAI%2C%20and%20implementing%20GAI%20technology.%20Therefore%2C%20the%20aim%20was%20to%20explore%20physiotherapy%20students%26%23039%3B%20experiences%20of%20and%20thoughts%20on%20GAI%20in%20their%20education%2C%20and%20its%20potential%20implications%20for%20their%20future%20careers%20in%20healthcare.%5CnMETHODS%3A%20Qualitative%20descriptive%20design.%20Focus%20groups%20were%20conducted%2C%20using%20a%20semi-structured%20interview%20guide%2C%20at%20the%20Physiotherapy%20program%20at%20Link%5Cu00f6ping%20University%2C%20Sweden%2C%20from%20March%20to%20April%202024.%20The%2015%20students%20were%20organized%20into%20three%20focus%20groups%2C%20one%20for%20each%20education%5Cu00a0year.%20The%20data%20was%20analyzed%20using%20inductive%20content%20analysis.%5CnRESULTS%3A%20An%20overarching%20theme%20%26quot%3BGAI-Great%20potential%20if%20navigating%20the%20challenges%26quot%3B%20emerged%20from%20three%20categories%3A%201%29%20%26quot%3BAreas%20of%20GAI%20use%20in%20the%20learning%20process%26quot%3B%3A%20Students%20viewed%20GAI%20as%20a%20tool%20for%20introduction%20and%20inspiration%2C%20assimilating%20course%20content%20and%20enhancing%20clinical%20reasoning%20and%20problem-solving%3B%202%29%20%26quot%3BOptimizing%20GAI%20use%20in%20education%26quot%3B%3A%20Students%20found%20GAI%20to%20be%20timesaving%2C%20tailored%2C%20and%20as%20a%20virtual%20study%20partner%20and%20teacher.%20They%20discussed%20the%20pros%20and%20cons%20of%20learning%2C%20concerns%20on%20permitted%20GAI%20usage%2C%20the%20need%20for%20a%20critical%20approach%2C%20and%20how%20individual%20experiences%20and%20interests%20influenced%20their%20interactions%20with%20GAI%3B%203%29%20%26quot%3BFuture%20with%20GAI%20in%20education%20and%20profession%26quot%3B%3A%20Students%20believed%20future%20GAI%20would%20be%20more%20reliable%2C%20use%20subject-specific%20GAI%20models%20and%20enhance%20health%20care%20delivery%2C%20but%20also%20pose%20risks%20related%20to%20profit%20motives%20and%20knowledge%20gaps.%5CnCONCLUSION%3A%20Physiotherapy%20students%20found%20GAI%20beneficial%20for%20learning%20and%20clinical%20reasoning%20but%20expressed%20concerns%20about%20its%20impact%20on%20learning%20quality.%20They%20emphasized%20the%20importance%20of%20a%20critical%20approach%20when%20using%20GAI%20and%20the%20need%20for%20organizational%20support%2C%20including%20supporting%20permitted%20GAI%20use.%20Students%20believed%20that%20future%20advanced%20GAI%20models%20could%20provide%20accurate%20and%20reliable%20educational%20tools%20and%20healthcare%20tools%20supporting%20documentation%20and%20evidence-based%20decision-making.%20However%2C%20potential%20risks%20include%20business%20profit%20motives%20and%20knowledge%20gaps.%20Navigating%20these%20challenges%20is%20essential%20to%20fully%20leveraging%20GAI%26%23039%3Bs%20benefits%20in%20education%20and%20physiotherapy%20practice.%20Therefore%2C%20fostering%20a%20critical%20approach%20and%20ensuring%20robust%20organizational%20support%20is%20crucial%20for%20maximizing%20the%20positive%20impact%20of%20GAI%20in%20physiotherapy.%22%2C%22date%22%3A%222025-04-24%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1186%5C%2Fs12909-025-07106-w%22%2C%22ISSN%22%3A%221472-6920%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40275241%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%22GNNVI6S7%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T07%3A52%3A48Z%22%7D%7D%2C%7B%22key%22%3A%22PX7GTCZK%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Wong%20et%20al.%22%2C%22parsedDate%22%3A%222025-04-23%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BWong%2C%20Brian%20Li%20Han%2C%20Garry%20Aslanyan%2C%20Warisa%20Panichkriangkrai%2C%20Ricardo%20Baptista%20Leite%2C%20Jemilah%20Mahmood%2C%20and%20Anders%20Nordstr%5Cu00f6m.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40267068%5C%2F%26%23039%3B%26gt%3BFrom%20algorithms%20to%20negotiations%3A%20Why%20health%20diplomacy%20must%20adapt%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BPLOS%20Global%20Public%20Health%26lt%3B%5C%2Fi%26gt%3B%205%2C%20no.%204%20%28April%2023%2C%202025%29%3A%20e0004488.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1371%5C%2Fjournal.pgph.0004488.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22From%20algorithms%20to%20negotiations%3A%20Why%20health%20diplomacy%20must%20adapt%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Brian%20Li%20Han%22%2C%22lastName%22%3A%22Wong%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Garry%22%2C%22lastName%22%3A%22Aslanyan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Warisa%22%2C%22lastName%22%3A%22Panichkriangkrai%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ricardo%20Baptista%22%2C%22lastName%22%3A%22Leite%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jemilah%22%2C%22lastName%22%3A%22Mahmood%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Anders%22%2C%22lastName%22%3A%22Nordstr%5Cu00f6m%22%7D%5D%2C%22abstractNote%22%3A%22Health%20diplomacy%20traditionally%20relies%20on%20consensus-building%20across%20nations%2C%20yet%20the%20accelerating%20integration%20of%20artificial%20intelligence%20%28AI%29%20into%20health%20systems%20poses%20new%20governance%20challenges.%20Rapidly%20changing%20geopolitical%20conditions-exemplified%20by%20shifts%20in%20U.S.%20global%20health%20funding%20and%20the%20expansion%20of%20AI%20beyond%20national%20boundaries-underscore%20the%20urgency%20of%20rethinking%20traditional%20approaches.%20This%20paper%2C%20based%20on%20insights%20from%20the%20Prince%20Mahidol%20Award%20Conference%202025%20side%20meeting%20on%20%26quot%3BNavigating%20the%20Future%3A%20AI%20%26amp%3B%20Global%20Health%20Diplomacy%2C%26quot%3B%20examines%20how%20AI%20can%20reshape%20the%20practice%20of%20health%20diplomacy%2C%20both%20empowering%20and%20unsettling%20global%20health%20objectives.%20We%20first%20explore%20the%20promise%20of%20AI%20in%20enhancing%20disease%20surveillance%2C%20resource%20allocation%2C%20and%20progress%20toward%20universal%20health%20coverage.%20However%2C%20inadequate%20governance%20can%20exacerbate%20inequalities%2C%20particularly%20if%20AI%20remains%20in%20the%20hands%20of%20profit-focused%20enterprises%20or%20if%20digital%20divides%20persist.%20Health%20diplomacy%2C%20therefore%2C%20must%20expand%20its%20purview%20to%20include%20technical%20literacy%2C%20data%20ethics%2C%20and%20robust%20regulatory%20frameworks%20that%20safeguard%20equity%20and%20transparency%20in%20AI%20design%20and%20deployment.%20To%20illustrate%20these%20dynamics%2C%20we%20emphasise%20the%20interplay%20of%20social%2C%20political%2C%20commercial%2C%20and%20digital%20determinants%20of%20health%2C%20each%20feeding%20into%20AI-driven%20innovations.%20Strong%20diplomatic%20engagement%20is%20critical%20to%20ensuring%20that%20AI%20becomes%20a%20tool%20for%20mutual%20benefit%20rather%20than%20a%20catalyst%20for%20further%20fragmentation.%20Effective%20policies%20must%20integrate%20environmental%20sustainability%20considerations%20alongside%20cross-sector%20collaboration.%20We%20conclude%20that%2C%20although%20AI%20cannot%20replace%20the%20vital%20human%20element%20of%20negotiation%20and%20trust-building%2C%20it%20can%20substantially%20enhance%20global%20health%20outcomes%20when%20governed%20ethically%20and%20inclusively.%20The%20future%20of%20health%20diplomacy%2C%20shaped%20by%20AI%2C%20requires%20agile%20adaptation%20and%20unified%20strategies%20to%20preserve%20equity%20and%20planetary%20well-being.%22%2C%22date%22%3A%222025-04-23%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1371%5C%2Fjournal.pgph.0004488%22%2C%22ISSN%22%3A%222767-3375%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40267068%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%22JL4N5KDE%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T08%3A45%3A08Z%22%7D%7D%2C%7B%22key%22%3A%22IZCWXC6V%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Giaxi%20et%20al.%22%2C%22parsedDate%22%3A%222025-04-19%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BGiaxi%2C%20Paraskevi%2C%20Victoria%20Vivilaki%2C%20Angeliki%20Sarella%2C%20and%20Kleanthi%20Gourounti.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40281891%5C%2F%26%23039%3B%26gt%3BArtificial%20Intelligence%20in%20Midwifery%3A%20A%20Scoping%20Review%20of%20Current%20Applications%2C%20Future%20Prospects%2C%20and%20Midwives%26%23039%3B%20Perspectives%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BHealthcare%20%28Basel%2C%20Switzerland%29%26lt%3B%5C%2Fi%26gt%3B%2013%2C%20no.%208%20%28April%2019%2C%202025%29%3A%20942.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.3390%5C%2Fhealthcare13080942.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Artificial%20Intelligence%20in%20Midwifery%3A%20A%20Scoping%20Review%20of%20Current%20Applications%2C%20Future%20Prospects%2C%20and%20Midwives%27%20Perspectives%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Paraskevi%22%2C%22lastName%22%3A%22Giaxi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Victoria%22%2C%22lastName%22%3A%22Vivilaki%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Angeliki%22%2C%22lastName%22%3A%22Sarella%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kleanthi%22%2C%22lastName%22%3A%22Gourounti%22%7D%5D%2C%22abstractNote%22%3A%22Background%5C%2FObjectives%3A%20Artificial%20intelligence%20%28AI%29%20is%20considered%20one%20of%20the%20core%20technological%20advancements%20of%20Industry%204.0%2C%20expected%20to%20transform%20various%20sectors%2C%20including%20healthcare.%20Midwifery%20can%20greatly%20benefit%20from%20AI%3B%20however%2C%20its%20current%20use%2C%20its%20future%20potential%2C%20and%20midwives%26%23039%3B%20attitudes%20remain%20underexplored.%20This%20study%20aimed%20to%20investigate%20the%20implementation%20of%2C%20prospects%20of%2C%20and%20attitudes%20of%20midwives%20toward%20AI.%20Methods%3A%20A%20scoping%20review%20was%20carried%20out%2C%20following%20the%20PRISMA%20guidelines.%20The%20search%20was%20conducted%20in%20Pubmed%2C%20Scopus%2C%20and%20Web%20of%20Science%2C%20from%20database%20inception%20to%202%20February%202025.%20Results%3A%20Eight%20studies%20met%20the%20inclusion%20criteria.%20Although%20AI%20is%20not%20yet%20widely%20implemented%20in%20midwifery%2C%20it%20has%20notable%20potential.%20Several%20potential%20benefits%20were%20recorded%2C%20such%20as%20the%20enhancement%20of%20clinical%20education%20through%20personalized%20learning%20tools%2C%20such%20as%20AI-driven%20virtual%20patients%20and%20customized%20assessments%2C%20as%20well%20as%20a%20reduction%20in%20clinical%20errors%20via%20predictive%20models%20and%20real-time%20monitoring%20technologies.%20The%20adoption%20of%20AI%20is%20therefore%20expected%20to%20improve%20quality%20of%20care%2C%20particularly%20in%20perinatal%20and%20neonatal%20settings.%20However%2C%20it%20was%20found%20that%20the%20integration%20remains%20limited%20due%20to%20two%20key%20obstacles%3A%20ethical%20concerns%20%28e.g.%2C%20data%20privacy%29%20and%20a%20notable%20level%20of%20anxiety%20or%20hesitation%20among%20midwives%2C%20associated%20with%20low%20levels%20of%20digital%20health%20literacy.%20Conclusions%3A%20It%20is%20important%20to%20form%20a%20relevant%20framework%20regarding%20the%20use%20of%20AI%20in%20midwifery%2C%20addressing%20ethical%20concerns%20and%20skepticism.%20Additionally%2C%20targeted%20educational%20interventions%20are%20needed%20to%20enhance%20midwives%26%23039%3B%20AI%20literacy%20and%20alleviate%20concerns.%20In%20general%2C%20it%20is%20essential%20to%20overcome%20these%20barriers%20to%20accelerate%20AI%20adoption%20in%20midwifery%20and%20unlock%20its%20full%20potential%20in%20perinatal%20care.%22%2C%22date%22%3A%222025-04-19%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.3390%5C%2Fhealthcare13080942%22%2C%22ISSN%22%3A%222227-9032%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40281891%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%2C%22A9JHPZBW%22%5D%2C%22dateModified%22%3A%222025-05-21T07%3A50%3A51Z%22%7D%7D%2C%7B%22key%22%3A%22P7ZGU8SI%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22L%5Cu00f3pez-P%5Cu00e9rez%20et%20al.%22%2C%22parsedDate%22%3A%222025-04-17%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BL%26%23xF3%3Bpez-P%26%23xE9%3Brez%2C%20Bel%26%23xE9%3Bn%2C%20Yuhui%20Chen%2C%20Xiuhui%20Li%2C%20Shixing%20Cheng%2C%20and%20Pooya%20Razavi.%20%26%23x201C%3BExploring%20the%20Potential%20of%20Large%20Language%20Models%20to%20Understand%20Interpersonal%20Emotion%20Regulation%20Strategies%20from%20Narratives.%26%23x201D%3B%20%26lt%3Bi%26gt%3BEmotion%20%28Washington%2C%20D.C.%29%26lt%3B%5C%2Fi%26gt%3B%2C%20April%2017%2C%202025.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1037%5C%2Femo0001528%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1037%5C%2Femo0001528%26lt%3B%5C%2Fa%26gt%3B.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Exploring%20the%20potential%20of%20large%20language%20models%20to%20understand%20interpersonal%20emotion%20regulation%20strategies%20from%20narratives%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bel%5Cu00e9n%22%2C%22lastName%22%3A%22L%5Cu00f3pez-P%5Cu00e9rez%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yuhui%22%2C%22lastName%22%3A%22Chen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xiuhui%22%2C%22lastName%22%3A%22Li%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shixing%22%2C%22lastName%22%3A%22Cheng%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pooya%22%2C%22lastName%22%3A%22Razavi%22%7D%5D%2C%22abstractNote%22%3A%22Interpersonal%20emotion%20regulation%20involves%20using%20diverse%20strategies%20to%20influence%20others%26%23039%3B%20emotions%2C%20commonly%20assessed%20with%20questionnaires.%20However%2C%20this%20method%20may%20be%20less%20effective%20for%20individuals%20with%20limited%20literacy%20or%20introspection%20skills.%20To%20address%20this%2C%20recent%20studies%20have%20adopted%20narrative-based%20approaches%2C%20though%20these%20require%20time-intensive%20qualitative%20analysis.%20Given%20the%20potential%20of%20artificial%20intelligence%20%28AI%29%20and%20large%20language%20models%20%28LLM%29%20for%20information%20classification%2C%20we%20evaluated%20the%20feasibility%20of%20using%20AI%20to%20categorize%20interpersonal%20emotion%20regulation%20strategies.%20We%20conducted%20two%20studies%20in%20which%20we%20compared%20AI%20performance%20against%20human%20coding%20in%20identifying%20regulation%20strategies%20from%20narrative%20data.%20In%20Study%201%2C%20with%202%2C824%20responses%2C%20ChatGPT%20initially%20achieved%20Kappa%20values%20over%20.47.%20Refinements%20in%20prompts%20%28i.e.%2C%20coding%20instructions%29%20led%20to%20improved%20consistency%20between%20ChatGPT%20and%20human%20coders%20%28%5Cu03ba%20%26gt%3B%20.79%29.%20In%20Study%202%2C%20the%20refined%20prompts%20demonstrated%20comparable%20accuracy%20%28%5Cu03ba%20%26gt%3B%20.76%29%20when%20analyzing%20a%20new%20set%20of%20responses%20%28N%20%3D%202090%29%2C%20using%20both%20ChatGPT%20and%20Claude.%20Additional%20evaluations%20of%20LLMs%26%23039%3B%20performance%20using%20different%20accuracy%20metrics%20pointed%20to%20notable%20variability%20in%20LLM%26%23039%3Bs%20capability%20when%20interpreting%20narratives%20across%20different%20emotions%20and%20regulatory%20strategies.%20These%20results%20point%20to%20the%20strengths%20and%20limitations%20of%20LLMs%20in%20classifying%20regulation%20strategies%2C%20and%20the%20importance%20of%20prompt%20engineering%20and%20validation.%20%28PsycInfo%20Database%20Record%20%28c%29%202025%20APA%2C%20all%20rights%20reserved%29.%22%2C%22date%22%3A%222025-04-17%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1037%5C%2Femo0001528%22%2C%22ISSN%22%3A%221931-1516%22%2C%22url%22%3A%22%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T08%3A52%3A20Z%22%7D%7D%2C%7B%22key%22%3A%22BPLIQJNT%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Tripathi%20et%20al.%22%2C%22parsedDate%22%3A%222025-04-17%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BTripathi%2C%20Satvik%2C%20Liam%20Mutter%2C%20Meghana%20Muppuri%2C%20Suhani%20Dheer%2C%20Emiliano%20Garza-Frias%2C%20Komal%20Awan%2C%20Aakash%20Jha%2C%20et%20al.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40286532%5C%2F%26%23039%3B%26gt%3BPRECISE%20framework%3A%20Enhanced%20radiology%20reporting%20with%20GPT%20for%20improved%20readability%2C%20reliability%2C%20and%20patient-centered%20care%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BEuropean%20Journal%20of%20Radiology%26lt%3B%5C%2Fi%26gt%3B%20187%20%28April%2017%2C%202025%29%3A%20112124.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.ejrad.2025.112124.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22PRECISE%20framework%3A%20Enhanced%20radiology%20reporting%20with%20GPT%20for%20improved%20readability%2C%20reliability%2C%20and%20patient-centered%20care%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Satvik%22%2C%22lastName%22%3A%22Tripathi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Liam%22%2C%22lastName%22%3A%22Mutter%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Meghana%22%2C%22lastName%22%3A%22Muppuri%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Suhani%22%2C%22lastName%22%3A%22Dheer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Emiliano%22%2C%22lastName%22%3A%22Garza-Frias%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Komal%22%2C%22lastName%22%3A%22Awan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Aakash%22%2C%22lastName%22%3A%22Jha%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%22%2C%22lastName%22%3A%22Dezube%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Azadeh%22%2C%22lastName%22%3A%22Tabari%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bernardo%20C.%22%2C%22lastName%22%3A%22Bizzo%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Keith%20J.%22%2C%22lastName%22%3A%22Dreyer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Christopher%20P.%22%2C%22lastName%22%3A%22Bridge%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dania%22%2C%22lastName%22%3A%22Daye%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20The%20PRECISE%20framework%2C%20defined%20as%20Patient-Focused%20Radiology%20Reports%20with%20Enhanced%20Clarity%20and%20Informative%20Summaries%20for%20Effective%20Communication%2C%20leverages%20GPT-4%20to%20create%20patient-friendly%20summaries%20of%20radiology%20reports%20at%20a%20sixth-grade%20reading%20level.%5CnPURPOSE%3A%20The%20purpose%20of%20the%20study%20was%20to%20evaluate%20the%20effectiveness%20of%20the%20PRECISE%20framework%20in%20improving%20the%20readability%2C%20reliability%2C%20and%20understandability%20of%20radiology%20reports.%20We%20hypothesized%20that%20the%20PRECISE%20framework%20improves%20the%20readability%20and%20patient%20understanding%20of%20radiology%20reports%20compared%20to%20the%20original%20versions.%5CnMATERIALS%20AND%20METHODS%3A%20The%20PRECISE%20framework%20was%20assessed%20using%20500%20chest%20X-ray%20reports.%20Readability%20was%20evaluated%20using%20the%20Flesch%20Reading%20Ease%2C%20Gunning%20Fog%20Index%2C%20and%20Automated%20Readability%20Index.%20Reliability%20was%20gauged%20by%20clinical%20volunteers%2C%20while%20understandability%20was%20assessed%20by%20non-medical%20volunteers.%20Statistical%20analyses%20including%20t-tests%2C%20regression%20analyses%2C%20and%20Mann-Whitney%20U%20tests%20were%20conducted%20to%20determine%20the%20significance%20of%20the%20differences%20in%20readability%20scores%20between%20the%20original%20and%20PRECISE-generated%20reports.%5CnRESULTS%3A%20Readability%20scores%20significantly%20improved%2C%20with%20the%20mean%20Flesch%20Reading%20Ease%20score%20increasing%20from%2038.28%20to%2080.82%20%28p-value%5Cu00a0%26lt%3B%5Cu00a00.001%29%2C%20the%20Gunning%20Fog%20Index%20decreasing%20from%2013.04%20to%206.99%20%28p-value%5Cu00a0%26lt%3B%5Cu00a00.001%29%2C%20and%20the%20ARI%20score%20improving%20from%2013.33%20to%205.86%20%28p-value%5Cu00a0%26lt%3B%5Cu00a00.001%29.%20Clinical%20volunteer%20assessments%20found%2095%5Cu00a0%25%20of%20the%20summaries%20reliable%2C%20and%20non-medical%20volunteers%20rated%2097%5Cu00a0%25%20of%20the%20PRECISE-generated%20summaries%20as%20fully%20understandable.%5CnCONCLUSION%3A%20The%20application%20of%20the%20PRECISE%20approach%20demonstrates%20promise%20in%20enhancing%20patient%20understanding%20and%20communication%20without%20adding%20significant%20burden%20to%20radiologists.%20With%20improved%20reliability%20and%20patient-friendly%20summaries%2C%20this%20approach%20holds%20promise%20for%20fostering%20patient%20engagement%20and%20understanding%20in%20healthcare%20decision-making.%20The%20PRECISE%20framework%20represents%20a%20pivotal%20step%20towards%20more%20inclusive%20and%20patient-centric%20care%20delivery.%22%2C%22date%22%3A%222025-04-17%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1016%5C%2Fj.ejrad.2025.112124%22%2C%22ISSN%22%3A%221872-7727%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40286532%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T08%3A35%3A37Z%22%7D%7D%2C%7B%22key%22%3A%223ZB7T8A7%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Reaver%20et%20al.%22%2C%22parsedDate%22%3A%222025-04-16%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BReaver%2C%20Carrie%20N.%2C%20Daniel%20E.%20Pereira%2C%20Elisa%20V.%20Carrillo%2C%20Carolena%20Rojas%20Marcos%2C%20and%20Charles%20A.%20Goldfarb.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40020034%5C%2F%26%23039%3B%26gt%3BEvaluating%20the%20Performance%20of%20Artificial%20Intelligence%20for%20Improving%20Readability%20of%20Online%20English-%20and%20Spanish-Language%20Orthopaedic%20Patient%20Educational%20Material%3A%20Challenges%20in%20Bridging%20the%20Digital%20Divide%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BThe%20Journal%20of%20Bone%20and%20Joint%20Surgery.%20American%20Volume%26lt%3B%5C%2Fi%26gt%3B%20107%2C%20no.%208%20%28April%2016%2C%202025%29%3A%20e36.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.2106%5C%2FJBJS.24.01078.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Evaluating%20the%20Performance%20of%20Artificial%20Intelligence%20for%20Improving%20Readability%20of%20Online%20English-%20and%20Spanish-Language%20Orthopaedic%20Patient%20Educational%20Material%3A%20Challenges%20in%20Bridging%20the%20Digital%20Divide%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Carrie%20N.%22%2C%22lastName%22%3A%22Reaver%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Daniel%20E.%22%2C%22lastName%22%3A%22Pereira%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Elisa%20V.%22%2C%22lastName%22%3A%22Carrillo%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Carolena%20Rojas%22%2C%22lastName%22%3A%22Marcos%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Charles%20A.%22%2C%22lastName%22%3A%22Goldfarb%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20The%20readability%20of%20most%20online%20patient%20educational%20materials%20%28OPEMs%29%20in%20orthopaedic%20surgery%20is%20above%20the%20American%20Medical%20Association%5C%2FNational%20Institutes%20of%20Health%20recommended%20reading%20level%20of%20sixth%20grade%20for%20both%20English-%20and%20Spanish-language%20content.%20The%20current%20project%20evaluates%20ChatGPT%26%23039%3Bs%20performance%20across%20English-%20and%20Spanish-language%20orthopaedic%20OPEMs%20when%20prompted%20to%20rewrite%20the%20material%20at%20a%20sixth-grade%20reading%20level.%5CnMETHODS%3A%20We%20performed%20a%20cross-sectional%20study%20evaluating%20the%20readability%20of%2057%20English-%20and%2056%20Spanish-language%20publicly%20available%20OPEMs%20found%20by%20querying%20online%20in%20both%20English%20and%20Spanish%20for%206%20common%20orthopaedic%20procedures.%20Five%20distinct%2C%20validated%20readability%20tests%20were%20used%20to%20score%20the%20OPEMs%20before%20and%20after%20ChatGPT%204.0%20was%20prompted%20to%20rewrite%20the%20OPEMs%20at%20a%20sixth-grade%20reading%20level.%20We%20compared%20the%20averages%20of%20each%20readability%20test%2C%20the%20cumulative%20average%20reading%20grade%20level%2C%20average%20total%20word%20count%2C%20average%20number%20of%20complex%20words%20%28defined%20as%20%5Cu22653%20syllables%29%2C%20and%20average%20number%20of%20long%20sentences%20%28defined%20as%20%26gt%3B22%20words%29%20between%20original%20content%20and%20ChatGPT-rewritten%20content%20for%20both%20languages%20using%20paired%20t%20tests.%5CnRESULTS%3A%20The%20cumulative%20average%20reading%20grade%20level%20of%20original%20English-%20and%20Spanish-language%20OPEMs%20was%209.6%20%5Cu00b1%202.6%20and%209.5%20%5Cu00b1%201.5%2C%20respectively.%20ChatGPT%20significantly%20lowered%20the%20reading%20grade%20level%20%28improved%20comprehension%29%20to%207.7%20%5Cu00b1%201.9%20%2895%25%20CI%20of%20difference%2C%201.68%20to%202.15%3B%20p%20%26lt%3B%200.05%29%20for%20English-language%20content%20and%208.3%20%5Cu00b1%201.3%20%2895%25%20CI%2C%201.17%20to%201.45%3B%20p%20%26lt%3B%200.05%29%20for%20Spanish-language%20content.%20English-language%20OPEMs%20saw%20a%20reduction%20of%202.0%20%5Cu00b1%201.8%20grade%20levels%2C%20whereas%20Spanish-language%20OPEMs%20saw%20a%20reduction%20of%201.5%20%5Cu00b1%201.2%20grade%20levels.%20Word%20count%2C%20use%20of%20complex%20words%2C%20and%20long%20sentences%20were%20also%20reduced%20significantly%20in%20both%20languages%20while%20still%20maintaining%20high%20accuracy%20and%20similarity%20compared%20with%20original%20content.%5CnCONCLUSIONS%3A%20Our%20study%20supports%20the%20potential%20of%20artificial%20intelligence%20as%20a%20low-cost%2C%20accessible%20tool%20to%20assist%20health%20professionals%20in%20improving%20the%20readability%20of%20orthopaedic%20OPEMs%20in%20both%20English%20and%20Spanish.%22%2C%22date%22%3A%222025-04-16%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.2106%5C%2FJBJS.24.01078%22%2C%22ISSN%22%3A%221535-1386%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40020034%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T09%3A20%3A52Z%22%7D%7D%2C%7B%22key%22%3A%22QM8ABS8M%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Young%20and%20Omosun%22%2C%22parsedDate%22%3A%222025-04-14%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BYoung%2C%20Anna%2C%20and%20Foluke%20Omosun.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40229204%5C%2F%26%23039%3B%26gt%3BA%20comparative%20analysis%20of%20CDC%20and%20AI-generated%20health%20information%20using%20computer-aided%20text%20analysis%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BJournal%20of%20Communication%20in%20Healthcare%26lt%3B%5C%2Fi%26gt%3B%2C%20April%2014%2C%202025%2C%201%5Cu201312.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1080%5C%2F17538068.2025.2487378.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22A%20comparative%20analysis%20of%20CDC%20and%20AI-generated%20health%20information%20using%20computer-aided%20text%20analysis%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Anna%22%2C%22lastName%22%3A%22Young%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Foluke%22%2C%22lastName%22%3A%22Omosun%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20AI-generated%20content%20is%20easy%20to%20access.%20Members%20of%20the%20public%20use%20it%20as%20an%20alternative%20or%20to%20supplement%20official%20sources%2C%20such%20as%20the%20Centers%20for%20Disease%20Control%20and%20Prevention%20%28CDC%29.%20However%2C%20the%20quality%20and%20reliability%20of%20AI-generated%20health%20information%20is%20questionable.%20This%20study%20aims%20to%20understand%20how%20AI-generated%20health%20information%20differs%20from%20that%20provided%20by%20the%20CDC%2C%20particularly%20in%20terms%20of%20sentiment%2C%20readability%2C%20and%20overall%20quality.%20Language%20expectancy%20theory%20serves%20as%20a%20framework%20and%20offers%20insights%20into%20how%20people%26%23039%3Bs%20expectations%20of%20message%20content%20from%20different%20sources%20can%20influence%20perceived%20credibility%20and%20persuasiveness%20of%20such%20information.%5CnMETHODS%3A%20Computer-aided%20text%20analysis%20was%20used%20to%20analyze%2020%20text%20entries%20from%20the%20CDC%20and%2020%20entries%20generated%20by%20ChatGPT%203.5.%20Content%20analysis%20utilizing%20human%20coders%20was%20used%20to%20assess%20the%20quality%20of%20information.%5CnRESULTS%3A%20ChatGPT%20used%20more%20negative%20sentiments%2C%20particularly%20words%20associated%20with%20anger%2C%20sadness%2C%20and%20disgust.%20The%20CDC%26%23039%3Bs%20health%20messages%20were%20significantly%20easier%20to%20read%20than%20those%20generated%20by%20ChatGPT.%20Furthermore%2C%20ChatGPT%26%23039%3Bs%20responses%20required%20a%20higher%20reading%20grade%20level.%20In%20terms%20of%20quality%2C%20the%20CDC%26%23039%3Bs%20information%20was%20a%20little%20higher%20quality%20than%20that%20of%20ChatGPT%2C%20with%20significant%20differences%20in%20DISCERN%20scores.%5CnCONCLUSION%3A%20Public%20health%20professionals%20need%20to%20educate%20the%20general%20public%20about%20the%20complexity%20and%20quality%20of%20AI-generated%20health%20information.%20Health%20literacy%20programs%20should%20address%20topics%20about%20quality%20and%20readability%20of%20AI-generated%20content.%20Other%20recommendations%20for%20using%20AI-generated%20health%20information%20are%20provided.%22%2C%22date%22%3A%222025-04-14%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1080%5C%2F17538068.2025.2487378%22%2C%22ISSN%22%3A%221753-8076%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40229204%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T08%3A55%3A22Z%22%7D%7D%2C%7B%22key%22%3A%22CYUEH79F%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22McGrath%20et%20al.%22%2C%22parsedDate%22%3A%222025-04-14%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BMcGrath%2C%20Colman%2C%20Chun%20Wang%20Reinhard%20Chau%2C%20and%20Gustavo%20Fabi%26%23xE1%3Bn%20Molina.%20%26%23x201C%3BMonitoring%20Oral%20Health%20Remotely%3A%20Ethical%20Considerations%20When%20Using%20AI%20among%20Vulnerable%20Populations.%26%23x201D%3B%20%26lt%3Bi%26gt%3BFrontiers%20in%20Oral%20Health%26lt%3B%5C%2Fi%26gt%3B%206%20%28April%2014%2C%202025%29%3A%201587630.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.3389%5C%2Ffroh.2025.1587630%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.3389%5C%2Ffroh.2025.1587630%26lt%3B%5C%2Fa%26gt%3B.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Monitoring%20oral%20health%20remotely%3A%20ethical%20considerations%20when%20using%20AI%20among%20vulnerable%20populations%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Colman%22%2C%22lastName%22%3A%22McGrath%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Chun%20Wang%20Reinhard%22%2C%22lastName%22%3A%22Chau%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gustavo%20Fabi%5Cu00e1n%22%2C%22lastName%22%3A%22Molina%22%7D%5D%2C%22abstractNote%22%3A%22Technological%20innovations%20in%20dentistry%20are%20revolutionizing%20the%20monitoring%20and%20management%20of%20oral%20health.%20This%20perspective%20article%20critically%20examines%20the%20rapid%20expansion%20of%20remote%20monitoring%20technologies-including%20artificial%20intelligence%20%28AI%29-driven%20diagnostics%2C%20electronic%20health%20records%20%28EHR%29%2C%20wearable%20devices%2C%20mobile%20health%20applications%2C%20and%20chatbots-and%20discusses%20their%20ethical%2C%20legal%2C%20and%20social%20implications.%20The%20accelerated%20adoption%20of%20these%20digital%20tools%2C%20particularly%20in%20the%20wake%20of%20the%20COVID-19%20pandemic%2C%20has%20enhanced%20accessibility%20to%20care%20while%20simultaneously%20raising%20significant%20concerns%20regarding%20patient%20consent%2C%20data%20privacy%2C%20and%20algorithmic%20biases.%20We%20review%20current%20applications%20ranging%20from%20AI-assisted%20detection%20of%20dental%20pathologies%20to%20blockchain-enabled%20data%20transfer%20within%20EHR%20systems%2C%20highlighting%20the%20potential%20for%20improved%20diagnostic%20accuracy%20and%20the%20risks%20associated%20with%20over-reliance%20on%20remote%20assessments.%20Furthermore%2C%20we%20underscore%20the%20challenges%20posed%20by%20the%20digital%20divide%2C%20where%20disparities%20in%20digital%20literacy%20and%20access%20may%20inadvertently%20exacerbate%20existing%20socio-economic%20and%20health%20inequalities.%20This%20article%20calls%20for%20the%20development%20and%20rigorous%20implementation%20of%20ethical%20frameworks%20and%20regulatory%20guidelines%20that%20ensure%20the%20reliability%2C%20transparency%2C%20and%20accountability%20of%20digital%20health%20innovations.%20By%20integrating%20multidisciplinary%20insights%2C%20our%20discussion%20aims%20to%20foster%20a%20balanced%20approach%20that%20maximizes%20the%20clinical%20benefits%20of%20emerging%20technologies%20while%20safeguarding%20patient%20autonomy%20and%20promoting%20equitable%20healthcare%20delivery.%22%2C%22date%22%3A%222025-04-14%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.3389%5C%2Ffroh.2025.1587630%22%2C%22ISSN%22%3A%222673-4842%22%2C%22url%22%3A%22%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%2C%22GUHR6SSX%22%5D%2C%22dateModified%22%3A%222025-05-21T08%3A37%3A09Z%22%7D%7D%2C%7B%22key%22%3A%223SWRBM6T%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Lavoie-Gagne%20et%20al.%22%2C%22parsedDate%22%3A%222025-04-12%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BLavoie-Gagne%2C%20Ophelie%20Z.%2C%20Oscar%20Y.%20Shen%2C%20Neal%20C.%20Chen%2C%20and%20Abhiram%20R.%20Bhashyam.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40219840%5C%2F%26%23039%3B%26gt%3BAssessing%20the%20Usability%20of%20ChatGPT%20Responses%20Compared%20to%20Other%20Online%20Information%20in%20Hand%20Surgery%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BHand%20%28New%20York%2C%20N.Y.%29%26lt%3B%5C%2Fi%26gt%3B%2C%20April%2012%2C%202025%2C%2015589447251329584.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1177%5C%2F15589447251329584.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Assessing%20the%20Usability%20of%20ChatGPT%20Responses%20Compared%20to%20Other%20Online%20Information%20in%20Hand%20Surgery%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ophelie%20Z.%22%2C%22lastName%22%3A%22Lavoie-Gagne%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Oscar%20Y.%22%2C%22lastName%22%3A%22Shen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Neal%20C.%22%2C%22lastName%22%3A%22Chen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Abhiram%20R.%22%2C%22lastName%22%3A%22Bhashyam%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20ChatGPT%20is%20a%20natural%20language%20processing%20tool%20with%20potential%20to%20increase%20accessibility%20of%20health%20information.%20This%20study%20aimed%20to%3A%20%281%29%20assess%20usability%20of%20online%20medical%20information%20for%20hand%20surgery%20topics%3B%20and%20%282%29%20evaluate%20the%20influence%20of%20medical%20consensus.%5CnMETHODS%3A%20Three%20phrases%20were%20posed%2020%20times%20each%20to%20Google%2C%20ChatGPT-3.5%2C%20and%20ChatGPT-4.0%3A%20%26quot%3BWhat%20is%20the%20cause%20of%20carpal%20tunnel%20syndrome%3F%26quot%3B%20%28high%20consensus%29%2C%20%26quot%3BWhat%20is%20the%20cause%20of%20tennis%20elbow%3F%26quot%3B%20%28moderate%20consensus%29%2C%20and%20%26quot%3BPlatelet-rich%20plasma%20for%20thumb%20arthritis%3F%26quot%3B%20%28low%20consensus%29.%20Readability%20was%20assessed%20by%20grade%20level%20while%20reliability%20and%20accuracy%20were%20scored%20based%20on%20predetermined%20rubrics.%20Scores%20were%20compared%20via%20Mann-Whitney%20U%20tests%20with%20alpha%20set%20to%20.05.%5CnRESULTS%3A%20Google%20responses%20had%20superior%20readability%20for%20moderate-high%20consensus%20topics%20%28P%20%26lt%3B%20.0001%29%20with%20an%20average%20eighth-grade%20reading%20level%20compared%20to%20college%20sophomore%20level%20for%20ChatGPT.%20Low%20consensus%20topics%20had%20poor%20readability%20throughout.%20ChatGPT-4%20responses%20had%20similar%20reliability%20but%20significantly%20inferior%20readability%20to%20ChatGPT-3.5%20for%20low%20medical%20consensus%20topics%20%28P%20%26lt%3B%20.01%29.%20There%20was%20no%20significant%20difference%20in%20accuracy%20between%20sources.%20ChatGPT-4%20and%20Google%20had%20differing%20coverage%20of%20cause%20of%20disease%20%28P%20%26lt%3B%20.05%29%20and%20procedure%20details%5C%2Fefficacy%5C%2Falternatives%20%28P%20%26lt%3B%20.05%29%20with%20similar%20coverage%20of%20anatomy%20and%20pathophysiology.%5CnCONCLUSIONS%3A%20Compared%20to%20Google%2C%20ChatGPT%20does%20not%20provide%20readable%20responses%20when%20providing%20reliable%20medical%20information.%20While%20patients%20can%20modulate%20ChatGPT%20readability%20with%20prompt%20engineering%2C%20this%20requires%20insight%20into%20their%20health%20literacy%20and%20is%20an%20additional%20barrier%20to%20accessing%20medical%20information.%20Medical%20consensus%20influences%20usability%20of%20online%20medical%20information%20for%20both%20Google%20and%20ChatGPT.%20Providers%20should%20remain%20aware%20of%20ChatGPT%20limitations%20in%20distributing%20medical%20information.%22%2C%22date%22%3A%222025-04-12%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1177%5C%2F15589447251329584%22%2C%22ISSN%22%3A%221558-9455%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40219840%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T08%3A57%3A25Z%22%7D%7D%2C%7B%22key%22%3A%2285MMNY6I%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Stephenson-Moe%20et%20al.%22%2C%22parsedDate%22%3A%222025-04-11%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BStephenson-Moe%2C%20Christoph%20A.%2C%20Benjamin%20J.%20Behers%2C%20Rebecca%20M.%20Gibons%2C%20Brett%20M.%20Behers%2C%20Laura%20De%20Jesus%20Herrera%2C%20Djhemson%20Anneaud%2C%20Manuel%20A.%20Rosario%2C%20Caroline%20N.%20Wojtas%2C%20Samantha%20Bhambrah%2C%20and%20Karen%20M.%20Hamad.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40228277%5C%2F%26%23039%3B%26gt%3BAssessing%20the%20quality%20and%20readability%20of%20patient%20education%20materials%20on%20chemotherapy%20cardiotoxicity%20from%20artificial%20intelligence%20chatbots%3A%20An%20observational%20cross-sectional%20study%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BMedicine%26lt%3B%5C%2Fi%26gt%3B%20104%2C%20no.%2015%20%28April%2011%2C%202025%29%3A%20e42135.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1097%5C%2FMD.0000000000042135.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Assessing%20the%20quality%20and%20readability%20of%20patient%20education%20materials%20on%20chemotherapy%20cardiotoxicity%20from%20artificial%20intelligence%20chatbots%3A%20An%20observational%20cross-sectional%20study%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Christoph%20A.%22%2C%22lastName%22%3A%22Stephenson-Moe%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Benjamin%20J.%22%2C%22lastName%22%3A%22Behers%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rebecca%20M.%22%2C%22lastName%22%3A%22Gibons%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Brett%20M.%22%2C%22lastName%22%3A%22Behers%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Laura%20De%22%2C%22lastName%22%3A%22Jesus%20Herrera%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Djhemson%22%2C%22lastName%22%3A%22Anneaud%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Manuel%20A.%22%2C%22lastName%22%3A%22Rosario%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Caroline%20N.%22%2C%22lastName%22%3A%22Wojtas%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Samantha%22%2C%22lastName%22%3A%22Bhambrah%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Karen%20M.%22%2C%22lastName%22%3A%22Hamad%22%7D%5D%2C%22abstractNote%22%3A%22Artificial%20intelligence%20%28AI%29%20and%20the%20introduction%20of%20Large%20Language%20Model%20%28LLM%29%20chatbots%20have%20become%20a%20common%20source%20of%20patient%20inquiry%20in%20healthcare.%20The%20quality%20and%20readability%20of%20AI-generated%20patient%20education%20materials%20%28PEM%29%20is%20the%20subject%20of%20many%20studies%20across%20multiple%20medical%20topics.%20Most%20demonstrate%20poor%20readability%20and%20acceptable%20quality.%20However%2C%20an%20area%20yet%20to%20be%20investigated%20is%20chemotherapy-induced%20cardiotoxicity.%20This%20study%20seeks%20to%20assess%20the%20quality%20and%20readability%20of%20chatbot%20created%20PEM%20relative%20to%20chemotherapy-induced%20cardiotoxicity.%20We%20conducted%20an%20observational%20cross-sectional%20study%20in%20August%202024%20by%20asking%2010%20questions%20to%204%20chatbots%3A%20ChatGPT%2C%20Microsoft%20Copilot%20%28Copilot%29%2C%20Google%20Gemini%20%28Gemini%29%2C%20and%20Meta%20AI%20%28Meta%29.%20The%20generated%20material%20was%20assessed%20for%20readability%20using%207%20tools%3A%20Flesch%20Reading%20Ease%20Score%20%28FRES%29%2C%20Flesch-Kincaid%20Grade%20Level%20%28FKGL%29%2C%20Gunning%20Fog%20Index%20%28GFI%29%2C%20Coleman-Liau%20Index%20%28CLI%29%2C%20Simple%20Measure%20of%20Gobbledygook%20%28SMOG%29%20Index%2C%20Automated%20Readability%20Index%20%28ARI%29%2C%20and%20FORCAST%20Grade%20Level.%20Quality%20was%20assessed%20using%20modified%20versions%20of%202%20validated%20tools%3A%20the%20Patient%20Education%20Materials%20Assessment%20Tool%20%28PEMAT%29%2C%20which%20outputs%20a%200%25%20to%20100%25%20score%2C%20and%20DISCERN%2C%20a%201%20%28unsatisfactory%29%20to%205%20%28highly%20satisfactory%29%20scoring%20system.%20Descriptive%20statistics%20were%20used%20to%20evaluate%20performance%20and%20compare%20chatbots%20amongst%20each%20other.%20Mean%20reading%20grade%20level%20%28RGL%29%20across%20all%20chatbots%20was%2013.7.%20Calculated%20RGLs%20for%20ChatGPT%2C%20Copilot%2C%20Gemini%20and%20Meta%20were%2014.2%2C%2014.0%2C%2012.5%2C%2014.2%2C%20respectively.%20Mean%20DISCERN%20scores%20across%20the%20chatbots%20was%204.2.%20DISCERN%20scores%20for%20ChatGPT%2C%20Copilot%2C%20Gemini%2C%20and%20Meta%20were%204.2%2C%204.3%2C%204.2%2C%20and%203.9%2C%20respectively.%20Median%20PEMAT%20scores%20for%20understandability%20and%20actionability%20were%2091.7%25%20and%2075%25%2C%20respectively.%20Understandability%20and%20actionability%20scores%20for%20ChatGPT%2C%20Copilot%2C%20Gemini%2C%20and%20Meta%20were%20100%25%20and%2075%25%2C%2091.7%25%20and%2075%25%2C%2090.9%25%20and%2075%25%2C%20and%2091.7%25%20and%2050%25%2C%20respectively.%20AI%20chatbots%20produce%20high%20quality%20PEM%20with%20poor%20readability.%20We%20do%20not%20discourage%20using%20chatbots%20to%20create%20PEM%20but%20recommend%20cautioning%20patients%20about%20their%20readability%20concerns.%20AI%20chatbots%20are%20not%20an%20alternative%20to%20a%20healthcare%20provider.%20Furthermore%2C%20there%20is%20no%20consensus%20on%20which%20chatbots%20create%20the%20highest%20quality%20PEM.%20Future%20studies%20are%20needed%20to%20assess%20the%20effectiveness%20of%20AI%20chatbots%20in%20providing%20PEM%20to%20patients%20and%20how%20the%20capabilities%20of%20AI%20chatbots%20are%20changing%20over%20time.%22%2C%22date%22%3A%222025-04-11%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1097%5C%2FMD.0000000000042135%22%2C%22ISSN%22%3A%221536-5964%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40228277%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T08%3A56%3A21Z%22%7D%7D%2C%7B%22key%22%3A%22U5YXSLMB%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22van%20Driel%20et%20al.%22%2C%22parsedDate%22%3A%222025-04-11%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BDriel%2C%20M.%20H.%20Elise%20van%2C%20Noa%20Blok%2C%20Jan%20A.%20J.%20G.%20van%20den%20Brand%2C%20Davy%20van%20de%20Sande%2C%20Marianne%20de%20Vries%2C%20Bram%20Eijlers%2C%20Fokko%20Smits%2C%20et%20al.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40294519%5C%2F%26%23039%3B%26gt%3BLeveraging%20GPT-4%20enables%20patient%20comprehension%20of%20radiology%20reports%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BEuropean%20Journal%20of%20Radiology%26lt%3B%5C%2Fi%26gt%3B%20187%20%28April%2011%2C%202025%29%3A%20112111.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.ejrad.2025.112111.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Leveraging%20GPT-4%20enables%20patient%20comprehension%20of%20radiology%20reports%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22M.%20H.%20Elise%22%2C%22lastName%22%3A%22van%20Driel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Noa%22%2C%22lastName%22%3A%22Blok%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jan%20A.%20J.%20G.%22%2C%22lastName%22%3A%22van%20den%20Brand%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Davy%22%2C%22lastName%22%3A%22van%20de%20Sande%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marianne%22%2C%22lastName%22%3A%22de%20Vries%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bram%22%2C%22lastName%22%3A%22Eijlers%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fokko%22%2C%22lastName%22%3A%22Smits%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jacob%20J.%22%2C%22lastName%22%3A%22Visser%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Diederik%22%2C%22lastName%22%3A%22Gommers%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Cornelis%22%2C%22lastName%22%3A%22Verhoef%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michel%20E.%22%2C%22lastName%22%3A%22van%20Genderen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dirk%20J.%22%2C%22lastName%22%3A%22Gr%5Cu00fcnhagen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Denise%20E.%22%2C%22lastName%22%3A%22Hilling%22%7D%5D%2C%22abstractNote%22%3A%22OBJECTIVE%3A%20To%20assess%20the%20feasibility%20of%20using%20GPT-4%20to%20simplify%20radiology%20reports%20into%20B1-level%20Dutch%20for%20enhanced%20patient%20comprehension.%5CnMETHODS%3A%20This%20study%20utilised%20GPT-4%2C%20optimised%20through%20prompt%20engineering%20in%20Microsoft%20Azure.%20The%20researchers%20iteratively%20refined%20prompts%20to%20ensure%20accurate%20and%20comprehensive%20translations%20of%20radiology%20reports.%20Two%20radiologists%20assessed%20the%20simplified%20outputs%20for%20accuracy%2C%20completeness%2C%20and%20patient%20suitability.%20A%20third%20radiologist%20independently%20validated%20the%20final%20versions.%20Twelve%20colorectal%20cancer%20patients%20were%20recruited%20from%20two%20hospitals%20in%20the%20Netherlands.%20Semi-structured%20interviews%20were%20conducted%20to%20evaluate%20patients%26%23039%3B%20comprehension%20and%20satisfaction%20with%20AI-generated%20reports.%5CnRESULTS%3A%20The%20optimised%20GPT-4%20tool%20produced%20simplified%20reports%20with%20high%20accuracy%20%28mean%20score%203.33%5C%2F4%29.%20Patient%20comprehension%20improved%20significantly%20from%202.00%20%28original%20reports%29%20to%203.28%20%28simplified%20reports%29%20and%203.50%20%28summaries%29.%20Correct%20classification%20of%20report%20outcomes%20increased%20from%2063.9%25%20to%2083.3%25.%20Patient%20satisfaction%20was%20high%20%28mean%208.30%5C%2F10%29%2C%20with%20most%20preferring%20the%20long%20simplified%20report.%5CnCONCLUSION%3A%20RADiANT%20successfully%20enhances%20patient%20understanding%20and%20satisfaction%20through%20automated%20AI-driven%20report%20simplification%2C%20offering%20a%20scalable%20solution%20for%20patient-centred%20communication%20in%20clinical%20practice.%20This%20tool%20reduces%20clinician%20workload%20and%20supports%20informed%20patient%20decision-making%2C%20demonstrating%20the%20potential%20of%20LLMs%20beyond%20English-based%20healthcare%20contexts.%22%2C%22date%22%3A%222025-04-11%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1016%5C%2Fj.ejrad.2025.112111%22%2C%22ISSN%22%3A%221872-7727%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40294519%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T08%3A35%3A18Z%22%7D%7D%2C%7B%22key%22%3A%22RDME7KUQ%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Sendlhofer%22%2C%22parsedDate%22%3A%222025-04-11%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BSendlhofer%2C%20Gerald.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2Fs00740-025-00556-4%26%23039%3B%26gt%3BSmart%20Hospital%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BWiener%20klinisches%20Magazin%26lt%3B%5C%2Fi%26gt%3B%2C%20April%2011%2C%202025.%20%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Smart%20Hospital%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gerald%22%2C%22lastName%22%3A%22Sendlhofer%22%7D%5D%2C%22abstractNote%22%3A%22Das%20Thema%20Patientensicherheit%20hat%20in%20den%20letzten%20Jahrzehnten%20an%20Bedeutung%20gewonnen%2C%20insbesondere%20seit%20dem%20Bericht%20%5Cu201eTo%20Err%20is%20Human%5Cu201c%20im%20Jahr%201999.%20Studien%20zeigen%2C%20dass%20die%20Fehlerquote%20im%20Gesundheitswesen%20h%5Cu00f6her%20ist%20als%20angenommen%2C%20wobei%20Medikationsfehler%2C%20Verwechslungen%20und%20Kommunikationsfehler%20sehr%20h%5Cu00e4ufig%20vorkommen.%20Vor%20der%20Pandemie%20waren%20die%20meisten%20Projekte%20analoger%20Natur%2C%20so%20wurden%20verschiedene%20Ma%5Cu00dfnahmen%20wie%20Checklisten%20oder%20Scores%20entwickelt%2C%20doch%20seit%202020%20liegt%20der%20Fokus%20zunehmend%20auf%20digitalen%20L%5Cu00f6sungen%20inklusive%20der%20Nutzung%20von%20k%5Cu00fcnstlicher%20Intelligenz.%20Der%20Begriff%20%5Cu201eSmart%20Hospital%5Cu201c%20wird%20seither%20meist%20mit%20digitalen%20L%5Cu00f6sungen%20verkn%5Cu00fcpft%2C%20jedoch%20steht%20der%20Begriff%20vielmehr%20f%5Cu00fcr%20eine%20Kombination%20aus%20Digitalisierung%20und%20Anpassung%20von%20herk%5Cu00f6mmlichen%20Arbeitsabl%5Cu00e4ufen.%20Um%20das%20Thema%20der%20Digitalisierung%20in%20Kombination%20mit%20den%20M%5Cu00f6glichkeiten%20der%20k%5Cu00fcnstlichen%20Intelligenz%20%28KI%29%20an%20einem%20konkreten%20Beispiel%20festzumachen%2C%20wird%20in%20folgendem%20das%20Risiko%20eines%20Medikationsfehlers%20herangezogen.%20Medikationsfehler%20sind%20ein%20zentrales%20Problem%2C%20%5Cu00dcber-%20oder%20Unterdosierung%2C%20ein%20falsches%20oder%20fehlendes%20Medikament%20kommen%20h%5Cu00e4ufig%20vor%20und%20weltweit%20sterben%20etwa%20alleine%20durch%20unleserliche%20Schrift%20ca.%5Cu00a07000%20Menschen.%20Digitale%20L%5Cu00f6sungen%20k%5Cu00f6nnen%20die%20Fehlerrate%20im%20Medikationsprozess%20signifikant%20reduzieren.%20Ein%20Forschungsprojekt%20der%20Medizinischen%20Universit%5Cu00e4t%20Graz%20untersucht%2C%20wie%20k%5Cu00fcnstliche%20Intelligenz%20zur%20Optimierung%20des%20Medikationsprozesses%20beitragen%20kann.%20Vorteile%20digitaler%20Systeme%20umfassen%20die%20Reduktion%20von%20Fehlern%20und%20die%20Entlastung%20des%20Personals.%20Technologische%20Innovationen%20bringen%20sowohl%20Chancen%20als%20auch%20Herausforderungen%20mit%20sich%2C%20wobei%20die%20Akzeptanz%20oft%20nach%20anf%5Cu00e4nglichem%20Widerstand%20steigt.%20Durch%20Digitalisierung%20und%20KI%20kann%20zweifelsfrei%20die%20Sicherheit%20von%20Patienten%20und%20Mitarbeitern%20erh%5Cu00f6ht%20werden%2C%20es%20gilt%20die%20richtigen%20Instrumente%20im%20richtigen%20Prozessschritt%20zu%20erarbeiten%20und%20zu%20implementieren.%22%2C%22date%22%3A%222025-04-11%22%2C%22language%22%3A%22de%22%2C%22DOI%22%3A%2210.1007%5C%2Fs00740-025-00556-4%22%2C%22ISSN%22%3A%221613-7817%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2Fs00740-025-00556-4%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%222G8YLGV7%22%2C%22CKAPKQE5%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-19T10%3A26%3A03Z%22%7D%7D%2C%7B%22key%22%3A%222M6MXJ9W%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Liu%20et%20al.%22%2C%22parsedDate%22%3A%222025-04-08%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BLiu%2C%20Xiao%2C%20Anjana%20Susarla%2C%20and%20Rema%20Padman.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40198918%5C%2F%26%23039%3B%26gt%3BPromoting%20Health%20Literacy%20With%20Human-in-the-Loop%20Video%20Understandability%20Classification%20of%20YouTube%20Videos%3A%20Development%20and%20Evaluation%20Study%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BJournal%20of%20Medical%20Internet%20Research%26lt%3B%5C%2Fi%26gt%3B%2027%20%28April%208%2C%202025%29%3A%20e56080.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.2196%5C%2F56080.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Promoting%20Health%20Literacy%20With%20Human-in-the-Loop%20Video%20Understandability%20Classification%20of%20YouTube%20Videos%3A%20Development%20and%20Evaluation%20Study%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xiao%22%2C%22lastName%22%3A%22Liu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Anjana%22%2C%22lastName%22%3A%22Susarla%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rema%22%2C%22lastName%22%3A%22Padman%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20An%20estimated%2093%25%20of%20adults%20in%20the%20United%20States%20access%20the%20internet%2C%20with%20up%20to%2080%25%20looking%20for%20health%20information.%20However%2C%20only%2012%25%20of%20US%20adults%20are%20proficient%20enough%20in%20health%20literacy%20to%20interpret%20health%20information%20and%20make%20informed%20health%20care%20decisions%20meaningfully.%20With%20the%20vast%20amount%20of%20health%20information%20available%20in%20multimedia%20formats%20on%20social%20media%20platforms%20such%20as%20YouTube%20and%20Facebook%2C%20there%20is%20an%20urgent%20need%20and%20a%20unique%20opportunity%20to%20design%20an%20automated%20approach%20to%20curate%20online%20health%20information%20using%20multiple%20criteria%20to%20meet%20the%20health%20literacy%20needs%20of%20a%20diverse%20population.%5CnOBJECTIVE%3A%20This%20study%20aimed%20to%20develop%20an%20automated%20approach%20to%20assessing%20the%20understandability%20of%20patient%20educational%20videos%20according%20to%20the%20Patient%20Education%20Materials%20Assessment%20Tool%20%28PEMAT%29%20guidelines%20and%20evaluating%20the%20impact%20of%20video%20understandability%20on%20viewer%20engagement.%20We%20also%20offer%20insights%20for%20content%20creators%20and%20health%20care%20organizations%20on%20how%20to%20improve%20engagement%20with%20these%20educational%20videos%20on%20user-generated%20content%20platforms.%5CnMETHODS%3A%20We%20developed%20a%20human-in-the-loop%2C%20augmented%20intelligence%20approach%20that%20explicitly%20focused%20on%20the%20human-algorithm%20interaction%2C%20combining%20PEMAT-based%20patient%20education%20constructs%20mapped%20to%20features%20extracted%20from%20the%20videos%2C%20annotations%20of%20the%20videos%20by%20domain%20experts%2C%20and%20cotraining%20methods%20from%20machine%20learning%20to%20assess%20the%20understandability%20of%20videos%20on%20diabetes%20and%20classify%20them.%20We%20further%20examined%20the%20impact%20of%20understandability%20on%20several%20dimensions%20of%20viewer%20engagement%20with%20the%20videos.%5CnRESULTS%3A%20We%20collected%209873%20YouTube%20videos%20on%20diabetes%20using%20search%20keywords%20extracted%20from%20a%20patient-oriented%20forum%20and%20reviewed%20by%20a%20medical%20expert.%20Our%20machine%20learning%20methods%20achieved%20a%20weighted%20precision%20of%200.84%2C%20a%20weighted%20recall%20of%200.79%2C%20and%20an%20F1-score%20of%200.81%20in%20classifying%20video%20understandability%20and%20could%20effectively%20identify%20patient%20educational%20videos%20that%20medical%20experts%20would%20like%20to%20recommend%20for%20patients.%20Videos%20rated%20as%20highly%20understandable%20had%20an%20average%20higher%20view%20count%20%28average%20treatment%20effect%20%5BATE%5D%3D2.55%3B%20P%26lt%3B.001%29%2C%20like%20count%20%28ATE%3D2.95%3B%20P%26lt%3B.001%29%2C%20and%20comment%20count%20%28ATE%3D3.10%3B%20P%26lt%3B.001%29%20than%20less%20understandable%20videos.%20In%20addition%2C%20in%20a%20user%20study%2C%204%20medical%20experts%20recommended%2072%25%20%28144%5C%2F200%29%20of%20the%20top%2010%20videos%20ranked%20by%20understandability%20compared%20to%2040%25%20%2880%5C%2F200%29%20of%20the%20top%2010%20videos%20ranked%20by%20YouTube%26%23039%3Bs%20default%20algorithm%20for%2020%20ramdomly%20selected%20search%20keywords.%5CnCONCLUSIONS%3A%20We%20developed%20a%20human-in-the-loop%2C%20scalable%20algorithm%20to%20assess%20the%20understandability%20of%20health%20information%20on%20YouTube.%20Our%20method%20optimally%20combines%20expert%20input%20with%20algorithmic%20support%2C%20enhancing%20engagement%20and%20aiding%20medical%20experts%20in%20recommending%20educational%20content.%20This%20solution%20also%20guides%20health%20care%20organizations%20in%20creating%20effective%20patient%20education%20materials%20for%20underserved%20health%20topics.%22%2C%22date%22%3A%222025-04-08%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.2196%5C%2F56080%22%2C%22ISSN%22%3A%221438-8871%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40198918%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T09%3A02%3A46Z%22%7D%7D%2C%7B%22key%22%3A%22UF3RFYL6%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Staccini%20et%20al.%22%2C%22parsedDate%22%3A%222025-04-08%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BStaccini%2C%20Pascal%2C%20Annie%20Y.%20S.%20Lau%2C%20and%20Findings%20from%20the%20Yearbook%202024%20Section%20on%20Consumer%20Health%20Informatics.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40199301%5C%2F%26%23039%3B%26gt%3BPrecision%20in%20Prevention%20and%20Health%20Surveillance%3A%20How%20Artificial%20Intelligence%20May%20Improve%20the%20Time%20of%20Identification%20of%20Health%20Concerns%20through%20Social%20Media%20Content%20Analysis%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BYearbook%20of%20Medical%20Informatics%26lt%3B%5C%2Fi%26gt%3B%2033%2C%20no.%201%20%28April%208%2C%202025%29%3A%20158%5Cu201365.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1055%5C%2Fs-0044-1800736.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Precision%20in%20Prevention%20and%20Health%20Surveillance%3A%20How%20Artificial%20Intelligence%20May%20Improve%20the%20Time%20of%20Identification%20of%20Health%20Concerns%20through%20Social%20Media%20Content%20Analysis%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pascal%22%2C%22lastName%22%3A%22Staccini%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Annie%20Y.%20S.%22%2C%22lastName%22%3A%22Lau%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22name%22%3A%22Findings%20from%20the%20Yearbook%202024%20Section%20on%20Consumer%20Health%20Informatics%22%7D%5D%2C%22abstractNote%22%3A%22OBJECTIVE%3A%20To%20explore%20how%20artificial%20intelligence%20%28AI%29%20methodologies%2C%20particularly%20through%20the%20analysis%20of%20social%20media%20content%2C%20can%20enhance%20%26quot%3Bprecision%20in%20prevention%20and%20health%20surveillance%26quot%3B%20%282024%20Yearbook%20topic%29.%20The%20focus%20is%20on%20leveraging%20advanced%20data%20analytics%20to%20improve%20the%20timeliness%20and%20accuracy%20of%20identifying%20emerging%20health%20concerns%2C%20thus%20enabling%20more%20proactive%20and%20effective%20health%20interventions.%5CnMETHODS%3A%20A%20comprehensive%20literature%20search%20strategy%20was%20conducted%20on%20PubMed%2C%20focusing%20on%20papers%20published%20in%202023%20related%20to%20consumer%20health%20informatics%2C%20precision%20prevention%2C%20and%20the%20intersection%20with%20social%20media.%20The%20search%20aimed%20to%20identify%20studies%20that%20utilized%20AI%20and%20machine%20learning%20techniques%20to%20analyse%20social%20media%20data%20for%20health%20surveillance%20purposes.%20Bibliometric%20analyses%20were%20applied%20to%20the%20retrieved%20articles%2C%20and%20tools%20such%20as%20%26quot%3BBibliometrix%26quot%3B%20were%20used%20to%20assess%20keyword%20frequencies%2C%20co-occurrence%20networks%2C%20and%20thematic%20maps.%20The%20studies%20were%20then%20independently%20reviewed%20and%20screened%20for%20relevance%2C%20with%20a%20final%20selection%20of%2010%20articles%20made%20based%20on%20their%20alignment%20with%20the%202024%20Yearbook%20topic%20and%20their%20methodological%20innovation.%5CnRESULTS%3A%20The%20analysis%20of%2089%20articles%20revealed%20several%20key%20themes%20and%20findings.%20Social%20media%20data%20offers%20a%20rich%20source%20of%20real-time%20insights%20into%20public%20health%20trends%2C%20and%20encompasses%20diverse%20demographic%20groups.%20AI%20methodologies%2C%20including%20machine%20learning%2C%20natural%20language%20processing%20%28NLP%29%2C%20and%20deep%20learning%2C%20play%20a%20crucial%20role%20in%20extracting%20and%20analysing%20health-related%20information%20from%20social%20media%20content.%20The%20integration%20of%20AI%20in%20health%20surveillance%20can%20provide%20early%20warnings%20of%20potential%20health%20crises%2C%20as%20demonstrated%20by%20studies%20on%20topics%20such%20as%20suicide%20prevention%2C%20mental%20health%2C%20and%20the%20impact%20of%20social%20media%20use%20on%20e-cigarette%20consumption%20among%20youth.%20Ethical%20and%20privacy%20considerations%20are%20paramount%2C%20necessitating%20robust%20data%20anonymization%20and%20transparent%20data%20handling%20practices.%20Advanced%20AI%20techniques%2C%20such%20as%20transformer-based%20topic%20modelling%20and%20federated%20learning%2C%20enhance%20the%20precision%20and%20security%20of%20health%20surveillance%20systems.%20The%20document%20highlights%20several%20case%20studies%20that%20demonstrate%20the%20practical%20applications%20of%20AI%20in%20health%20surveillance%2C%20such%20as%20monitoring%20public%20discussions%20about%20delta-8%20THC%20and%20assessing%20suicide-related%20tweets%20and%20their%20association%20with%20help-seeking%20behaviour%20in%20the%20US.%5CnCONCLUSION%3A%20Integrating%20AI%20and%20social%20media%20content%20analysis%20in%20precision%20prevention%20and%20health%20surveillance%20has%20significant%20potential%20to%20improve%20public%20health%20outcomes.%20By%20leveraging%20real-time%2C%20comprehensive%20data%20from%20social%20media%20platforms%2C%20AI%20can%20enhance%20the%20timeliness%20and%20accuracy%20of%20identifying%20health%20concerns.%20Addressing%20ethical%20and%20privacy%20challenges%20is%20crucial%20to%20ensure%20responsible%20and%20effective%20implementation.%20The%20continuous%20advancement%20of%20AI%20technologies%20will%20play%20a%20critical%20role%20in%20safeguarding%20public%20health%20and%20responding%20to%20emerging%20health%20threats.%22%2C%22date%22%3A%222025-04-08%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1055%5C%2Fs-0044-1800736%22%2C%22ISSN%22%3A%222364-0502%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40199301%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T08%3A39%3A21Z%22%7D%7D%2C%7B%22key%22%3A%22DJ2P92PK%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Hou%20et%20al.%22%2C%22parsedDate%22%3A%222025-04-07%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BHou%2C%20Zhiyuan%2C%20Zhengdong%20Wu%2C%20Zhiqiang%20Qu%2C%20Liubing%20Gong%2C%20Hui%20Peng%2C%20Mark%20Jit%2C%20Heidi%20J.%20Larson%2C%20Joseph%20T.%20Wu%2C%20and%20Leesa%20Lin.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40195450%5C%2F%26%23039%3B%26gt%3BA%20vaccine%20chatbot%20intervention%20for%20parents%20to%20improve%20HPV%20vaccination%20uptake%20among%20middle%20school%20girls%3A%20a%20cluster%20randomized%20trial%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BNature%20Medicine%26lt%3B%5C%2Fi%26gt%3B%2C%20April%207%2C%202025.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1038%5C%2Fs41591-025-03618-6.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22A%20vaccine%20chatbot%20intervention%20for%20parents%20to%20improve%20HPV%20vaccination%20uptake%20among%20middle%20school%20girls%3A%20a%20cluster%20randomized%20trial%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Zhiyuan%22%2C%22lastName%22%3A%22Hou%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Zhengdong%22%2C%22lastName%22%3A%22Wu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Zhiqiang%22%2C%22lastName%22%3A%22Qu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Liubing%22%2C%22lastName%22%3A%22Gong%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hui%22%2C%22lastName%22%3A%22Peng%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Mark%22%2C%22lastName%22%3A%22Jit%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Heidi%20J.%22%2C%22lastName%22%3A%22Larson%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Joseph%20T.%22%2C%22lastName%22%3A%22Wu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Leesa%22%2C%22lastName%22%3A%22Lin%22%7D%5D%2C%22abstractNote%22%3A%22Conversational%20artificial%20intelligence%2C%20in%20the%20form%20of%20chatbots%20powered%20by%20large%20language%20models%2C%20offers%20a%20new%20approach%20to%20facilitating%20human-like%20interactions%2C%20yet%20its%20efficacy%20in%20enhancing%20vaccination%20uptake%20remains%20under-investigated.%20This%20study%20assesses%20the%20effectiveness%20of%20a%20vaccine%20chatbot%20in%20improving%20human%20papillomavirus%20%28HPV%29%20vaccination%20among%20female%20middle%20school%20students%20aged%2012-15%5Cu2009years%20across%20diverse%20socioeconomic%20settings%20in%20China%2C%20where%20HPV%20vaccination%20is%20primarily%20paid%20out-of-pocket.%20A%20school-based%20cluster%20randomized%20trial%20was%20conducted%20from%2018%20January%20to%2031%20May%202024.%20The%20study%20included%202%2C671%20parents%20from%20180%20middle%20school%20classes%20stratified%20by%20socioeconomic%20setting%2C%20school%20and%20grade%20level%20in%20Shanghai%20megacity%2C%20and%20urban%20and%20rural%20regions%20of%20Anhui%20Province.%20Participants%20were%20randomly%20assigned%20to%20either%20the%20intervention%20group%20%2890%20classes%2C%201%2C294%20parents%29%2C%20which%20engaged%20with%20the%20chatbot%20for%20two%20weeks%2C%20or%20the%20control%20group%20%2890%20classes%2C%201%2C377%20parents%29%2C%20which%20received%20usual%20care.%20The%20primary%20outcome%20was%20the%20receipt%20or%20scheduled%20appointment%20of%20the%20HPV%20vaccine%20for%20participants%26%23039%3B%20daughters.%20In%20intention-to-treat%20analyses%2C%207.1%25%20of%20the%20intervention%20group%20met%20this%20outcome%20versus%201.8%25%20of%20the%20control%20group%20%28P%5Cu2009%26lt%3B%5Cu20090.001%29%20over%20a%20two-week%20intervention%20period.%20In%20addition%2C%20there%20was%20a%20statistically%20significant%20increase%20in%20HPV%20vaccination-specific%20consultations%20with%20health%20professionals%20%2849.1%25%20versus%2017.6%25%2C%20P%5Cu2009%26lt%3B%5Cu20090.001%29%2C%20along%20with%20enhanced%20vaccine%20literacy%20%28P%5Cu2009%26lt%3B%5Cu20090.001%29%20and%20rumor%20discernment%20%28P%5Cu2009%26lt%3B%5Cu20090.001%29%20among%20participants%20using%20the%20chatbot.%20These%20findings%20indicate%20that%20the%20chatbot%20effectively%20increased%20vaccination%20and%20improved%20parental%20vaccine%20literacy%2C%20although%20further%20research%20is%20necessary%20to%20scale%20and%20sustain%20these%20gains.%20Clinical%20trial%20registration%3A%20NCT06227689%20.%22%2C%22date%22%3A%222025-04-07%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1038%5C%2Fs41591-025-03618-6%22%2C%22ISSN%22%3A%221546-170X%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40195450%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%226DTIS6M4%22%2C%22MDZ69LY7%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T09%3A03%3A46Z%22%7D%7D%2C%7B%22key%22%3A%22TPTB4VZC%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22El%20Arab%20et%20al.%22%2C%22parsedDate%22%3A%222025-04-04%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BEl%20Arab%2C%20Rabie%20Adel%2C%20Omayma%20Abdulaziz%20Al%20Moosa%2C%20Fuad%20H.%20Abuadas%2C%20and%20Joel%20Somerville.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40072926%5C%2F%26%23039%3B%26gt%3BThe%20Role%20of%20AI%20in%20Nursing%20Education%20and%20Practice%3A%20Umbrella%20Review%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BJournal%20of%20Medical%20Internet%20Research%26lt%3B%5C%2Fi%26gt%3B%2027%20%28April%204%2C%202025%29%3A%20e69881.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.2196%5C%2F69881.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22The%20Role%20of%20AI%20in%20Nursing%20Education%20and%20Practice%3A%20Umbrella%20Review%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rabie%20Adel%22%2C%22lastName%22%3A%22El%20Arab%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Omayma%20Abdulaziz%22%2C%22lastName%22%3A%22Al%20Moosa%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fuad%20H.%22%2C%22lastName%22%3A%22Abuadas%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Joel%22%2C%22lastName%22%3A%22Somerville%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20Artificial%20intelligence%20%28AI%29%20is%20rapidly%20transforming%20health%20care%2C%20offering%20substantial%20advancements%20in%20patient%20care%2C%20clinical%20workflows%2C%20and%20nursing%20education.%5CnOBJECTIVE%3A%20This%20umbrella%20review%20aims%20to%20evaluate%20the%20integration%20of%20AI%20into%20nursing%20practice%20and%20education%2C%20with%20a%20focus%20on%20ethical%20and%20social%20implications%2C%20and%20to%20propose%20evidence-based%20recommendations%20to%20support%20the%20responsible%20and%20effective%20adoption%20of%20AI%20technologies%20in%20nursing.%5CnMETHODS%3A%20We%20included%20systematic%20reviews%2C%20scoping%20reviews%2C%20rapid%20reviews%2C%20narrative%20reviews%2C%20literature%20reviews%2C%20and%20meta-analyses%20focusing%20on%20AI%20integration%20in%20nursing%2C%20published%20up%20to%20October%202024.%20A%20new%20search%20was%20conducted%20in%20January%202025%20to%20identify%20any%20potentially%20eligible%20reviews%20published%20thereafter.%20However%2C%20no%20new%20reviews%20were%20found.%20Eligibility%20was%20guided%20by%20the%20Sample%2C%20Phenomenon%20of%20Interest%2C%20Design%2C%20Evaluation%2C%20Research%20type%20framework%3B%20databases%20%28PubMed%20or%20MEDLINE%2C%20CINAHL%2C%20Web%20of%20Science%2C%20Embase%2C%20and%20IEEE%20Xplore%29%20were%20searched%20using%20comprehensive%20keywords.%20Two%20reviewers%20independently%20screened%20records%20and%20extracted%20data.%20Risk%20of%20bias%20was%20assessed%20with%20Risk%20of%20Bias%20in%20Systematic%20Reviews%20%28ROBIS%29%20and%20A%20Measurement%20Tool%20to%20Assess%20Systematic%20Reviews%2C%20version%202%20%28AMSTAR%202%29%2C%20which%20we%20adapted%20for%20systematic%20and%20nonsystematic%20review%20types.%20A%20thematic%20synthesis%20approach%2C%20conducted%20independently%20by%202%20reviewers%2C%20identified%20recurring%20patterns%20across%20the%20included%20reviews.%5CnRESULTS%3A%20The%20search%20strategy%20yielded%2018%20eligible%20studies%20after%20screening%20274%20records.%20These%20studies%20encompassed%20diverse%20methodologies%20and%20focused%20on%20nursing%20professionals%2C%20students%2C%20educators%2C%20and%20researchers.%20First%2C%20ethical%20and%20social%20implications%20were%20consistently%20highlighted%2C%20with%20studies%20emphasizing%20concerns%20about%20data%20privacy%2C%20algorithmic%20bias%2C%20transparency%2C%20accountability%2C%20and%20the%20necessity%20for%20equitable%20access%20to%20AI%20technologies.%20Second%2C%20the%20transformation%20of%20nursing%20education%20emerged%20as%20a%20critical%20area%2C%20with%20an%20urgent%20need%20to%20update%20curricula%20by%20integrating%20AI-driven%20educational%20tools%20and%20fostering%20both%20technical%20competencies%20and%20ethical%20decision-making%20skills%20among%20nursing%20students%20and%20professionals.%20Third%2C%20strategies%20for%20integration%20were%20identified%20as%20essential%20for%20effective%20implementation%2C%20calling%20for%20scalable%20models%2C%20robust%20ethical%20frameworks%2C%20and%20interdisciplinary%20collaboration%2C%20while%20also%20addressing%20key%20barriers%20such%20as%20resistance%20to%20AI%20adoption%2C%20lack%20of%20standardized%20AI%20education%2C%20and%20disparities%20in%20technology%20access.%5CnCONCLUSIONS%3A%20AI%20holds%20substantial%20promises%20for%20revolutionizing%20nursing%20practice%20and%20education.%20However%2C%20realizing%20this%20potential%20necessitates%20a%20strategic%20approach%20that%20addresses%20ethical%20concerns%2C%20integrates%20AI%20literacy%20into%20nursing%20curricula%2C%20and%20ensures%20equitable%20access%20to%20AI%20technologies.%20Limitations%20of%20this%20review%20include%20the%20heterogeneity%20of%20included%20studies%20and%20potential%20publication%20bias.%20Our%20findings%20underscore%20the%20need%20for%20comprehensive%20ethical%20frameworks%20and%20regulatory%20guidelines%20tailored%20to%20nursing%20applications%2C%20updated%20nursing%20curricula%20to%20include%20AI%20literacy%20and%20ethical%20training%2C%20and%20investments%20in%20infrastructure%20to%20promote%20equitable%20AI%20access.%20Future%20research%20should%20focus%20on%20developing%20standardized%20implementation%20strategies%20and%20evaluating%20the%20long-term%20impacts%20of%20AI%20integration%20on%20nursing%20practice%20and%20patient%20outcomes.%22%2C%22date%22%3A%222025-04-04%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.2196%5C%2F69881%22%2C%22ISSN%22%3A%221438-8871%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40072926%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%226DCTQ3Z4%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T09%3A19%3A07Z%22%7D%7D%2C%7B%22key%22%3A%22QJ9ALXEB%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22El-Sayed%20et%20al.%22%2C%22parsedDate%22%3A%222025-04-04%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BEl-Sayed%2C%20Ahmed%20Abdelwahab%20Ibrahim%2C%20Samira%20Ahmed%20Alsenany%2C%20Raghad%20Saad%20Eid%20Almalki%2C%20and%20Maha%20Gamal%20Ramadan%20Asal.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40215710%5C%2F%26%23039%3B%26gt%3BFostering%20creativity-nurturing%20behaviors%20among%20nurse%20educators%3A%20Investigating%20the%20interplay%20between%20evidence-based%20practice%20climate%20and%20artificial%20intelligence%20competence%20self-efficacy%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BNurse%20Education%20Today%26lt%3B%5C%2Fi%26gt%3B%20151%20%28April%204%2C%202025%29%3A%20106734.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.nedt.2025.106734.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Fostering%20creativity-nurturing%20behaviors%20among%20nurse%20educators%3A%20Investigating%20the%20interplay%20between%20evidence-based%20practice%20climate%20and%20artificial%20intelligence%20competence%20self-efficacy%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ahmed%20Abdelwahab%20Ibrahim%22%2C%22lastName%22%3A%22El-Sayed%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Samira%20Ahmed%22%2C%22lastName%22%3A%22Alsenany%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Raghad%20Saad%20Eid%22%2C%22lastName%22%3A%22Almalki%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maha%20Gamal%20Ramadan%22%2C%22lastName%22%3A%22Asal%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20Fostering%20creativity%20in%20nursing%20education%20is%20essential%20for%20equipping%20students%20with%20critical%20thinking%20and%20problem-solving%20skills.%20Nurse%20educators%20play%20a%20pivotal%20role%20in%20nurturing%20creativity%20among%20nursing%20students%2C%20yet%20their%20effectiveness%20is%20shaped%20by%20institutional%20and%20technological%20influences.%20While%20an%20evidence-based%20practice%20%28EBP%29%20climate%20provides%20a%20structured%20framework%20for%20innovative%20teaching%2C%20the%20increasing%20integration%20of%20artificial%20intelligence%20%28AI%29%20in%20education%20necessitates%20that%20educators%20develop%20AI%20competence%20self-efficacy.%20AI%20tools%2C%20such%20as%20personalized%20learning%20systems%2C%20adaptive%20simulations%2C%20and%20data-driven%20decision-making%20platforms%2C%20enhance%20creativity-nurturing%20behaviors%20by%20supporting%20individualized%20student%20engagement%20and%20dynamic%20problem-solving%20approaches.%20However%2C%20the%20extent%20to%20which%20AI%20competence%20self-efficacy%20strengthens%20the%20relationship%20between%20EBP%20climate%20and%20creativity-nurturing%20behaviors%20remains%20underexplored.%5CnOBJECTIVES%3A%20To%20examine%20the%20relationship%20between%20EBP%20climate%20and%20creativity-nurturing%20behaviors%20among%20nurse%20educators%2C%20with%20a%20specific%20focus%20on%20the%20moderating%20role%20of%20AI%20competence%20self-efficacy.%20The%20key%20research%20question%20is%3A%20Does%20AI%20competence%20self-efficacy%20enhance%20the%20positive%20effect%20of%20EBP%20climate%20on%20creativity-nurturing%20behaviors%20among%20nurse%20educators%3F%5CnDESIGN%3A%20A%20cross-sectional%20study.%5CnMETHODS%3A%20Data%20were%20collected%20from%20570%20nurse%20educators%20using%20a%20structured%20online%20questionnaire%20measuring%20EBP%20climate%2C%20AI%20competence%20self-efficacy%2C%20and%20creativity-nurturing%20behaviors.%20Regression%20analyses%2C%20including%20interaction%20terms%2C%20assessed%20the%20moderating%20role%20of%20AI%20competence%20self-efficacy.%5CnRESULTS%3A%20Findings%20indicate%20that%20both%20EBP%20climate%20and%20AI%20competence%20self-efficacy%20significantly%20predict%20creativity-nurturing%20behaviors.%20Furthermore%2C%20AI%20competence%20self-efficacy%20moderates%20this%20relationship%2C%20amplifying%20the%20positive%20effect%20for%20educators%20with%20higher%20AI%20competence.%5CnCONCLUSION%3A%20EBP%20climate%20and%20AI%20competence%20self-efficacy%20are%20crucial%20in%20fostering%20creativity-nurturing%20behaviors%20among%20nurse%20educators.%20Higher%20AI%20competence%20self-efficacy%20enhances%20the%20ability%20to%20leverage%20EBP%20climate%20for%20creative%20teaching.%5CnIMPLICATIONS%3A%20Nursing%20institutions%20should%20enhance%20AI%20competence%20among%20nurse%20educators%20through%20targeted%20AI%20literacy%20programs%2C%20faculty%20mentorship%2C%20and%20integration%20of%20AI-driven%20teaching%20tools%20to%20optimize%20creativity-nurturing%20behaviors%20within%20an%20evidence-based%20educational%20environment.%22%2C%22date%22%3A%222025-04-04%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1016%5C%2Fj.nedt.2025.106734%22%2C%22ISSN%22%3A%221532-2793%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40215710%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%226DCTQ3Z4%22%2C%22ZKMQLZWF%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T08%3A59%3A11Z%22%7D%7D%2C%7B%22key%22%3A%22R6JY5Q5X%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Olawade%20et%20al.%22%2C%22parsedDate%22%3A%222025-04-04%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BOlawade%2C%20David%20B.%2C%20Kusal%20Weerasinghe%2C%20Jennifer%20Teke%2C%20Maines%20Msiska%2C%20Stergios%20Boussios%2C%20and%20Eleni%20Hatzidimitriadou.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40198930%5C%2F%26%23039%3B%26gt%3BEvaluating%20AI%20adoption%20in%20healthcare%3A%20Insights%20from%20the%20information%20governance%20professionals%20in%20the%20United%20Kingdom%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BInternational%20Journal%20of%20Medical%20Informatics%26lt%3B%5C%2Fi%26gt%3B%20199%20%28April%204%2C%202025%29%3A%20105909.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.ijmedinf.2025.105909.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Evaluating%20AI%20adoption%20in%20healthcare%3A%20Insights%20from%20the%20information%20governance%20professionals%20in%20the%20United%20Kingdom%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22David%20B.%22%2C%22lastName%22%3A%22Olawade%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kusal%22%2C%22lastName%22%3A%22Weerasinghe%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jennifer%22%2C%22lastName%22%3A%22Teke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maines%22%2C%22lastName%22%3A%22Msiska%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Stergios%22%2C%22lastName%22%3A%22Boussios%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Eleni%22%2C%22lastName%22%3A%22Hatzidimitriadou%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20Artificial%20Intelligence%20%28AI%29%20is%20increasingly%20being%20integrated%20into%20healthcare%20to%20improve%20diagnostics%2C%20treatment%20planning%2C%20and%20operational%20efficiency.%20However%2C%20its%20adoption%20raises%20significant%20concerns%20related%20to%20data%20privacy%2C%20ethical%20integrity%2C%20and%20regulatory%20compliance.%20While%20much%20of%20the%20existing%20literature%20focuses%20on%20the%20clinical%20applications%20of%20AI%2C%20limited%20attention%20has%20been%20given%20to%20the%20perspectives%20of%20Information%20Governance%20%28IG%29%20professionals%2C%20who%20play%20a%20critical%20role%20in%20ensuring%20responsible%20and%20compliant%20AI%20implementation%20within%20healthcare%20systems.%5CnOBJECTIVE%3A%20This%20study%20aims%20to%20explore%20the%20perceptions%20of%20IG%20professionals%20in%20Kent%2C%20United%20Kingdom%2C%20on%20the%20use%20of%20AI%20in%20healthcare%20delivery%20and%20research%2C%20with%20a%20focus%20on%20data%20governance%2C%20ethical%20considerations%2C%20and%20regulatory%20implications.%5CnMETHODS%3A%20A%20qualitative%20exploratory%20design%20was%20employed.%20Six%20IG%20professionals%20from%20NHS%20trusts%20in%20Kent%20were%20purposively%20selected%20based%20on%20their%20roles%20in%20compliance%2C%20data%20governance%2C%20and%20policy%20enforcement.%20Semi-structured%20interviews%20were%20conducted%20and%20thematically%20analysed%20using%20NVivo%20software%2C%20guided%20by%20the%20Unified%20Theory%20of%20Acceptance%20and%20Use%20of%20Technology%20%28UTAUT%29.%5CnRESULTS%3A%20Thematic%20analysis%20revealed%20varying%20levels%20of%20AI%20knowledge%20among%20IG%20professionals.%20While%20participants%20acknowledged%20AI%26%23039%3Bs%20potential%20to%20improve%20efficiency%2C%20they%20raised%20concerns%20about%20data%20accuracy%2C%20algorithmic%20bias%2C%20cybersecurity%20risks%2C%20and%20unclear%20regulatory%20frameworks.%20Participants%20also%20highlighted%20the%20importance%20of%20ethical%20implementation%20and%20the%20need%20for%20national%20oversight.%5CnCONCLUSION%3A%20AI%20offers%20promising%20opportunities%20in%20healthcare%2C%20but%20its%20adoption%20must%20be%20underpinned%20by%20robust%20governance%20structures.%20Enhancing%20AI%20literacy%20among%20IG%20teams%20and%20establishing%20clearer%20regulatory%20frameworks%20will%20be%20key%20to%20safe%20and%20ethical%20implementation.%22%2C%22date%22%3A%222025-04-04%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1016%5C%2Fj.ijmedinf.2025.105909%22%2C%22ISSN%22%3A%221872-8243%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40198930%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T09%3A02%3A00Z%22%7D%7D%2C%7B%22key%22%3A%226J5B8FQD%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Santos%20and%20Nazar%5Cu00e9%22%2C%22parsedDate%22%3A%222025-04-03%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BSantos%2C%20Paulo%2C%20and%20Isabel%20Nazar%5Cu00e9.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40248038%5C%2F%26%23039%3B%26gt%3BThe%20doctor%20and%20patient%20of%20tomorrow%3A%20exploring%20the%20intersection%20of%20artificial%20intelligence%2C%20preventive%20medicine%2C%20and%20ethical%20challenges%20in%20future%20healthcare%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BFrontiers%20in%20Digital%20Health%26lt%3B%5C%2Fi%26gt%3B%207%20%28April%203%2C%202025%29%3A%201588479.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.3389%5C%2Ffdgth.2025.1588479.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22The%20doctor%20and%20patient%20of%20tomorrow%3A%20exploring%20the%20intersection%20of%20artificial%20intelligence%2C%20preventive%20medicine%2C%20and%20ethical%20challenges%20in%20future%20healthcare%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Paulo%22%2C%22lastName%22%3A%22Santos%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Isabel%22%2C%22lastName%22%3A%22Nazar%5Cu00e9%22%7D%5D%2C%22abstractNote%22%3A%22Artificial%20intelligence%20%28AI%29%20%26%23039%3Bs%20rapid%20integration%20into%20healthcare%20transforms%20medical%20decision-making%2C%20preventive%20strategies%2C%20and%20patient%20engagement.%20AI-driven%20technologies%2C%20including%20real-time%20health%20monitoring%20and%20predictive%20analytics%2C%20offer%20new%20personalized%20preventive%20care%20possibilities.%20However%2C%20concerns%20regarding%20ethical%20implications%2C%20data%20security%2C%20and%20equitable%20access%20remain%20unresolved.%20This%20paper%20addresses%20the%20critical%20gap%20in%20AI%20integration%20in%20preventive%20healthcare%2C%20highlighting%20statistical%20evidence%20of%20its%20impact.%20It%20also%20explores%20the%20intersection%20of%20AI%2C%20preventive%20medicine%2C%20and%20ethical%20challenges%20in%20future%20healthcare%2C%20envisioning%20the%20evolving%20roles%20of%20physicians%20and%20patients%20in%20an%20AI-integrated%20ecosystem.%20A%20fictional%20case%20study%20projected%20for%202040%2C%20illustrating%20an%20entirely%20digitized%2C%20AI-supported%20healthcare%20system%2C%20frames%20the%20discussion%20about%20digital%20health%20technologies%2C%20privacy%20regulations%2C%20and%20AI%26%23039%3Bs%20ethical%20implications%20in%20the%20future%20of%20preventive%20medicine.%20Digital%20health%20interventions%20powered%20by%20AI%20will%20facilitate%20real-time%20preventive%20strategies%2C%20strengthen%20patient%20autonomy%2C%20and%20enhance%20precision%20medicine.%20However%2C%20algorithmic%20bias%2C%20data%20privacy%2C%20and%20healthcare%20equity%20challenges%20must%20be%20addressed%20to%20ensure%20AI%20fosters%20inclusivity%20rather%20than%20exacerbating%20disparities.%20Regulatory%20frameworks%2C%20such%20as%20GDPR%2C%20provide%20foundational%20protections%2C%20but%20further%20adaptations%20are%20required%20to%20govern%20AI%26%23039%3Bs%20expanding%20role%20in%20medicine.%20This%20digital-assisted%20preventive%20medicine%20has%20the%20potential%20to%20redefine%20patient-provider%20interactions%2C%20enhance%20healthcare%20efficiency%2C%20and%20promote%20proactive%20health%20management.%20However%2C%20achieving%20this%20vision%20requires%20a%20multidisciplinary%20approach%20involving%20health%20professionals%2C%20policymakers%2C%20and%20technology%20developers.%20Future%20research%20should%20focus%20on%20regulatory%20strategies%2C%20digital%20literacy%2C%20and%20ethical%20AI%20implementation%20to%20balance%20innovation%20with%20equity%2C%20ensuring%20that%20digital%20healthcare%20remains%20patient-centered%20and%20inclusive.%22%2C%22date%22%3A%222025-04-03%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.3389%5C%2Ffdgth.2025.1588479%22%2C%22ISSN%22%3A%222673-253X%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40248038%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T08%3A51%3A06Z%22%7D%7D%2C%7B%22key%22%3A%225FNHE9IE%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Ellison%20et%20al.%22%2C%22parsedDate%22%3A%222025-04%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BEllison%2C%20India%20E.%2C%20Wendelyn%20M.%20Oslock%2C%20Abiha%20Abdullah%2C%20Lauren%20Wood%2C%20Mohanraj%20Thirumalai%2C%20Nathan%20English%2C%20Bayley%20A.%20Jones%2C%20Robert%20Hollis%2C%20Michael%20Rubyan%2C%20and%20Daniel%20I.%20Chu.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F39756334%5C%2F%26%23039%3B%26gt%3BDe%20novo%20generation%20of%20colorectal%20patient%20educational%20materials%20using%20large%20language%20models%3A%20Prompt%20engineering%20key%20to%20improved%20readability%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BSurgery%26lt%3B%5C%2Fi%26gt%3B%20180%20%28April%202025%29%3A%20109024.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.surg.2024.109024.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22De%20novo%20generation%20of%20colorectal%20patient%20educational%20materials%20using%20large%20language%20models%3A%20Prompt%20engineering%20key%20to%20improved%20readability%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22India%20E.%22%2C%22lastName%22%3A%22Ellison%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Wendelyn%20M.%22%2C%22lastName%22%3A%22Oslock%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Abiha%22%2C%22lastName%22%3A%22Abdullah%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lauren%22%2C%22lastName%22%3A%22Wood%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Mohanraj%22%2C%22lastName%22%3A%22Thirumalai%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nathan%22%2C%22lastName%22%3A%22English%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bayley%20A.%22%2C%22lastName%22%3A%22Jones%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Robert%22%2C%22lastName%22%3A%22Hollis%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%22%2C%22lastName%22%3A%22Rubyan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Daniel%20I.%22%2C%22lastName%22%3A%22Chu%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20Improving%20patient%20education%20has%20been%20shown%20to%20improve%20clinical%20outcomes%20and%20reduce%20disparities%2C%20though%20such%20efforts%20can%20be%20labor%20intensive.%20Large%20language%20models%20may%20serve%20as%20an%20accessible%20method%20to%20improve%20patient%20educational%20material.%20The%20aim%20of%20this%20study%20was%20to%20compare%20readability%20between%20existing%20educational%20materials%20and%20those%20generated%20by%20large%20language%20models.%5CnMETHODS%3A%20Baseline%20colorectal%20surgery%20educational%20materials%20were%20gathered%20from%20a%20large%20academic%20institution%20%28n%5Cu00a0%3D%2052%29.%20Three%20prompts%20were%20entered%20into%20Perplexity%20and%20ChatGPT%203.5%20for%20each%20topic%3A%20a%20Basic%20prompt%20that%20simply%20requested%20patient%20educational%20information%20the%20topic%2C%20an%20Iterative%20prompt%20that%20repeated%20instruction%20asking%20for%20the%20information%20to%20be%20more%20health%20literate%2C%20and%20a%20Metric-based%20prompt%20that%20requested%20a%20sixth-grade%20reading%20level%2C%20short%20sentences%2C%20and%20short%20words.%20Flesch-Kincaid%20Grade%20Level%20or%20Grade%20Level%2C%20Flesch-Kincaid%20Reading%20Ease%20or%20Ease%2C%20and%20Modified%20Grade%20Level%20scores%20were%20calculated%20for%20all%20materials%2C%20and%20unpaired%20t%20tests%20were%20used%20to%20compare%20mean%20scores%20between%20baseline%20and%20documents%20generated%20by%20artificial%20intelligence%20platforms.%5CnRESULTS%3A%20Overall%20existing%20materials%20were%20longer%20than%20materials%20generated%20by%20the%20large%20language%20models%20across%20categories%20and%20prompts%3A%20863-956%20words%20vs%20170-265%20%28ChatGPT%29%20and%20220-313%20%28Perplexity%29%2C%20all%20P%20%26lt%3B%20.01.%20Baseline%20materials%20did%20not%20meet%20sixth-grade%20readability%20guidelines%20based%20on%20grade%20level%20%28Grade%20Level%207.0-9.8%20and%20Modified%20Grade%20Level%209.6-11.5%29%20or%20ease%20of%20readability%20%28Ease%2053.1-65.0%29.%20Readability%20of%20materials%20generated%20by%20a%20large%20language%20model%20varied%20by%20prompt%20and%20platform.%20Overall%2C%20ChatGPT%20materials%20were%20more%20readable%20than%20baseline%20materials%20with%20the%20Metric-based%20prompt%3A%20Grade%20Level%205.2%20vs%208.1%2C%20Modified%20Grade%20Level%207.3%20vs%2010.3%2C%20and%20Ease%2070.5%20vs%2060.4%2C%20all%20P%20%26lt%3B%20.01.%20In%20contrast%2C%20Perplexity-generated%20materials%20were%20significantly%20less%20readable%20except%20for%20those%20generated%20with%20the%20Metric-based%20prompt%2C%20which%20did%20not%20statistically%20differ.%5CnCONCLUSION%3A%20Both%20existing%20materials%20and%20the%20majority%20of%20educational%20materials%20created%20by%20large%20language%20models%20did%20not%20meet%20readability%20recommendations.%20The%20exception%20to%20this%20was%20with%20ChatGPT%20materials%20generated%20with%20a%20Metric-based%20prompt%20that%20consistently%20improved%20readability%20scores%20from%20baseline%20and%20met%20recommendations%20in%20terms%20of%20the%20average%20Grade%20Level%20score.%20The%20variability%20in%20performance%20highlights%20the%20importance%20of%20the%20prompt%20used%20with%20large%20language%20models.%22%2C%22date%22%3A%222025-04%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1016%5C%2Fj.surg.2024.109024%22%2C%22ISSN%22%3A%221532-7361%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F39756334%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T09%3A56%3A37Z%22%7D%7D%2C%7B%22key%22%3A%22FQUJAU58%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Tuygunov%20et%20al.%22%2C%22parsedDate%22%3A%222025-04%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BTuygunov%2C%20Nozimjon%2C%20Lakshman%20Samaranayake%2C%20Zohaib%20Khurshid%2C%20Paak%20Rewthamrongsris%2C%20Falk%20Schwendicke%2C%20Thanaphum%20Osathanon%2C%20and%20Noor%20Azlin%20Yahya.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40011130%5C%2F%26%23039%3B%26gt%3BThe%20Transformative%20Role%20of%20Artificial%20Intelligence%20in%20Dentistry%3A%20A%20Comprehensive%20Overview%20Part%202%3A%20The%20Promise%20and%20Perils%2C%20and%20the%20International%20Dental%20Federation%20Communique%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BInternational%20Dental%20Journal%26lt%3B%5C%2Fi%26gt%3B%2075%2C%20no.%202%20%28April%202025%29%3A%20397%5Cu2013404.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.identj.2025.02.006.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22The%20Transformative%20Role%20of%20Artificial%20Intelligence%20in%20Dentistry%3A%20A%20Comprehensive%20Overview%20Part%202%3A%20The%20Promise%20and%20Perils%2C%20and%20the%20International%20Dental%20Federation%20Communique%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nozimjon%22%2C%22lastName%22%3A%22Tuygunov%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lakshman%22%2C%22lastName%22%3A%22Samaranayake%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Zohaib%22%2C%22lastName%22%3A%22Khurshid%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Paak%22%2C%22lastName%22%3A%22Rewthamrongsris%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Falk%22%2C%22lastName%22%3A%22Schwendicke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Thanaphum%22%2C%22lastName%22%3A%22Osathanon%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Noor%20Azlin%22%2C%22lastName%22%3A%22Yahya%22%7D%5D%2C%22abstractNote%22%3A%22In%20the%20final%20part%20of%20this%20two%20part%20article%20on%20artificial%20intelligence%20%28AI%29%20in%20dentistry%20we%20review%20its%20transformative%20role%2C%20focusing%20on%20AI%20in%20dental%20education%2C%20patient%20communications%2C%20challenges%20of%20integration%2C%20strategies%20to%20overcome%20barriers%2C%20ethical%20considerations%2C%20and%20finally%2C%20the%20recently%20released%20International%20Dental%20Federation%20%28FDI%29%20Communique%20%28white%20paper%29%20on%20AI%20in%20Dentistry.%20AI%20in%20dental%20education%20is%20highlighted%20for%20its%20potential%20in%20enhancing%20theoretical%20and%20practical%20dimensions%2C%20including%20patient%20telemonitoring%20and%20virtual%20training%20ecosystems.%20Challenges%20of%20AI%20integration%20in%20dentistry%20are%20outlined%2C%20such%20as%20data%20availability%2C%20bias%2C%20and%20human%20accountability.%20Strategies%20to%20overcome%20these%20challenges%20include%20promoting%20AI%20literacy%2C%20establishing%20regulations%2C%20and%20focusing%20on%20specific%20AI%20implementations.%20Ethical%20considerations%20in%20AI%20integration%20within%20dentistry%2C%20such%20as%20patient%20privacy%20and%20algorithm%20bias%2C%20are%20emphasized.%20The%20need%20for%20clear%20guidelines%20and%20ongoing%20evaluation%20of%20AI%20systems%20is%20crucial.%20The%20FDI%20White%20Paper%20on%20AI%20in%20Dentistry%20provides%20insights%20into%20the%20significance%20of%20AI%20in%20oral%20care%2C%20dental%20education%2C%20and%20research%2C%20along%20with%20standards%20for%20governance.%20It%20discusses%20AI%26%23039%3Bs%20impact%20on%20individual%20patients%2C%20community%20health%2C%20dental%20education%2C%20and%20research.%20The%20paper%20addresses%20biases%2C%20limited%20generalizability%2C%20accessibility%2C%20and%20regulatory%20requirements%20for%20AI%20in%20dental%20practice.%20In%20conclusion%2C%20AI%20plays%20a%20significant%20role%20in%20modern%20dental%20care%2C%20offering%20benefits%20in%20diagnosis%2C%20treatment%20planning%2C%20and%20decision-making.%20While%20facing%20challenges%2C%20strategic%20initiatives%20focusing%20on%20AI%20literacy%2C%20regulations%2C%20and%20targeted%20implementations%20can%20help%20overcome%20barriers%20and%20maximize%20the%20potential%20of%20AI%20in%20dentistry.%20Ethical%20considerations%20and%20ongoing%20evaluation%20are%20essential%20for%20ensuring%20responsible%2C%20effective%20and%20efficacious%20deployment%20of%20AI%20technologies%20in%20dental%20ecosystem.%22%2C%22date%22%3A%222025-04%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1016%5C%2Fj.identj.2025.02.006%22%2C%22ISSN%22%3A%221875-595X%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40011130%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%2C%22GUHR6SSX%22%5D%2C%22dateModified%22%3A%222025-05-21T09%3A21%3A35Z%22%7D%7D%2C%7B%22key%22%3A%22VZ6Y2WQ8%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Samaranayake%20et%20al.%22%2C%22parsedDate%22%3A%222025-04%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BSamaranayake%2C%20Lakshman%2C%20Nozimjon%20Tuygunov%2C%20Falk%20Schwendicke%2C%20Thanaphum%20Osathanon%2C%20Zohaib%20Khurshid%2C%20Shukhrat%20A.%20Boymuradov%2C%20and%20Arief%20Cahyanto.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40074616%5C%2F%26%23039%3B%26gt%3BThe%20Transformative%20Role%20of%20Artificial%20Intelligence%20in%20Dentistry%3A%20A%20Comprehensive%20Overview.%20Part%201%3A%20Fundamentals%20of%20AI%2C%20and%20its%20Contemporary%20Applications%20in%20Dentistry%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BInternational%20Dental%20Journal%26lt%3B%5C%2Fi%26gt%3B%2075%2C%20no.%202%20%28April%202025%29%3A%20383%5Cu201396.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.identj.2025.02.005.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22The%20Transformative%20Role%20of%20Artificial%20Intelligence%20in%20Dentistry%3A%20A%20Comprehensive%20Overview.%20Part%201%3A%20Fundamentals%20of%20AI%2C%20and%20its%20Contemporary%20Applications%20in%20Dentistry%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lakshman%22%2C%22lastName%22%3A%22Samaranayake%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nozimjon%22%2C%22lastName%22%3A%22Tuygunov%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Falk%22%2C%22lastName%22%3A%22Schwendicke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Thanaphum%22%2C%22lastName%22%3A%22Osathanon%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Zohaib%22%2C%22lastName%22%3A%22Khurshid%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shukhrat%20A.%22%2C%22lastName%22%3A%22Boymuradov%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Arief%22%2C%22lastName%22%3A%22Cahyanto%22%7D%5D%2C%22abstractNote%22%3A%22Artificial%20intelligence%20%28AI%29%20holds%20immense%20promise%20in%20revolutionising%20dentistry%2C%20spanning%2C%20diagnostics%2C%20treatment%20planning%20and%20educational%20realms.%20This%20narrative%20review%2C%20in%20two%20parts%2C%20explores%20the%20fundamentals%20and%20the%20multifaceted%20potential%20of%20AI%20in%20dentistry.%20The%20current%20article%20explores%20the%20profound%20impact%20of%20AI%20in%20dentistry%2C%20encompassing%20diagnostic%20tools%2C%20treatment%20planning%2C%20and%20patient%20care.%20The%20Part%202%20of%20the%20article%20delves%20into%20the%20potential%20of%20AI%20in%20patient%20education%2C%20ethics%20and%20the%20FDI%20communique%20on%20AI%20in%20dentistry.%20The%20review%20begins%20by%20elucidating%20the%20historical%20context%20of%20AI%2C%20outlining%20its%20recent%20widespread%20use%20in%20various%20sectors%2C%20including%20medicine%20and%20dentistry.%20The%20narrative%20delves%20into%20the%20fundamental%20concepts%20of%20AI%2C%20which%20entails%20developing%20machines%20capable%20of%20executing%20tasks%20that%20typically%20necessitate%20human%20intellect.%20In%20the%20biomedical%20realm%2C%20AI%20has%20evolved%20from%20exploring%20computational%20models%20to%20constructing%20systems%20for%20clinical%20data%20processing%20and%20interpretation%2C%20aiming%20to%20enhance%20medical%5C%2Fdental%20decision-making.%20The%20discussion%20delves%20into%20the%20pivotal%20role%20of%20AI%20models%20in%20dentistry%2C%20such%20as%20Large%20Language%20Models%20%28LLM%29%2C%20Large%20Vision%20Models%20%28LVM%29%2C%20and%20Multimodality%20Models%20%28MM%29%2C%20revolutionizing%20processes%20from%20clinical%20documentation%20to%20treatment%20planning.%20The%20narrative%20extends%20to%20the%20applications%20of%20AI%20in%20dental%20specialties%20such%20as%20periodontics%2C%20endodontics%2C%20oral%20medicine%20and%20pathology%2C%20restorative%20dentistry%2C%20prosthodontics%2C%20paediatric%20dentistry%2C%20forensic%20odontology%2C%20oral%20and%20maxillofacial%20surgery%2C%20orthodontics%2C%20and%20orofacial%20pain%20management.%20AI%26%23039%3Bs%20role%20in%20improving%20treatment%20outcomes%2C%20diagnostic%20accuracy%2C%20and%20decision-making%20processes%20is%20evident%20across%20these%20specialties%2C%20showcasing%20its%20potential%20in%20transforming%20dental%20care.%20The%20review%20concludes%20by%20highlighting%20the%20need%20for%20continued%20validation%2C%20interdisciplinary%20collaboration%2C%20and%20regulatory%20frameworks%20to%20ensure%20the%20seamless%20integration%20of%20AI%20into%20dentistry%2C%20paving%20the%20way%20for%20enhanced%20patient%20outcomes%20and%20evidence-based%20practice%20in%20the%20field.%22%2C%22date%22%3A%222025-04%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1016%5C%2Fj.identj.2025.02.005%22%2C%22ISSN%22%3A%221875-595X%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40074616%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%2C%22GUHR6SSX%22%5D%2C%22dateModified%22%3A%222025-05-21T09%3A18%3A09Z%22%7D%7D%2C%7B%22key%22%3A%22IE8W3UWB%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Biesheuvel%20et%20al.%22%2C%22parsedDate%22%3A%222025-04%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BBiesheuvel%2C%20Laurens%20A.%2C%20Jessica%20D.%20Workum%2C%20Merijn%20Reuland%2C%20Michel%20E.%20van%20Genderen%2C%20Patrick%20Thoral%2C%20Dave%20Dongelmans%2C%20and%20Paul%20Elbers.%20%26%23x201C%3BLarge%20Language%20Models%20in%20Critical%20Care.%26%23x201D%3B%20%26lt%3Bi%26gt%3BJournal%20of%20Intensive%20Medicine%26lt%3B%5C%2Fi%26gt%3B%205%2C%20no.%202%20%28April%202025%29%3A%20113%26%23x2013%3B18.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.jointm.2024.12.001%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.jointm.2024.12.001%26lt%3B%5C%2Fa%26gt%3B.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Large%20language%20models%20in%20critical%20care%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Laurens%20A.%22%2C%22lastName%22%3A%22Biesheuvel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jessica%20D.%22%2C%22lastName%22%3A%22Workum%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Merijn%22%2C%22lastName%22%3A%22Reuland%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michel%20E.%22%2C%22lastName%22%3A%22van%20Genderen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Patrick%22%2C%22lastName%22%3A%22Thoral%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dave%22%2C%22lastName%22%3A%22Dongelmans%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Paul%22%2C%22lastName%22%3A%22Elbers%22%7D%5D%2C%22abstractNote%22%3A%22The%20advent%20of%20chat%20generative%20pre-trained%20transformer%20%28ChatGPT%29%20and%20large%20language%20models%20%28LLMs%29%20has%20revolutionized%20natural%20language%20processing%20%28NLP%29.%20These%20models%20possess%20unprecedented%20capabilities%20in%20understanding%20and%20generating%20human-like%20language.%20This%20breakthrough%20holds%20significant%20promise%20for%20critical%20care%20medicine%2C%20where%20unstructured%20data%20and%20complex%20clinical%20information%20are%20abundant.%20Key%20applications%20of%20LLMs%20in%20this%20field%20include%20administrative%20support%20through%20automated%20documentation%20and%20patient%20chart%20summarization%3B%20clinical%20decision%20support%20by%20assisting%20in%20diagnostics%20and%20treatment%20planning%3B%20personalized%20communication%20to%20enhance%20patient%20and%20family%20understanding%3B%20and%20improving%20data%20quality%20by%20extracting%20insights%20from%20unstructured%20clinical%20notes.%20Despite%20these%20opportunities%2C%20challenges%20such%20as%20the%20risk%20of%20generating%20inaccurate%20or%20biased%20information%20%26quot%3Bhallucinations%26quot%3B%2C%20ethical%20considerations%2C%20and%20the%20need%20for%20clinician%20artificial%20intelligence%20%28AI%29%20literacy%20must%20be%20addressed.%20Integrating%20LLMs%20with%20traditional%20machine%20learning%20models%20-%20an%20approach%20known%20as%20Hybrid%20AI%20-%20combines%20the%20strengths%20of%20both%20technologies%20while%20mitigating%20their%20limitations.%20Careful%20implementation%2C%20regulatory%20compliance%2C%20and%20ongoing%20validation%20are%20essential%20to%20ensure%20that%20LLMs%20enhance%20patient%20care%20rather%20than%20hinder%20it.%20LLMs%20have%20the%20potential%20to%20transform%20critical%20care%20practices%2C%20but%20integrating%20them%20requires%20caution.%20Responsible%20use%20and%20thorough%20clinician%20training%20are%20crucial%20to%20fully%20realize%20their%20benefits.%22%2C%22date%22%3A%222025-04%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1016%5C%2Fj.jointm.2024.12.001%22%2C%22ISSN%22%3A%222667-100X%22%2C%22url%22%3A%22%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T08%3A52%3A45Z%22%7D%7D%2C%7B%22key%22%3A%22AJEFBAYU%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Yun%20and%20Bickmore%22%2C%22parsedDate%22%3A%222025-03-31%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BYun%2C%20Hye%20Sun%2C%20and%20Timothy%20Bickmore.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40163112%5C%2F%26%23039%3B%26gt%3BOnline%20Health%20Information-Seeking%20in%20the%20Era%20of%20Large%20Language%20Models%3A%20Cross-Sectional%20Web-Based%20Survey%20Study%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BJournal%20of%20Medical%20Internet%20Research%26lt%3B%5C%2Fi%26gt%3B%2027%20%28March%2031%2C%202025%29%3A%20e68560.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.2196%5C%2F68560.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Online%20Health%20Information-Seeking%20in%20the%20Era%20of%20Large%20Language%20Models%3A%20Cross-Sectional%20Web-Based%20Survey%20Study%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hye%20Sun%22%2C%22lastName%22%3A%22Yun%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Timothy%22%2C%22lastName%22%3A%22Bickmore%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20As%20large%20language%20model%20%28LLM%29-based%20chatbots%20such%20as%20ChatGPT%20%28OpenAI%29%20grow%20in%20popularity%2C%20it%20is%20essential%20to%20understand%20their%20role%20in%20delivering%20online%20health%20information%20compared%20to%20other%20resources.%20These%20chatbots%20often%20generate%20inaccurate%20content%2C%20posing%20potential%20safety%20risks.%20This%20motivates%20the%20need%20to%20examine%20how%20users%20perceive%20and%20act%20on%20health%20information%20provided%20by%20LLM-based%20chatbots.%5CnOBJECTIVE%3A%20This%20study%20investigates%20the%20patterns%2C%20perceptions%2C%20and%20actions%20of%20users%20seeking%20health%20information%20online%2C%20including%20LLM-based%20chatbots.%20The%20relationships%20between%20online%20health%20information-seeking%20behaviors%20and%20important%20sociodemographic%20characteristics%20are%20examined%20as%20well.%5CnMETHODS%3A%20A%20web-based%20survey%20of%20crowd%20workers%20was%20conducted%20via%20Prolific.%20The%20questionnaire%20covered%20sociodemographic%20information%2C%20trust%20in%20health%20care%20providers%2C%20eHealth%20literacy%2C%20artificial%20intelligence%20%28AI%29%20attitudes%2C%20chronic%20health%20condition%20status%2C%20online%20health%20information%20source%20types%2C%20perceptions%2C%20and%20actions%2C%20such%20as%20cross-checking%20or%20adherence.%20Quantitative%20and%20qualitative%20analyses%20were%20applied.%5CnRESULTS%3A%20Most%20participants%20consulted%20search%20engines%20%28291%5C%2F297%2C%2098%25%29%20and%20health-related%20websites%20%28203%5C%2F297%2C%2068.4%25%29%20for%20their%20health%20information%2C%20while%2021.2%25%20%2863%5C%2F297%29%20used%20LLM-based%20chatbots%2C%20with%20ChatGPT%20and%20Microsoft%20Copilot%20being%20the%20most%20popular.%20Most%20participants%20%28268%5C%2F297%2C%2090.2%25%29%20sought%20information%20on%20health%20conditions%2C%20with%20fewer%20seeking%20advice%20on%20medication%20%28179%5C%2F297%2C%2060.3%25%29%2C%20treatments%20%28137%5C%2F297%2C%2046.1%25%29%2C%20and%20self-diagnosis%20%2862%5C%2F297%2C%2023.2%25%29.%20Perceived%20information%20quality%20and%20trust%20varied%20little%20across%20source%20types.%20The%20preferred%20source%20for%20validating%20information%20from%20the%20internet%20was%20consulting%20health%20care%20professionals%20%2840%5C%2F132%2C%2030.3%25%29%2C%20while%20only%20a%20very%20small%20percentage%20of%20participants%20%285%5C%2F214%2C%202.3%25%29%20consulted%20AI%20tools%20to%20cross-check%20information%20from%20search%20engines%20and%20health-related%20websites.%20For%20information%20obtained%20from%20LLM-based%20chatbots%2C%2019.4%25%20%2812%5C%2F63%29%20of%20participants%20cross-checked%20the%20information%2C%20while%2048.4%25%20%2830%5C%2F63%29%20of%20participants%20followed%20the%20advice.%20Both%20of%20these%20rates%20were%20lower%20than%20information%20from%20search%20engines%2C%20health-related%20websites%2C%20forums%2C%20or%20social%20media.%20Furthermore%2C%20use%20of%20LLM-based%20chatbots%20for%20health%20information%20was%20negatively%20correlated%20with%20age%20%28%5Cu03c1%3D-0.16%2C%20P%3D.006%29.%20In%20contrast%2C%20attitudes%20surrounding%20AI%20for%20medicine%20had%20significant%20positive%20correlations%20with%20the%20number%20of%20source%20types%20consulted%20for%20health%20advice%20%28%5Cu03c1%3D0.14%2C%20P%3D.01%29%2C%20use%20of%20LLM-based%20chatbots%20for%20health%20information%20%28%5Cu03c1%3D0.31%2C%20P%26lt%3B.001%29%2C%20and%20number%20of%20health%20topics%20searched%20%28%5Cu03c1%3D0.19%2C%20P%26lt%3B.001%29.%5CnCONCLUSIONS%3A%20Although%20traditional%20online%20sources%20remain%20dominant%2C%20LLM-based%20chatbots%20are%20emerging%20as%20a%20resource%20for%20health%20information%20for%20some%20users%2C%20specifically%20those%20who%20are%20younger%20and%20have%20a%20higher%20trust%20in%20AI.%20The%20perceived%20quality%20and%20trustworthiness%20of%20health%20information%20varied%20little%20across%20source%20types.%20However%2C%20the%20adherence%20to%20health%20information%20from%20LLM-based%20chatbots%20seemed%20more%20cautious%20compared%20to%20search%20engines%20or%20health-related%20websites.%20As%20LLMs%20continue%20to%20evolve%2C%20enhancing%20their%20accuracy%20and%20transparency%20will%20be%20essential%20in%20mitigating%20any%20potential%20risks%20by%20supporting%20responsible%20information-seeking%20while%20maximizing%20the%20potential%20of%20AI%20in%20health%20contexts.%22%2C%22date%22%3A%222025-03-31%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.2196%5C%2F68560%22%2C%22ISSN%22%3A%221438-8871%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40163112%5C%2F%22%2C%22collections%22%3A%5B%227NLACL24%22%2C%2246NNKHWR%22%2C%22MDZ69LY7%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T09%3A09%3A10Z%22%7D%7D%2C%7B%22key%22%3A%22VJ8BI43U%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Abbas%20et%20al.%22%2C%22parsedDate%22%3A%222025-03-21%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BAbbas%2C%20Syed%20A.%2C%20Izmir%20Yusifzada%2C%20and%20Sufia%20Athar.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40255778%5C%2F%26%23039%3B%26gt%3BRevolutionizing%20Medicine%3A%20Chatbots%20as%20Catalysts%20for%20Improved%20Diagnosis%2C%20Treatment%2C%20and%20Patient%20Support%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BCureus%26lt%3B%5C%2Fi%26gt%3B%2017%2C%20no.%203%20%28March%2021%2C%202025%29%3A%20e80935.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.7759%5C%2Fcureus.80935.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Revolutionizing%20Medicine%3A%20Chatbots%20as%20Catalysts%20for%20Improved%20Diagnosis%2C%20Treatment%2C%20and%20Patient%20Support%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Syed%20A.%22%2C%22lastName%22%3A%22Abbas%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Izmir%22%2C%22lastName%22%3A%22Yusifzada%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sufia%22%2C%22lastName%22%3A%22Athar%22%7D%5D%2C%22abstractNote%22%3A%22Chatbots%20have%20emerged%20as%20one%20of%20the%20revolutionary%20tools%20in%20healthcare%20that%20combine%20artificial%20intelligence%20to%20improve%20patient%20engagement%20in%20diagnosis%2C%20treatment%2C%20monitoring%2C%20and%20support.%20In%20this%20review%2C%20the%20application%20of%20chatbots%20in%20medicine%20over%20the%20past%20two%20decades%20is%20discussed%2C%20focusing%20on%20their%20application%20in%20several%20aspects%20of%20medicine%2C%20including%20oncology%2C%20psychiatry%2C%20and%20chronic%20disease%20management.%20A%20total%20of%2038%20clinically%20relevant%20studies%20were%20identified%20from%20a%20comprehensive%20literature%20search.%20These%20studies%20demonstrate%20that%20the%20efficacy%20of%20chatbots%20in%20early%20symptom%20detection%2C%20personalized%20treatment%20planning%2C%20and%20emotional%20support%20has%20a%20particular%20emphasis%20on%20addressing%20mental%20health%20needs.%20The%20review%20focuses%20on%20the%20role%20of%20chatbots%20in%20improving%20the%20communication%20gap%20between%20patients%20and%20health%20providers%20to%20achieve%20improved%20access%20to%20medical%20information%20and%20treatment%20adherence.%20The%20findings%20underscore%20the%20substantial%20promise%20of%20chatbots%20in%20enhancing%20healthcare%20delivery%20and%20reveal%20areas%20that%20need%20further%20exploration%2C%20particularly%20in%20radiology%20and%20advanced%20diagnostics.%20With%20the%20continuous%20rise%20in%20technological%20development%2C%20the%20use%20of%20chatbots%20is%20expected%20to%20become%20more%20central%20in%20streamlining%20health%20processes%20toward%20better%20patient%20outcomes%20and%20enhanced%20health%20literacy.%20This%20review%2C%20therefore%2C%20calls%20for%20continued%20investment%20in%20the%20incorporation%20of%20these%20chatbot%20innovations%20in%20healthcare%20systems%20for%20their%20full%20potential%20to%20be%20realized%20in%20patient%20care.%22%2C%22date%22%3A%222025-03-21%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.7759%5C%2Fcureus.80935%22%2C%22ISSN%22%3A%222168-8184%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40255778%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T08%3A48%3A35Z%22%7D%7D%2C%7B%22key%22%3A%22AH657GHR%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Koch%20et%20al.%22%2C%22parsedDate%22%3A%222025-03-21%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BKoch%2C%20Roland%2C%20Marie-Theres%20Steffen%2C%20Anna-Jasmin%20Wetzel%2C%20Christine%20Preiser%2C%20Malte%20Klemmt%2C%20Hans-J%5Cu00f6rg%20Ehni%2C%20Regina%20Mueller%2C%20and%20Stefanie%20Joos.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40117573%5C%2F%26%23039%3B%26gt%3BExploring%20Laypersons%26%23039%3B%20Experiences%20With%20a%20Mobile%20Symptom%20Checker%20App%20as%20an%20Interface%20Between%20eHealth%20Literacy%2C%20Health%20Literacy%2C%20and%20Health-Related%20Behavior%3A%20Qualitative%20Interview%20Study%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BJMIR%20Formative%20Research%26lt%3B%5C%2Fi%26gt%3B%209%20%28March%2021%2C%202025%29%3A%20e60647.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.2196%5C%2F60647.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Exploring%20Laypersons%27%20Experiences%20With%20a%20Mobile%20Symptom%20Checker%20App%20as%20an%20Interface%20Between%20eHealth%20Literacy%2C%20Health%20Literacy%2C%20and%20Health-Related%20Behavior%3A%20Qualitative%20Interview%20Study%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Roland%22%2C%22lastName%22%3A%22Koch%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marie-Theres%22%2C%22lastName%22%3A%22Steffen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Anna-Jasmin%22%2C%22lastName%22%3A%22Wetzel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Christine%22%2C%22lastName%22%3A%22Preiser%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Malte%22%2C%22lastName%22%3A%22Klemmt%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hans-J%5Cu00f6rg%22%2C%22lastName%22%3A%22Ehni%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Regina%22%2C%22lastName%22%3A%22Mueller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Stefanie%22%2C%22lastName%22%3A%22Joos%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20Symptom%20checkers%20aim%20to%20help%20users%20recognize%20medical%20symptoms%20and%20recommend%20actions.%20However%2C%20they%20are%20not%20yet%20reliable%20for%20self-triage%20or%20diagnostics.%20Health%20literacy%20plays%20a%20role%20in%20their%20use%2C%20but%20the%20process%20from%20symptom%20recognition%20to%20health%20care%20consultation%20remains%20unclear.%5CnOBJECTIVE%3A%20This%20qualitative%20observatory%20study%20explored%20how%20laypersons%20use%20symptom%20checkers%2C%20focusing%20on%20the%20process%20of%20use%2C%20entry%20points%20and%20outcomes%2C%20and%20the%20role%20of%20health%20literacy.%20Laypersons%20are%20defined%20as%20individuals%20who%20are%20neither%20medical%20professionals%20nor%20developers%20of%20such%20apps.%20Three%20research%20questions%20were%20addressed%3A%20%281%29%20How%20do%20such%20users%20describe%20the%20process%20of%20using%20symptom%20checkers%3F%20%282%29%20What%20are%20entry%20points%20and%20possible%20outcomes%20of%20symptom%20checker%20app%20use%3F%20%283%29%20How%20are%20health%20literacy%20and%20eHealth%20literacy%20expressed%20during%20the%20use%20of%20symptom%20checker%20apps%3F%5CnMETHODS%3A%20As%20part%20of%20the%20Ethical%2C%20Legal%2C%20and%20Social%20Implications%20of%20Symptom%20Checker%20Apps%20in%20Primary%20Health%20Care%20project%2C%2015%20laypersons%20%28n%3D9%2C%2060%25%20female%20and%20n%3D6%2C%2040%25%20male%3B%20mean%20age%2030.7%2C%20SD%2013.6%20years%29%20were%20interviewed%20about%20their%20experiences%20with%20the%20symptom%20checker%20Ada.%20The%20interviews%20were%20analyzed%20using%20an%20integrative%20approach%20combining%20social%20positioning%2C%20agency%2C%20and%20the%20Rubicon%20model%20as%20a%20heuristic%20framework.%5CnRESULTS%3A%20App%20use%20follows%20a%20cyclic%20process%20comprising%204%20steps%3A%20motivation%20%28influenced%20by%20biography%20and%20context%29%2C%20intention%20formation%20%28assigning%20a%20purpose%29%2C%20intention%20implementation%20%28recruiting%20resources%29%2C%20and%20evaluation%20%28transforming%20interactions%20into%20health-related%20insights%29.%20Biographical%2C%20social%2C%20and%20contextual%20factors%20shape%20process%20initiation.%20Users%20use%20symptom%20checkers%20for%203%20main%20purposes%3A%20understanding%20their%20condition%2C%20receiving%20recommendations%20for%20action%2C%20and%20documenting%20or%20communicating%20health-related%20information.%20Each%20purpose%20requires%20specific%20planning%20and%20integration%20into%20health-related%20behaviors%20drawing%20on%20personal%2C%20social%2C%20and%20technological%20resources.%20Evaluation%20depends%20on%20contextual%20factors%2C%20app%20outputs%2C%20and%20the%20outcomes%20of%20users%26%23039%3B%20health-related%20actions.%20Users%20assess%20whether%20the%20app%20aligns%20with%20their%20expectations%2C%20condition%20severity%2C%20and%20previous%20experiences%2C%20with%20health%20literacy%20playing%20a%20critical%20role%20in%20validation%20processes.%5CnCONCLUSIONS%3A%20Symptom%20checker%20use%20is%20a%20complex%2C%20cyclic%20process%20shaped%20by%20context%2C%20biography%2C%20and%20health%20literacy.%20Users%20are%20motivated%20by%20health%20concerns%20influenced%20by%20personal%2C%20social%2C%20and%20contextual%20factors%2C%20with%20trust%20and%20attitudes%20impacting%20initial%20engagement.%20Intention%20formation%20reflects%20a%20balance%20between%20user%20skills%20and%20context%2C%20where%20app%20outputs%20inform%20decisions%20but%20may%20not%20always%20lead%20to%20action%2C%20especially%20in%20ambiguous%20situations.%20Users%20rely%20on%20personal%20resources%20and%20social%20networks%20to%20integrate%20app%20use%20into%20health-related%20behaviors%2C%20highlighting%20the%20limitations%20of%20symptom%20checkers%20in%20providing%20social%20or%20empathetic%20support.%20Symptom%20checkers%20have%20the%20potential%20to%20serve%20as%20an%20interface%20between%20users%20and%20health%20care%2C%20but%20future%20development%20must%20address%20the%20complexity%20of%20their%20use%20to%20unlock%20this%20potential.%5CnINTERNATIONAL%20REGISTERED%20REPORT%20IDENTIFIER%20%28IRRID%29%3A%20RR2-10.2196%5C%2F34026.%22%2C%22date%22%3A%222025-03-21%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.2196%5C%2F60647%22%2C%22ISSN%22%3A%222561-326X%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40117573%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%227FBAMELL%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T09%3A13%3A29Z%22%7D%7D%2C%7B%22key%22%3A%22VZJVL4AT%22%2C%22library%22%3A%7B%22id%22%3A6298796%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22%5Cu0160uto%20Pavi%5Cu010di%5Cu0107%20et%20al.%22%2C%22parsedDate%22%3A%222025-03-19%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3B%5Cu0160uto%20Pavi%5Cu010di%5Cu0107%2C%20Jelena%2C%20Ana%20Maru%5Cu0161i%5Cu0107%2C%20and%20Ivan%20Buljan.%20%26quot%3B%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40106236%5C%2F%26%23039%3B%26gt%3BUsing%20ChatGPT%20to%20Improve%20the%20Presentation%20of%20Plain%20Language%20Summaries%20of%20Cochrane%20Systematic%20Reviews%20About%20Oncology%20Interventions%3A%20Cross-Sectional%20Study%26lt%3B%5C%2Fa%26gt%3B.%26quot%3B%20%26lt%3Bi%26gt%3BJMIR%20Cancer%26lt%3B%5C%2Fi%26gt%3B%2011%20%28March%2019%2C%202025%29%3A%20e63347.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.2196%5C%2F63347.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Using%20ChatGPT%20to%20Improve%20the%20Presentation%20of%20Plain%20Language%20Summaries%20of%20Cochrane%20Systematic%20Reviews%20About%20Oncology%20Interventions%3A%20Cross-Sectional%20Study%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jelena%22%2C%22lastName%22%3A%22%5Cu0160uto%20Pavi%5Cu010di%5Cu0107%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ana%22%2C%22lastName%22%3A%22Maru%5Cu0161i%5Cu0107%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ivan%22%2C%22lastName%22%3A%22Buljan%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20Plain%20language%20summaries%20%28PLSs%29%20of%20Cochrane%20systematic%20reviews%20are%20a%20simple%20format%20for%20presenting%20medical%20information%20to%20the%20lay%20public.%20This%20is%20particularly%20important%20in%20oncology%2C%20where%20patients%20have%20a%20more%20active%20role%20in%20decision-making.%20However%2C%20current%20PLS%20formats%20often%20exceed%20the%20readability%20requirements%20for%20the%20general%20population.%20There%20is%20still%20a%20lack%20of%20cost-effective%20and%20more%20automated%20solutions%20to%20this%20problem.%5CnOBJECTIVE%3A%20This%20study%20assessed%20whether%20a%20large%20language%20model%20%28eg%2C%20ChatGPT%29%20can%20improve%20the%20readability%20and%20linguistic%20characteristics%20of%20Cochrane%20PLSs%20about%20oncology%20interventions%2C%20without%20changing%20evidence%20synthesis%20conclusions.%5CnMETHODS%3A%20The%20dataset%20included%20275%20scientific%20abstracts%20and%20corresponding%20PLSs%20of%20Cochrane%20systematic%20reviews%20about%20oncology%20interventions.%20ChatGPT-4%20was%20tasked%20to%20make%20each%20scientific%20abstract%20into%20a%20PLS%20using%203%20prompts%20as%20follows%3A%20%281%29%20rewrite%20this%20scientific%20abstract%20into%20a%20PLS%20to%20achieve%20a%20Simple%20Measure%20of%20Gobbledygook%20%28SMOG%29%20index%20of%206%2C%20%282%29%20rewrite%20the%20PLS%20from%20prompt%201%20so%20it%20is%20more%20emotional%2C%20and%20%283%29%20rewrite%20this%20scientific%20abstract%20so%20it%20is%20easier%20to%20read%20and%20more%20appropriate%20for%20the%20lay%20audience.%20ChatGPT-generated%20PLSs%20were%20analyzed%20for%20word%20count%2C%20level%20of%20readability%20%28SMOG%20index%29%2C%20and%20linguistic%20characteristics%20using%20Linguistic%20Inquiry%20and%20Word%20Count%20%28LIWC%29%20software%20and%20compared%20with%20the%20original%20PLSs.%20Two%20independent%20assessors%20reviewed%20the%20conclusiveness%20categories%20of%20ChatGPT-generated%20PLSs%20and%20compared%20them%20with%20original%20abstracts%20to%20evaluate%20consistency.%20The%20conclusion%20of%20each%20abstract%20about%20the%20efficacy%20and%20safety%20of%20the%20intervention%20was%20categorized%20as%20conclusive%20%28positive%5C%2Fnegative%5C%2Fequal%29%2C%20inconclusive%2C%20or%20unclear.%20Group%20comparisons%20were%20conducted%20using%20the%20Friedman%20nonparametric%20test.%5CnRESULTS%3A%20ChatGPT-generated%20PLSs%20using%20the%20first%20prompt%20%28SMOG%20index%206%29%20were%20the%20shortest%20and%20easiest%20to%20read%2C%20with%20a%20median%20SMOG%20score%20of%208.2%20%2895%25%20CI%208-8.4%29%2C%20compared%20with%20the%20original%20PLSs%20%28median%20SMOG%20score%2013.1%2C%2095%25%20CI%2012.9-13.4%29.%20These%20PLSs%20had%20a%20median%20word%20count%20of%20240%20%2895%25%20CI%20232-248%29%20compared%20with%20the%20original%20PLSs%26%23039%3B%20median%20word%20count%20of%20364%20%2895%25%20CI%20339-388%29.%20The%20second%20prompt%20%28emotional%20tone%29%20generated%20PLSs%20with%20a%20median%20SMOG%20score%20of%2011.4%20%2895%25%20CI%2011.1-12%29%2C%20again%20lower%20than%20the%20original%20PLSs.%20PLSs%20produced%20with%20the%20third%20prompt%20%28write%20simpler%20and%20easier%29%20had%20a%20median%20SMOG%20score%20of%208.7%20%2895%25%20CI%208.4-8.8%29.%20ChatGPT-generated%20PLSs%20across%20all%20prompts%20demonstrated%20reduced%20analytical%20tone%20and%20increased%20authenticity%2C%20clout%2C%20and%20emotional%20tone%20compared%20with%20the%20original%20PLSs.%20Importantly%2C%20the%20conclusiveness%20categorization%20of%20the%20original%20abstracts%20was%20unchanged%20in%20the%20ChatGPT-generated%20PLSs.%5CnCONCLUSIONS%3A%20ChatGPT%20can%20be%20a%20valuable%20tool%20in%20simplifying%20PLSs%20as%20medically%20related%20formats%20for%20lay%20audiences.%20More%20research%20is%20needed%2C%20including%20oversight%20mechanisms%20to%20ensure%20that%20the%20information%20is%20accurate%2C%20reliable%2C%20and%20culturally%20relevant%20for%20different%20audiences.%22%2C%22date%22%3A%222025-03-19%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.2196%5C%2F63347%22%2C%22ISSN%22%3A%222369-1999%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpubmed.ncbi.nlm.nih.gov%5C%2F40106236%5C%2F%22%2C%22collections%22%3A%5B%2246NNKHWR%22%2C%224UVUVQXJ%22%5D%2C%22dateModified%22%3A%222025-05-21T09%3A15%3A58Z%22%7D%7D%5D%7D
Zhou, Mi, Yun Pan, Yuye Zhang, Xiaomei Song, and Youbin Zhou. "Evaluating AI-generated patient education materials for spinal surgeries: Comparative analysis of readability and DISCERN quality across ChatGPT and deepseek models." International Journal of Medical Informatics 198 (June 2025): 105871. https://doi.org/10.1016/j.ijmedinf.2025.105871.
Bracey, Solomon, Nasif Bhuiyan, Amelia Pietropaolo, and Bhaskar Somani. "Exploring the impact of artificial intelligence-enabled decision aids in improving patient inclusivity, empowerment, and education in urology: a systematic review by EAU endourology." Current Opinion in Urology, May 15, 2025. https://doi.org/10.1097/MOU.0000000000001301.
Frey, Nicolas, Louis Agha-Mir-Salim, Elena Hinz, Akira-Sebastian Poncette, and Felix Balzer. "Assessing Healthcare Stakeholder Understanding of Machine Learning Documentation." Studies in Health Technology and Informatics 327 (May 15, 2025): 318–22. https://doi.org/10.3233/SHTI250336.
Heizmann, Carolin, Patricia Gleim, and Philipp Kellmeyer. "Participatory Co-Creation of an AI-Supported Patient Information System: A Multi-Method Qualitative Study." Studies in Health Technology and Informatics 327 (May 15, 2025): 338–42. https://doi.org/10.3233/SHTI250340.
Turner, Jonathan, Damon Berry, Julie Doyle, Harish Kambampati, Orla Moran, Suzanne Smith, Michael Wilson, and Dympna O'Sullivan. "Improving the Readability of Dementia Information Documents Using ChatGPT." Studies in Health Technology and Informatics 327 (May 15, 2025): 880–81. https://doi.org/10.3233/SHTI250489.
Schmiedmayer, Paul, Adrit Rao, Philipp Zagar, Lauren Aalami, Vishnu Ravi, Aydin Zahedivash, Dong-Han Yao, Arash Fereydooni, and Oliver Aalami. "LLMonFHIR: A Physician-Validated, Large Language Model-Based Mobile Application for Querying Patient Electronic Health Data." JACC. Advances 4, no. 6 Pt 1 (May 14, 2025): 101780. https://doi.org/10.1016/j.jacadv.2025.101780.
Wieben, Ann, Linsey Steege, Roger Brown, and Andrea Gilmore-Bykovskyi. "Examining the Impact of Interface Design and Nurse Characteristics on Satisfaction With Machine Learning Decision Support Explanations." Computers, Informatics, Nursing: CIN, May 8, 2025. https://doi.org/10.1097/CIN.0000000000001323.
Gavai, Anand K., and Jos van Hillegersberg. "AI-driven personalized nutrition: RAG-based digital health solution for obesity and type 2 diabetes." PLOS Digital Health 4, no. 5 (May 6, 2025): e0000758. https://doi.org/10.1371/journal.pdig.0000758.
Dontchos, Brian N., Katerina Dodelzon, Sonya Bhole, Christine E. Edmonds, Lisa A. Mullen, Jay R. Parikh, Carolyn P. Daly, James A. Epling, Soren Christensen, and Lars J. Grimm. "Opinions and preferences regarding artificial intelligence use in healthcare delivery: results from a national multi-site survey of breast imaging patients." Journal of the American College of Radiology: JACR, May 6, 2025, S1546-1440(25)00268-6. https://doi.org/10.1016/j.jacr.2025.05.001.
Liu, Sizuo, Yufen Lin, Runze Yan, Zhiyuan Wang, Delgersuren Bold, and Xiao Hu. "Leveraging Artificial Intelligence for Digital Symptom Management in Oncology: The Development of CRCWeb." JMIR Cancer, May 5, 2025. https://doi.org/10.2196/68516.
Zeiler, Michael, Sandra Vögl, Ursula Prinz, Nino Werner, Gudrun Wagner, Andreas Karwautz, Natalie Zeller, Lorenz Ackermann, and Karin Waldherr. “Game Design, Effectiveness, and Implementation of Serious Games Promoting Aspects of Mental Health Literacy Among Children and Adolescents: Systematic Review.” JMIR Mental Health 12 (May 5, 2025): e67418. https://doi.org/10.2196/67418.
Kelly, Anthony, Eoin Noctor, Laura Ryan, and Pepijn van de Ven. "The Effectiveness of a Custom AI Chatbot for Type 2 Diabetes Mellitus Health Literacy: Development and Evaluation Study." Journal of Medical Internet Research 27 (May 5, 2025): e70131. https://doi.org/10.2196/70131.
Berger-Estilita, Joana, Mia Gisselbaek, Arnout Devos, Albert Chan, Pier Luigi Ingrassia, Basak Ceyda Meco, Odmara L. Barreto Chang, et al. "AI and inclusion in simulation education and leadership: a global cross-sectional evaluation of diversity." Advances in Simulation (London, England) 10, no. 1 (May 4, 2025): 26. https://doi.org/10.1186/s41077-025-00355-1.
Agaoglu, Ferhat Onur, Murat Bas, Sinan Tarsuslu, Lokman Onur Ekinci, and Nihat Bugra Agaoglu. "The mediating digital literacy and the moderating role of academic support in the relationship between artificial intelligence usage and creative thinking in nursing students." BMC Nursing 24, no. 1 (May 2, 2025): 484. https://doi.org/10.1186/s12912-025-03128-3.
Wang, Bo, Cecilie Katrine Grønvik, Karen Fortuna, Trude Eines, Ingunn Mundal, and Marianne Storm. "What Is in There for Artificial Intelligence to Support Mental Health Care for Persons with Serious Mental Illness? Opportunities and Challenges." Studies in Health Technology and Informatics 325 (May 2, 2025): 8–15. https://doi.org/10.3233/SHTI250208.
Nickel, Brooke, Julie Ayre, M. Luke Marinovich, David P. Smith, Karen Chiam, Christoph I. Lee, Timothy J. Wilt, Melody Taba, Kirsten McCaffery, and Nehmat Houssami. "Are AI chatbots concordant with evidence-based cancer screening recommendations?" Patient Education and Counseling 134 (May 2025): 108677. https://doi.org/10.1016/j.pec.2025.108677.
Weber, V., A. Truelove, S. S. Gohari, L. A. Wynne, R. J. Kearns, and J. E. O'Carroll. "Online patient information on labour epidural analgesia provided by UK National Health Services hospitals: assessment of readability and improvement of readability standards using ChatGPT." International Journal of Obstetric Anesthesia 62 (May 2025): 104344. https://doi.org/10.1016/j.ijoa.2025.104344.
Tripathi, Satvik, Dana Alkhulaifat, Meghana Muppuri, Ameena Elahi, and Farouk Dako. "Large Language Models for Global Health Clinics: Opportunities and Challenges." Journal of the American College of Radiology: JACR, April 29, 2025, S1546-1440(25)00205-4. https://doi.org/10.1016/j.jacr.2025.04.007.
Pérez-Esteve, Clara, Mercedes Guilabert, Valerie Matarredona, Einav Srulovici, Susanna Tella, Reinhard Strametz, and José Joaquín Mira. "AI in Home Care-Evaluation of Large Language Models for Future Training of Informal Caregivers: Observational Comparative Case Study." Journal of Medical Internet Research 27 (April 28, 2025): e70703. https://doi.org/10.2196/70703.
Chokkakula, Santosh, Siomui Chong, Bing Yang, Hong Jiang, Juan Yu, Ruiqin Han, Idress Hamad Attitalla, Chengliang Yin, and Shuyao Zhang. "Quantum leap in medical mentorship: exploring ChatGPT's transition from textbooks to terabytes." Frontiers in Medicine 12 (April 28, 2025): 1517981. https://doi.org/10.3389/fmed.2025.1517981.
Høj, Simon, Vibeke Backer, Charlotte Suppli Ulrik, Torben Sigsgaard, and Howraman Meteran. "Artificial intelligence in asthma health literacy: a comparative analysis of ChatGPT versus Gemini." The Journal of Asthma: Official Journal of the Association for the Care of Asthma, April 26, 2025, 1–7. https://doi.org/10.1080/02770903.2025.2495729.
Buchgraber-Schnalzer, Bianca, Marco Tilli, Rupert Beinhauer, Waltraud Jelinek-Krickl, Raphaele Raab, Klaus Lichtenegger, Michael Hammer, Gernot Reishofer, and Helmut Ritschl. "cMOOC Recommendations to Enhance AI Literacy Among Healthcare Professionals." Studies in Health Technology and Informatics 324 (April 24, 2025): 135–40. https://doi.org/10.3233/SHTI250174.
Ding, Dan, Lindsey Morris, Gina Novario, Andrea Fairman, Kacey Roehrich, Palma Foschi Walko, and Jessica Boateng. "Mainstream Smart Home Technology-Based Intervention to Enhance Functional Independence in Individuals With Complex Physical Disabilities: Single-Group Pre-Post Feasibility Study." JMIR Rehabilitation and Assistive Technologies 12 (April 24, 2025): e70855. https://doi.org/10.2196/70855.
Lindbäck, Yvonne, Karin Schröder, Torkel Engström, Karin Valeskog, and Sofi Sonesson. "Generative artificial intelligence in physiotherapy education: great potential amidst challenges- a qualitative interview study." BMC Medical Education 25, no. 1 (April 24, 2025): 603. https://doi.org/10.1186/s12909-025-07106-w.
Wong, Brian Li Han, Garry Aslanyan, Warisa Panichkriangkrai, Ricardo Baptista Leite, Jemilah Mahmood, and Anders Nordström. "From algorithms to negotiations: Why health diplomacy must adapt." PLOS Global Public Health 5, no. 4 (April 23, 2025): e0004488. https://doi.org/10.1371/journal.pgph.0004488.
Giaxi, Paraskevi, Victoria Vivilaki, Angeliki Sarella, and Kleanthi Gourounti. "Artificial Intelligence in Midwifery: A Scoping Review of Current Applications, Future Prospects, and Midwives' Perspectives." Healthcare (Basel, Switzerland) 13, no. 8 (April 19, 2025): 942. https://doi.org/10.3390/healthcare13080942.
López-Pérez, Belén, Yuhui Chen, Xiuhui Li, Shixing Cheng, and Pooya Razavi. “Exploring the Potential of Large Language Models to Understand Interpersonal Emotion Regulation Strategies from Narratives.” Emotion (Washington, D.C.), April 17, 2025. https://doi.org/10.1037/emo0001528.
Tripathi, Satvik, Liam Mutter, Meghana Muppuri, Suhani Dheer, Emiliano Garza-Frias, Komal Awan, Aakash Jha, et al. "PRECISE framework: Enhanced radiology reporting with GPT for improved readability, reliability, and patient-centered care." European Journal of Radiology 187 (April 17, 2025): 112124. https://doi.org/10.1016/j.ejrad.2025.112124.
Reaver, Carrie N., Daniel E. Pereira, Elisa V. Carrillo, Carolena Rojas Marcos, and Charles A. Goldfarb. "Evaluating the Performance of Artificial Intelligence for Improving Readability of Online English- and Spanish-Language Orthopaedic Patient Educational Material: Challenges in Bridging the Digital Divide." The Journal of Bone and Joint Surgery. American Volume 107, no. 8 (April 16, 2025): e36. https://doi.org/10.2106/JBJS.24.01078.
Young, Anna, and Foluke Omosun. "A comparative analysis of CDC and AI-generated health information using computer-aided text analysis." Journal of Communication in Healthcare, April 14, 2025, 1–12. https://doi.org/10.1080/17538068.2025.2487378.
McGrath, Colman, Chun Wang Reinhard Chau, and Gustavo Fabián Molina. “Monitoring Oral Health Remotely: Ethical Considerations When Using AI among Vulnerable Populations.” Frontiers in Oral Health 6 (April 14, 2025): 1587630. https://doi.org/10.3389/froh.2025.1587630.
Lavoie-Gagne, Ophelie Z., Oscar Y. Shen, Neal C. Chen, and Abhiram R. Bhashyam. "Assessing the Usability of ChatGPT Responses Compared to Other Online Information in Hand Surgery." Hand (New York, N.Y.), April 12, 2025, 15589447251329584. https://doi.org/10.1177/15589447251329584.
Stephenson-Moe, Christoph A., Benjamin J. Behers, Rebecca M. Gibons, Brett M. Behers, Laura De Jesus Herrera, Djhemson Anneaud, Manuel A. Rosario, Caroline N. Wojtas, Samantha Bhambrah, and Karen M. Hamad. "Assessing the quality and readability of patient education materials on chemotherapy cardiotoxicity from artificial intelligence chatbots: An observational cross-sectional study." Medicine 104, no. 15 (April 11, 2025): e42135. https://doi.org/10.1097/MD.0000000000042135.
Driel, M. H. Elise van, Noa Blok, Jan A. J. G. van den Brand, Davy van de Sande, Marianne de Vries, Bram Eijlers, Fokko Smits, et al. "Leveraging GPT-4 enables patient comprehension of radiology reports." European Journal of Radiology 187 (April 11, 2025): 112111. https://doi.org/10.1016/j.ejrad.2025.112111.
Sendlhofer, Gerald. "Smart Hospital." Wiener klinisches Magazin, April 11, 2025.
Liu, Xiao, Anjana Susarla, and Rema Padman. "Promoting Health Literacy With Human-in-the-Loop Video Understandability Classification of YouTube Videos: Development and Evaluation Study." Journal of Medical Internet Research 27 (April 8, 2025): e56080. https://doi.org/10.2196/56080.
Staccini, Pascal, Annie Y. S. Lau, and Findings from the Yearbook 2024 Section on Consumer Health Informatics. "Precision in Prevention and Health Surveillance: How Artificial Intelligence May Improve the Time of Identification of Health Concerns through Social Media Content Analysis." Yearbook of Medical Informatics 33, no. 1 (April 8, 2025): 158–65. https://doi.org/10.1055/s-0044-1800736.
Hou, Zhiyuan, Zhengdong Wu, Zhiqiang Qu, Liubing Gong, Hui Peng, Mark Jit, Heidi J. Larson, Joseph T. Wu, and Leesa Lin. "A vaccine chatbot intervention for parents to improve HPV vaccination uptake among middle school girls: a cluster randomized trial." Nature Medicine, April 7, 2025. https://doi.org/10.1038/s41591-025-03618-6.
El Arab, Rabie Adel, Omayma Abdulaziz Al Moosa, Fuad H. Abuadas, and Joel Somerville. "The Role of AI in Nursing Education and Practice: Umbrella Review." Journal of Medical Internet Research 27 (April 4, 2025): e69881. https://doi.org/10.2196/69881.
El-Sayed, Ahmed Abdelwahab Ibrahim, Samira Ahmed Alsenany, Raghad Saad Eid Almalki, and Maha Gamal Ramadan Asal. "Fostering creativity-nurturing behaviors among nurse educators: Investigating the interplay between evidence-based practice climate and artificial intelligence competence self-efficacy." Nurse Education Today 151 (April 4, 2025): 106734. https://doi.org/10.1016/j.nedt.2025.106734.
Olawade, David B., Kusal Weerasinghe, Jennifer Teke, Maines Msiska, Stergios Boussios, and Eleni Hatzidimitriadou. "Evaluating AI adoption in healthcare: Insights from the information governance professionals in the United Kingdom." International Journal of Medical Informatics 199 (April 4, 2025): 105909. https://doi.org/10.1016/j.ijmedinf.2025.105909.
Santos, Paulo, and Isabel Nazaré. "The doctor and patient of tomorrow: exploring the intersection of artificial intelligence, preventive medicine, and ethical challenges in future healthcare." Frontiers in Digital Health 7 (April 3, 2025): 1588479. https://doi.org/10.3389/fdgth.2025.1588479.
Ellison, India E., Wendelyn M. Oslock, Abiha Abdullah, Lauren Wood, Mohanraj Thirumalai, Nathan English, Bayley A. Jones, Robert Hollis, Michael Rubyan, and Daniel I. Chu. "De novo generation of colorectal patient educational materials using large language models: Prompt engineering key to improved readability." Surgery 180 (April 2025): 109024. https://doi.org/10.1016/j.surg.2024.109024.
Tuygunov, Nozimjon, Lakshman Samaranayake, Zohaib Khurshid, Paak Rewthamrongsris, Falk Schwendicke, Thanaphum Osathanon, and Noor Azlin Yahya. "The Transformative Role of Artificial Intelligence in Dentistry: A Comprehensive Overview Part 2: The Promise and Perils, and the International Dental Federation Communique." International Dental Journal 75, no. 2 (April 2025): 397–404. https://doi.org/10.1016/j.identj.2025.02.006.
Samaranayake, Lakshman, Nozimjon Tuygunov, Falk Schwendicke, Thanaphum Osathanon, Zohaib Khurshid, Shukhrat A. Boymuradov, and Arief Cahyanto. "The Transformative Role of Artificial Intelligence in Dentistry: A Comprehensive Overview. Part 1: Fundamentals of AI, and its Contemporary Applications in Dentistry." International Dental Journal 75, no. 2 (April 2025): 383–96. https://doi.org/10.1016/j.identj.2025.02.005.
Biesheuvel, Laurens A., Jessica D. Workum, Merijn Reuland, Michel E. van Genderen, Patrick Thoral, Dave Dongelmans, and Paul Elbers. “Large Language Models in Critical Care.” Journal of Intensive Medicine 5, no. 2 (April 2025): 113–18. https://doi.org/10.1016/j.jointm.2024.12.001.
Yun, Hye Sun, and Timothy Bickmore. "Online Health Information-Seeking in the Era of Large Language Models: Cross-Sectional Web-Based Survey Study." Journal of Medical Internet Research 27 (March 31, 2025): e68560. https://doi.org/10.2196/68560.
Abbas, Syed A., Izmir Yusifzada, and Sufia Athar. "Revolutionizing Medicine: Chatbots as Catalysts for Improved Diagnosis, Treatment, and Patient Support." Cureus 17, no. 3 (March 21, 2025): e80935. https://doi.org/10.7759/cureus.80935.
Koch, Roland, Marie-Theres Steffen, Anna-Jasmin Wetzel, Christine Preiser, Malte Klemmt, Hans-Jörg Ehni, Regina Mueller, and Stefanie Joos. "Exploring Laypersons' Experiences With a Mobile Symptom Checker App as an Interface Between eHealth Literacy, Health Literacy, and Health-Related Behavior: Qualitative Interview Study." JMIR Formative Research 9 (March 21, 2025): e60647. https://doi.org/10.2196/60647.
Šuto Pavičić, Jelena, Ana Marušić, and Ivan Buljan. "Using ChatGPT to Improve the Presentation of Plain Language Summaries of Cochrane Systematic Reviews About Oncology Interventions: Cross-Sectional Study." JMIR Cancer 11 (March 19, 2025): e63347. https://doi.org/10.2196/63347.