ChatGPT provides acceptable responses to patient questions regarding common shoulder pathology

ChatGPT is rapidly becoming a source of medical knowledge for patients. This study aims to assess the completeness and accuracy of ChatGPT's answers to the most frequently asked patients' questions about shoulder pathology. ChatGPT (version 3.5) was queried to produce the five most common...

Full description

Saved in:
Bibliographic Details
Published inShoulder & elbow p. 17585732241283971
Main Authors Ghilzai, Umar, Fiedler, Benjamin, Ghali, Abdullah, Singh, Aaron, Cass, Benjamin, Young, Allan, Ahmed, Adil Shahzad
Format Journal Article
LanguageEnglish
Published United States 25.09.2024
Subjects
Online AccessGet more information

Cover

Loading…
Abstract ChatGPT is rapidly becoming a source of medical knowledge for patients. This study aims to assess the completeness and accuracy of ChatGPT's answers to the most frequently asked patients' questions about shoulder pathology. ChatGPT (version 3.5) was queried to produce the five most common shoulder pathologies: biceps tendonitis, rotator cuff tears, shoulder arthritis, shoulder dislocation and adhesive capsulitis. Subsequently, it generated the five most common patient questions regarding these pathologies and was queried to respond. Responses were evaluated by three shoulder and elbow fellowship-trained orthopedic surgeons with a mean of 9 years of independent practice, on Likert scales for accuracy (1-6) and completeness (rated 1-3). For all questions, responses were deemed acceptable, rated at least "nearly all correct," indicated by a score of 5 or greater for accuracy, and "adequately complete," indicated by a minimum of 2 for completeness. The mean scores for accuracy and completeness, respectively, were 5.5 and 2.6 for rotator cuff tears, 5.8 and 2.7 for shoulder arthritis, 5.5 and 2.3 for shoulder dislocations, 5.1 and 2.4 for adhesive capsulitis, 5.8 and 2.9 for biceps tendonitis. ChatGPT provides both accurate and complete responses to the most common patients' questions about shoulder pathology. These findings suggest that Large Language Models might play a role as a patient resource; however, patients should always verify online information with their physician. Level V Expert Opinion.
AbstractList ChatGPT is rapidly becoming a source of medical knowledge for patients. This study aims to assess the completeness and accuracy of ChatGPT's answers to the most frequently asked patients' questions about shoulder pathology. ChatGPT (version 3.5) was queried to produce the five most common shoulder pathologies: biceps tendonitis, rotator cuff tears, shoulder arthritis, shoulder dislocation and adhesive capsulitis. Subsequently, it generated the five most common patient questions regarding these pathologies and was queried to respond. Responses were evaluated by three shoulder and elbow fellowship-trained orthopedic surgeons with a mean of 9 years of independent practice, on Likert scales for accuracy (1-6) and completeness (rated 1-3). For all questions, responses were deemed acceptable, rated at least "nearly all correct," indicated by a score of 5 or greater for accuracy, and "adequately complete," indicated by a minimum of 2 for completeness. The mean scores for accuracy and completeness, respectively, were 5.5 and 2.6 for rotator cuff tears, 5.8 and 2.7 for shoulder arthritis, 5.5 and 2.3 for shoulder dislocations, 5.1 and 2.4 for adhesive capsulitis, 5.8 and 2.9 for biceps tendonitis. ChatGPT provides both accurate and complete responses to the most common patients' questions about shoulder pathology. These findings suggest that Large Language Models might play a role as a patient resource; however, patients should always verify online information with their physician. Level V Expert Opinion.
Author Cass, Benjamin
Singh, Aaron
Ghilzai, Umar
Young, Allan
Ahmed, Adil Shahzad
Ghali, Abdullah
Fiedler, Benjamin
Author_xml – sequence: 1
  givenname: Umar
  surname: Ghilzai
  fullname: Ghilzai, Umar
  organization: Baylor College of Medicine, Department of Orthopedic Surgery, Houston, TX, USA
– sequence: 2
  givenname: Benjamin
  surname: Fiedler
  fullname: Fiedler, Benjamin
  organization: Baylor College of Medicine, Department of Orthopedic Surgery, Houston, TX, USA
– sequence: 3
  givenname: Abdullah
  surname: Ghali
  fullname: Ghali, Abdullah
  organization: Baylor College of Medicine, Department of Orthopedic Surgery, Houston, TX, USA
– sequence: 4
  givenname: Aaron
  orcidid: 0000-0003-3806-3464
  surname: Singh
  fullname: Singh, Aaron
  organization: UT Health San Antonio, Department of Orthopaedics, San Antonio, TX, USA
– sequence: 5
  givenname: Benjamin
  surname: Cass
  fullname: Cass, Benjamin
  organization: Sydney Shoulder Research Institute, Sydney Shoulder Specialists, Greenwich, New South Wales, Australia
– sequence: 6
  givenname: Allan
  surname: Young
  fullname: Young, Allan
  organization: Sydney Shoulder Research Institute, Sydney Shoulder Specialists, Greenwich, New South Wales, Australia
– sequence: 7
  givenname: Adil Shahzad
  surname: Ahmed
  fullname: Ahmed, Adil Shahzad
  organization: Baylor College of Medicine, Department of Orthopedic Surgery, Houston, TX, USA
BackLink https://www.ncbi.nlm.nih.gov/pubmed/39545009$$D View this record in MEDLINE/PubMed
BookMark eNo1z81Kw0AUBeBZVOyPPoAbmReIzv9MllK0CgVd1K3lJrlNIkkmZiZC394EdXXhO4cDd00Wne-QkBvO7ji39p5b7bSVQigunEwtX5DVbMmMS7IO4ZMxY43Vl2QpU600Y-mKfGwriLu3A-0H_10XGCjkOfYRsgbpgKH3XZgwetpDrLGL9GvEEOuJp7iEoai7kua-bX1HQ-XHpsBh7la-8eX5ilycoAl4_Xc35P3p8bB9Tvavu5ftwz7JhUxjAg611MYBN-AMoJGpY5gyJ52SymUnWwiLaLRhWWadKhQAWjTGZBJyLcSG3P7u9mPWYnHsh7qF4Xz8f1T8AAsvVyM
ContentType Journal Article
Copyright The Author(s) 2024.
Copyright_xml – notice: The Author(s) 2024.
DBID NPM
DOI 10.1177/17585732241283971
DatabaseName PubMed
DatabaseTitle PubMed
DatabaseTitleList PubMed
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
DeliveryMethod no_fulltext_linktorsrc
ExternalDocumentID 39545009
Genre Journal Article
GroupedDBID 05W
0R~
1OC
4.4
54M
AACMV
AACTG
AAEWN
AAGMC
AAJPV
AAKGS
AARDL
AATAA
AATBZ
AAUAS
ABAWP
ABCCA
ABJNI
ABLUO
ABPNF
ABQXT
ABVFX
ACARO
ACDXX
ACFEJ
ACGFS
ACGZU
ACJER
ACJTF
ACLFY
ACLZU
ACOXC
ACROE
ACSIQ
ACTQU
ACUAV
ACUIR
ACXKE
ACXMB
ADBBV
ADRRZ
ADVBO
AECGH
AEDTQ
AEFTW
AEKYL
AEPTA
AERKM
AESZF
AEUHG
AEUIJ
AEWDL
AEWHI
AFKRG
AFMOU
AFQAA
AGKLV
AGWFA
AHMBA
AIIQI
AIOMO
AJUZI
AJXAJ
ALKWR
ALMA_UNASSIGNED_HOLDINGS
ALTZF
AMCVQ
ANDLU
AOIJS
ARTOV
AUTPY
AYAKG
BBRGL
BDDNI
BKIIM
BPACV
BSEHC
BWJAD
DC.
DV7
EBS
ESX
FHBDP
GROUPED_SAGE_PREMIER_JOURNAL_COLLECTION
H13
HZ~
J8X
JCYGO
K.F
M4V
NPM
O9-
OIG
OK1
PQQKQ
ROL
RPM
S01
SCNPE
SFC
SHG
SPQ
SPV
ID FETCH-LOGICAL-c239t-a8e53568a16a86ae63980e908384348bf7d27ee6560bb784d4aae7e666b3ac522
ISSN 1758-5732
IngestDate Thu Nov 28 20:51:40 EST 2024
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords large language model
machine learning
shoulder
ChatGPT
Artificial intelligence
Language English
License The Author(s) 2024.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c239t-a8e53568a16a86ae63980e908384348bf7d27ee6560bb784d4aae7e666b3ac522
ORCID 0000-0003-3806-3464
OpenAccessLink https://pubmed.ncbi.nlm.nih.gov/PMC11559869
PMID 39545009
ParticipantIDs pubmed_primary_39545009
PublicationCentury 2000
PublicationDate 2024-Sep-25
PublicationDateYYYYMMDD 2024-09-25
PublicationDate_xml – month: 09
  year: 2024
  text: 2024-Sep-25
  day: 25
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Shoulder & elbow
PublicationTitleAlternate Shoulder Elbow
PublicationYear 2024
SSID ssj0067675
Score 2.320505
Snippet ChatGPT is rapidly becoming a source of medical knowledge for patients. This study aims to assess the completeness and accuracy of ChatGPT's answers to the...
SourceID pubmed
SourceType Index Database
StartPage 17585732241283971
Title ChatGPT provides acceptable responses to patient questions regarding common shoulder pathology
URI https://www.ncbi.nlm.nih.gov/pubmed/39545009
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT9tAEF4VKlVcKlBbnkV76C0yIvF6H8cQERASqBKJxKlo1h43IOKg4BO_vrMP2xK0QLlY0a5jbXa-rL-ZnW-WsR9WFEZZxESaQici0wWtgyZPpMB-VgCUg75TI59fyNOpOLvKrrrtAq8uqe1B_vhXXcl7rEptZFenkv0Py7YPpQb6TPalK1mYrm-y8WgG9cnPSS_K6R56kLssFa-GWobk11DBIVZP7fmXgE99W-Jvh42guKUB9x5m7rBrXLp7Z12sPfLWy6bXIQXv7KINfZ_Mbu4ew5nW0zm0qb5jorZRZHiE1S3Mb6ruGxA02UNbkAPcBaQvaTg-yjOEZURLjEcMhEueCNrluISSB5JkKkYtw7Lo2lwT0QWiMyYcuvJ88fbbxy_eS_N_P_fWTA1xv0NfWuGV3if1tJuuFbaitDvs48LFd8K721ev8xLa-BviPrgr0fVsXGvsU_OsJz6J5yaTdfY5OhV8GBCywT5g9YX9iujgDTp4hw7eooPXCx7RwVt08BYdPKCDN-jgLTq-sun4eDI6TeJpGkk-SE2dgMYszaSGvgQtAYma6kM0RMG1SIW2pSoGCtEVY7JWaVEIAFRI7q1NISea_o2tVosKtxiXOWgoodSIxPCMAmGsTAulJTkDRGG32WaYjuv7UDLlupmonX_27LK1Dk177GNJ_1H8ToSvtvveRn8AfaZTjA
link.rule.ids 780
linkProvider National Library of Medicine
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=ChatGPT+provides+acceptable+responses+to+patient+questions+regarding+common+shoulder+pathology&rft.jtitle=Shoulder+%26+elbow&rft.au=Ghilzai%2C+Umar&rft.au=Fiedler%2C+Benjamin&rft.au=Ghali%2C+Abdullah&rft.au=Singh%2C+Aaron&rft.date=2024-09-25&rft.issn=1758-5732&rft.spage=17585732241283971&rft_id=info:doi/10.1177%2F17585732241283971&rft_id=info%3Apmid%2F39545009&rft_id=info%3Apmid%2F39545009&rft.externalDocID=39545009
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1758-5732&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1758-5732&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1758-5732&client=summon