ChatGPT-Generated Differential Diagnosis Lists for Complex Case–Derived Clinical Vignettes: Diagnostic Accuracy Evaluation

Background:The diagnostic accuracy of differential diagnoses generated by artificial intelligence chatbots, including ChatGPT models, for complex clinical vignettes derived from general internal medicine (GIM) department case reports is unknown.Objective:This study aims to evaluate the accuracy of t...

Full description

Saved in:
Bibliographic Details
Published inJMIR medical informatics Vol. 11; p. e48808
Main Authors Hirosawa, Takanobu, Kawamura, Ren, Harada, Yukinori, Mizuta, Kazuya, Tokumasu, Kazuki, Kaji, Yuki, Suzuki, Tomoharu, Shimizu, Taro
Format Journal Article
LanguageEnglish
Published Toronto JMIR Publications 09.10.2023
Subjects
Online AccessGet full text

Cover

Loading…
Abstract Background:The diagnostic accuracy of differential diagnoses generated by artificial intelligence chatbots, including ChatGPT models, for complex clinical vignettes derived from general internal medicine (GIM) department case reports is unknown.Objective:This study aims to evaluate the accuracy of the differential diagnosis lists generated by both third-generation ChatGPT (ChatGPT-3.5) and fourth-generation ChatGPT (ChatGPT-4) by using case vignettes from case reports published by the Department of GIM of Dokkyo Medical University Hospital, Japan.Methods:We searched PubMed for case reports. Upon identification, physicians selected diagnostic cases, determined the final diagnosis, and displayed them into clinical vignettes. Physicians typed the determined text with the clinical vignettes in the ChatGPT-3.5 and ChatGPT-4 prompts to generate the top 10 differential diagnoses. The ChatGPT models were not specially trained or further reinforced for this task. Three GIM physicians from other medical institutions created differential diagnosis lists by reading the same clinical vignettes. We measured the rate of correct diagnosis within the top 10 differential diagnosis lists, top 5 differential diagnosis lists, and the top diagnosis.Results:In total, 52 case reports were analyzed. The rates of correct diagnosis by ChatGPT-4 within the top 10 differential diagnosis lists, top 5 differential diagnosis lists, and top diagnosis were 83% (43/52), 81% (42/52), and 60% (31/52), respectively. The rates of correct diagnosis by ChatGPT-3.5 within the top 10 differential diagnosis lists, top 5 differential diagnosis lists, and top diagnosis were 73% (38/52), 65% (34/52), and 42% (22/52), respectively. The rates of correct diagnosis by ChatGPT-4 were comparable to those by physicians within the top 10 (43/52, 83% vs 39/52, 75%, respectively; P=.47) and within the top 5 (42/52, 81% vs 35/52, 67%, respectively; P=.18) differential diagnosis lists and top diagnosis (31/52, 60% vs 26/52, 50%, respectively; P=.43) although the difference was not significant. The ChatGPT models’ diagnostic accuracy did not significantly vary based on open access status or the publication date (before 2011 vs 2022).Conclusions:This study demonstrates the potential diagnostic accuracy of differential diagnosis lists generated using ChatGPT-3.5 and ChatGPT-4 for complex clinical vignettes from case reports published by the GIM department. The rate of correct diagnoses within the top 10 and top 5 differential diagnosis lists generated by ChatGPT-4 exceeds 80%. Although derived from a limited data set of case reports from a single department, our findings highlight the potential utility of ChatGPT-4 as a supplementary tool for physicians, particularly for those affiliated with the GIM department. Further investigations should explore the diagnostic accuracy of ChatGPT by using distinct case materials beyond its training data. Such efforts will provide a comprehensive insight into the role of artificial intelligence in enhancing clinical decision-making.
AbstractList Background:The diagnostic accuracy of differential diagnoses generated by artificial intelligence chatbots, including ChatGPT models, for complex clinical vignettes derived from general internal medicine (GIM) department case reports is unknown.Objective:This study aims to evaluate the accuracy of the differential diagnosis lists generated by both third-generation ChatGPT (ChatGPT-3.5) and fourth-generation ChatGPT (ChatGPT-4) by using case vignettes from case reports published by the Department of GIM of Dokkyo Medical University Hospital, Japan.Methods:We searched PubMed for case reports. Upon identification, physicians selected diagnostic cases, determined the final diagnosis, and displayed them into clinical vignettes. Physicians typed the determined text with the clinical vignettes in the ChatGPT-3.5 and ChatGPT-4 prompts to generate the top 10 differential diagnoses. The ChatGPT models were not specially trained or further reinforced for this task. Three GIM physicians from other medical institutions created differential diagnosis lists by reading the same clinical vignettes. We measured the rate of correct diagnosis within the top 10 differential diagnosis lists, top 5 differential diagnosis lists, and the top diagnosis.Results:In total, 52 case reports were analyzed. The rates of correct diagnosis by ChatGPT-4 within the top 10 differential diagnosis lists, top 5 differential diagnosis lists, and top diagnosis were 83% (43/52), 81% (42/52), and 60% (31/52), respectively. The rates of correct diagnosis by ChatGPT-3.5 within the top 10 differential diagnosis lists, top 5 differential diagnosis lists, and top diagnosis were 73% (38/52), 65% (34/52), and 42% (22/52), respectively. The rates of correct diagnosis by ChatGPT-4 were comparable to those by physicians within the top 10 (43/52, 83% vs 39/52, 75%, respectively; P=.47) and within the top 5 (42/52, 81% vs 35/52, 67%, respectively; P=.18) differential diagnosis lists and top diagnosis (31/52, 60% vs 26/52, 50%, respectively; P=.43) although the difference was not significant. The ChatGPT models’ diagnostic accuracy did not significantly vary based on open access status or the publication date (before 2011 vs 2022).Conclusions:This study demonstrates the potential diagnostic accuracy of differential diagnosis lists generated using ChatGPT-3.5 and ChatGPT-4 for complex clinical vignettes from case reports published by the GIM department. The rate of correct diagnoses within the top 10 and top 5 differential diagnosis lists generated by ChatGPT-4 exceeds 80%. Although derived from a limited data set of case reports from a single department, our findings highlight the potential utility of ChatGPT-4 as a supplementary tool for physicians, particularly for those affiliated with the GIM department. Further investigations should explore the diagnostic accuracy of ChatGPT by using distinct case materials beyond its training data. Such efforts will provide a comprehensive insight into the role of artificial intelligence in enhancing clinical decision-making.
The diagnostic accuracy of differential diagnoses generated by artificial intelligence chatbots, including ChatGPT models, for complex clinical vignettes derived from general internal medicine (GIM) department case reports is unknown.BACKGROUNDThe diagnostic accuracy of differential diagnoses generated by artificial intelligence chatbots, including ChatGPT models, for complex clinical vignettes derived from general internal medicine (GIM) department case reports is unknown.This study aims to evaluate the accuracy of the differential diagnosis lists generated by both third-generation ChatGPT (ChatGPT-3.5) and fourth-generation ChatGPT (ChatGPT-4) by using case vignettes from case reports published by the Department of GIM of Dokkyo Medical University Hospital, Japan.OBJECTIVEThis study aims to evaluate the accuracy of the differential diagnosis lists generated by both third-generation ChatGPT (ChatGPT-3.5) and fourth-generation ChatGPT (ChatGPT-4) by using case vignettes from case reports published by the Department of GIM of Dokkyo Medical University Hospital, Japan.We searched PubMed for case reports. Upon identification, physicians selected diagnostic cases, determined the final diagnosis, and displayed them into clinical vignettes. Physicians typed the determined text with the clinical vignettes in the ChatGPT-3.5 and ChatGPT-4 prompts to generate the top 10 differential diagnoses. The ChatGPT models were not specially trained or further reinforced for this task. Three GIM physicians from other medical institutions created differential diagnosis lists by reading the same clinical vignettes. We measured the rate of correct diagnosis within the top 10 differential diagnosis lists, top 5 differential diagnosis lists, and the top diagnosis.METHODSWe searched PubMed for case reports. Upon identification, physicians selected diagnostic cases, determined the final diagnosis, and displayed them into clinical vignettes. Physicians typed the determined text with the clinical vignettes in the ChatGPT-3.5 and ChatGPT-4 prompts to generate the top 10 differential diagnoses. The ChatGPT models were not specially trained or further reinforced for this task. Three GIM physicians from other medical institutions created differential diagnosis lists by reading the same clinical vignettes. We measured the rate of correct diagnosis within the top 10 differential diagnosis lists, top 5 differential diagnosis lists, and the top diagnosis.In total, 52 case reports were analyzed. The rates of correct diagnosis by ChatGPT-4 within the top 10 differential diagnosis lists, top 5 differential diagnosis lists, and top diagnosis were 83% (43/52), 81% (42/52), and 60% (31/52), respectively. The rates of correct diagnosis by ChatGPT-3.5 within the top 10 differential diagnosis lists, top 5 differential diagnosis lists, and top diagnosis were 73% (38/52), 65% (34/52), and 42% (22/52), respectively. The rates of correct diagnosis by ChatGPT-4 were comparable to those by physicians within the top 10 (43/52, 83% vs 39/52, 75%, respectively; P=.47) and within the top 5 (42/52, 81% vs 35/52, 67%, respectively; P=.18) differential diagnosis lists and top diagnosis (31/52, 60% vs 26/52, 50%, respectively; P=.43) although the difference was not significant. The ChatGPT models' diagnostic accuracy did not significantly vary based on open access status or the publication date (before 2011 vs 2022).RESULTSIn total, 52 case reports were analyzed. The rates of correct diagnosis by ChatGPT-4 within the top 10 differential diagnosis lists, top 5 differential diagnosis lists, and top diagnosis were 83% (43/52), 81% (42/52), and 60% (31/52), respectively. The rates of correct diagnosis by ChatGPT-3.5 within the top 10 differential diagnosis lists, top 5 differential diagnosis lists, and top diagnosis were 73% (38/52), 65% (34/52), and 42% (22/52), respectively. The rates of correct diagnosis by ChatGPT-4 were comparable to those by physicians within the top 10 (43/52, 83% vs 39/52, 75%, respectively; P=.47) and within the top 5 (42/52, 81% vs 35/52, 67%, respectively; P=.18) differential diagnosis lists and top diagnosis (31/52, 60% vs 26/52, 50%, respectively; P=.43) although the difference was not significant. The ChatGPT models' diagnostic accuracy did not significantly vary based on open access status or the publication date (before 2011 vs 2022).This study demonstrates the potential diagnostic accuracy of differential diagnosis lists generated using ChatGPT-3.5 and ChatGPT-4 for complex clinical vignettes from case reports published by the GIM department. The rate of correct diagnoses within the top 10 and top 5 differential diagnosis lists generated by ChatGPT-4 exceeds 80%. Although derived from a limited data set of case reports from a single department, our findings highlight the potential utility of ChatGPT-4 as a supplementary tool for physicians, particularly for those affiliated with the GIM department. Further investigations should explore the diagnostic accuracy of ChatGPT by using distinct case materials beyond its training data. Such efforts will provide a comprehensive insight into the role of artificial intelligence in enhancing clinical decision-making.CONCLUSIONSThis study demonstrates the potential diagnostic accuracy of differential diagnosis lists generated using ChatGPT-3.5 and ChatGPT-4 for complex clinical vignettes from case reports published by the GIM department. The rate of correct diagnoses within the top 10 and top 5 differential diagnosis lists generated by ChatGPT-4 exceeds 80%. Although derived from a limited data set of case reports from a single department, our findings highlight the potential utility of ChatGPT-4 as a supplementary tool for physicians, particularly for those affiliated with the GIM department. Further investigations should explore the diagnostic accuracy of ChatGPT by using distinct case materials beyond its training data. Such efforts will provide a comprehensive insight into the role of artificial intelligence in enhancing clinical decision-making.
BackgroundThe diagnostic accuracy of differential diagnoses generated by artificial intelligence chatbots, including ChatGPT models, for complex clinical vignettes derived from general internal medicine (GIM) department case reports is unknown. ObjectiveThis study aims to evaluate the accuracy of the differential diagnosis lists generated by both third-generation ChatGPT (ChatGPT-3.5) and fourth-generation ChatGPT (ChatGPT-4) by using case vignettes from case reports published by the Department of GIM of Dokkyo Medical University Hospital, Japan. MethodsWe searched PubMed for case reports. Upon identification, physicians selected diagnostic cases, determined the final diagnosis, and displayed them into clinical vignettes. Physicians typed the determined text with the clinical vignettes in the ChatGPT-3.5 and ChatGPT-4 prompts to generate the top 10 differential diagnoses. The ChatGPT models were not specially trained or further reinforced for this task. Three GIM physicians from other medical institutions created differential diagnosis lists by reading the same clinical vignettes. We measured the rate of correct diagnosis within the top 10 differential diagnosis lists, top 5 differential diagnosis lists, and the top diagnosis. ResultsIn total, 52 case reports were analyzed. The rates of correct diagnosis by ChatGPT-4 within the top 10 differential diagnosis lists, top 5 differential diagnosis lists, and top diagnosis were 83% (43/52), 81% (42/52), and 60% (31/52), respectively. The rates of correct diagnosis by ChatGPT-3.5 within the top 10 differential diagnosis lists, top 5 differential diagnosis lists, and top diagnosis were 73% (38/52), 65% (34/52), and 42% (22/52), respectively. The rates of correct diagnosis by ChatGPT-4 were comparable to those by physicians within the top 10 (43/52, 83% vs 39/52, 75%, respectively; P=.47) and within the top 5 (42/52, 81% vs 35/52, 67%, respectively; P=.18) differential diagnosis lists and top diagnosis (31/52, 60% vs 26/52, 50%, respectively; P=.43) although the difference was not significant. The ChatGPT models’ diagnostic accuracy did not significantly vary based on open access status or the publication date (before 2011 vs 2022). ConclusionsThis study demonstrates the potential diagnostic accuracy of differential diagnosis lists generated using ChatGPT-3.5 and ChatGPT-4 for complex clinical vignettes from case reports published by the GIM department. The rate of correct diagnoses within the top 10 and top 5 differential diagnosis lists generated by ChatGPT-4 exceeds 80%. Although derived from a limited data set of case reports from a single department, our findings highlight the potential utility of ChatGPT-4 as a supplementary tool for physicians, particularly for those affiliated with the GIM department. Further investigations should explore the diagnostic accuracy of ChatGPT by using distinct case materials beyond its training data. Such efforts will provide a comprehensive insight into the role of artificial intelligence in enhancing clinical decision-making.
Author Tokumasu, Kazuki
Hirosawa, Takanobu
Kawamura, Ren
Harada, Yukinori
Shimizu, Taro
Mizuta, Kazuya
Kaji, Yuki
Suzuki, Tomoharu
AuthorAffiliation 1 Department of Diagnostic and Generalist Medicine Dokkyo Medical University Tochigi Japan
3 Department of General Medicine International University of Health and Welfare Narita Hospital Chiba Japan
4 Department of Hospital Medicine Urasoe General Hospital Okinawa Japan
2 Department of General Medicine Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences Okayama Japan
AuthorAffiliation_xml – name: 2 Department of General Medicine Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences Okayama Japan
– name: 1 Department of Diagnostic and Generalist Medicine Dokkyo Medical University Tochigi Japan
– name: 3 Department of General Medicine International University of Health and Welfare Narita Hospital Chiba Japan
– name: 4 Department of Hospital Medicine Urasoe General Hospital Okinawa Japan
Author_xml – sequence: 1
  givenname: Takanobu
  orcidid: 0000-0002-3573-8203
  surname: Hirosawa
  fullname: Hirosawa, Takanobu
– sequence: 2
  givenname: Ren
  orcidid: 0000-0002-5632-3218
  surname: Kawamura
  fullname: Kawamura, Ren
– sequence: 3
  givenname: Yukinori
  orcidid: 0000-0001-6042-7397
  surname: Harada
  fullname: Harada, Yukinori
– sequence: 4
  givenname: Kazuya
  orcidid: 0009-0000-8822-7127
  surname: Mizuta
  fullname: Mizuta, Kazuya
– sequence: 5
  givenname: Kazuki
  orcidid: 0000-0001-9513-6864
  surname: Tokumasu
  fullname: Tokumasu, Kazuki
– sequence: 6
  givenname: Yuki
  orcidid: 0000-0002-0267-9876
  surname: Kaji
  fullname: Kaji, Yuki
– sequence: 7
  givenname: Tomoharu
  orcidid: 0000-0002-5557-0516
  surname: Suzuki
  fullname: Suzuki, Tomoharu
– sequence: 8
  givenname: Taro
  orcidid: 0000-0002-3788-487X
  surname: Shimizu
  fullname: Shimizu, Taro
BookMark eNpdks9uEzEQxleoFS0l77ASQkKqQu1dr-3lgqptCZUiwaFwtbzjSepoYwfbG1GJA-_AG_IkuElBNCf_-803n2fmRXHkvMOimFDytqItv2BSEvmsOK2qlk5b3rKj__YnxSTGFSGEMso5F8-Lk1pIWjEuT4sf3Z1Os8-30xk6DDqhKa_sYoEBXbJ6yAe9dD7aWM5tTLFc-FB2fr0Z8HvZ6Yi_f_66wmC3Oa4brLOQY77apcOUML77G54slJcAY9BwX15v9TDqZL17WRwv9BBx8rieFV8-XN92H6fzT7Ob7nI-hYbQNDVAoKcCBEHT11VPjTBCGMp6bQhwQkxfmfwxBIZCNy0wAKCyhkYCSiD1WXGz1zVer9Qm2LUO98prq3YXPiyVDtnjgIrkXC2gkI3gTDAmOW_rumItq3qiNcta7_dam7Ffo4Fcp6CHJ6JPX5y9U0u_VZQ0LaN1mxXePCoE_23EmNTaRsBh0A79GFUlBZM14_wh2asDdOXH4HKtVO6ubIgkosrU6z0FwccYcPHPDSXqYT7Ubj4yd37AgU27RmSjdjig_wBvVrzp
CitedBy_id crossref_primary_10_1002_ajmg_a_63878
crossref_primary_10_1186_s12909_024_06309_x
crossref_primary_10_2196_58758
crossref_primary_10_2196_53985
crossref_primary_10_7759_cureus_48235
crossref_primary_10_1177_20552076241265215
crossref_primary_10_1007_s00508_024_02343_3
crossref_primary_10_7759_cureus_50629
crossref_primary_10_1016_j_oooo_2024_11_087
crossref_primary_10_1515_dx_2024_0027
crossref_primary_10_1001_jamanetworkopen_2024_57879
crossref_primary_10_1038_s41746_025_01543_z
crossref_primary_10_1177_00031348241256075
crossref_primary_10_3389_fdmed_2024_1456208
crossref_primary_10_1111_bcp_16275
crossref_primary_10_1016_j_xops_2024_100600
crossref_primary_10_2196_54067
crossref_primary_10_1111_epi_18322
crossref_primary_10_3390_diagnostics14161779
crossref_primary_10_2196_51798
crossref_primary_10_1111_nan_12997
crossref_primary_10_2196_54704
crossref_primary_10_1016_j_anndiagpath_2024_152392
crossref_primary_10_1111_odi_15082
crossref_primary_10_1515_dx_2024_0095
crossref_primary_10_3390_diagnostics14212393
crossref_primary_10_2147_JPR_S509845
crossref_primary_10_1111_jep_14011
crossref_primary_10_2196_59267
crossref_primary_10_2196_56110
crossref_primary_10_3390_app142310802
crossref_primary_10_1038_s41746_025_01556_8
crossref_primary_10_1016_j_esmorw_2024_100042
crossref_primary_10_4103_NRR_NRR_D_24_00165
crossref_primary_10_2196_65263
crossref_primary_10_1038_s41598_023_50884_w
crossref_primary_10_1186_s12911_024_02757_z
crossref_primary_10_1016_j_dld_2024_02_014
crossref_primary_10_7759_cureus_73127
crossref_primary_10_3390_curroncol31070284
crossref_primary_10_1007_s11606_024_09177_9
crossref_primary_10_2196_59133
crossref_primary_10_3390_jcm14020572
crossref_primary_10_1016_j_jfma_2024_08_032
crossref_primary_10_1016_S1473_3099_23_00750_8
crossref_primary_10_1515_dx_2024_0033
crossref_primary_10_1007_s00784_024_05587_5
crossref_primary_10_1016_j_spinee_2024_12_035
crossref_primary_10_1038_s41591_024_03180_7
crossref_primary_10_1186_s12911_024_02824_5
crossref_primary_10_3390_info16010038
Cites_doi 10.2196/35225
10.1097/INF.0000000000003852
10.1136/bcr-2017-223844
10.1001/jama.2022.13735
10.1371/journal.pone.0148991
10.1111/opo.12131
10.1515/dx-2023-0116
10.1148/radiol.223312
10.1370/afm.2908
10.1515/dx-2013-0029
10.1371/journal.pdig.0000198
10.1056/nejmra2302038
10.1016/j.amjmed.2023.02.011
10.2147/ijgm.s96741
10.17226/21794
10.1016/B978-0-12-398476-0.00002-6
10.1016/j.dsx.2023.102744
10.1136/bmjqs-2022-015436
10.1038/s41591-023-02289-5
10.48550/arXiv.2212.00857
10.2196/31810
10.1056/nejmsr2214184
10.3390/ijerph20043378
10.1111/medu.13382
10.1001/jama.2023.8288
10.3390/healthcare10040608
10.48550/arXiv.2303.08774
ContentType Journal Article
Copyright 2023. This work is licensed under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Takanobu Hirosawa, Ren Kawamura, Yukinori Harada, Kazuya Mizuta, Kazuki Tokumasu, Yuki Kaji, Tomoharu Suzuki, Taro Shimizu. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 09.10.2023.
Takanobu Hirosawa, Ren Kawamura, Yukinori Harada, Kazuya Mizuta, Kazuki Tokumasu, Yuki Kaji, Tomoharu Suzuki, Taro Shimizu. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 09.10.2023. 2023
Copyright_xml – notice: 2023. This work is licensed under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
– notice: Takanobu Hirosawa, Ren Kawamura, Yukinori Harada, Kazuya Mizuta, Kazuki Tokumasu, Yuki Kaji, Tomoharu Suzuki, Taro Shimizu. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 09.10.2023.
– notice: Takanobu Hirosawa, Ren Kawamura, Yukinori Harada, Kazuya Mizuta, Kazuki Tokumasu, Yuki Kaji, Tomoharu Suzuki, Taro Shimizu. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 09.10.2023. 2023
DBID AAYXX
CITATION
3V.
7X7
7XB
88C
8FI
8FJ
8FK
ABUWG
AFKRA
AZQEC
BENPR
CCPQU
DWQXO
FYUFA
GHDGH
K9.
M0S
M0T
PHGZM
PHGZT
PIMPY
PJZUB
PKEHL
PPXIY
PQEST
PQQKQ
PQUKI
7X8
5PM
DOA
DOI 10.2196/48808
DatabaseName CrossRef
ProQuest Central (Corporate)
Health & Medical Collection (ProQuest)
ProQuest Central (purchase pre-March 2016)
Healthcare Administration Database (Alumni)
ProQuest Hospital Collection
Hospital Premium Collection (Alumni Edition)
ProQuest Central (Alumni) (purchase pre-March 2016)
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
ProQuest Central Essentials
ProQuest Central
ProQuest One Community College
ProQuest Central
Health Research Premium Collection
Health Research Premium Collection (Alumni)
ProQuest Health & Medical Complete (Alumni)
ProQuest Health & Medical Collection
Healthcare Administration Database (ProQuest)
ProQuest Central Premium
ProQuest One Academic
ProQuest Publicly Available Content Database
ProQuest Health & Medical Research Collection
ProQuest One Academic Middle East (New)
ProQuest One Health & Nursing
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Academic
ProQuest One Academic UKI Edition
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
Publicly Available Content Database
ProQuest One Academic Middle East (New)
ProQuest Central Essentials
ProQuest Health & Medical Complete (Alumni)
ProQuest Central (Alumni Edition)
ProQuest One Community College
ProQuest One Health & Nursing
ProQuest Central
ProQuest Health & Medical Research Collection
Health Research Premium Collection
Health and Medicine Complete (Alumni Edition)
ProQuest Central Korea
Health & Medical Research Collection
ProQuest Central (New)
ProQuest One Academic Eastern Edition
ProQuest Health Management
ProQuest Hospital Collection
Health Research Premium Collection (Alumni)
ProQuest Hospital Collection (Alumni)
ProQuest Health & Medical Complete
ProQuest One Academic UKI Edition
ProQuest Health Management (Alumni Edition)
ProQuest One Academic
ProQuest One Academic (New)
ProQuest Central (Alumni)
MEDLINE - Academic
DatabaseTitleList Publicly Available Content Database
MEDLINE - Academic

Database_xml – sequence: 1
  dbid: DOA
  name: Open Access资源_DOAJ
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: BENPR
  name: ProQuest Central
  url: https://www.proquest.com/central
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 2291-9694
ExternalDocumentID oai_doaj_org_article_0c0c9ce78576474486693324942b0aa4
PMC10594139
10_2196_48808
GroupedDBID 53G
5VS
7X7
8FI
8FJ
AAFWJ
AAYXX
ABUWG
ADBBV
AFKRA
AFPKN
ALIPV
ALMA_UNASSIGNED_HOLDINGS
AOIJS
BAWUL
BCNDV
BENPR
CCPQU
CITATION
DIK
EMOBN
FYUFA
GROUPED_DOAJ
HMCUK
HYE
KQ8
M0T
M48
M~E
OK1
PGMZT
PHGZM
PHGZT
PIMPY
RPM
UKHRP
3V.
7XB
8FK
AZQEC
DWQXO
K9.
PJZUB
PKEHL
PPXIY
PQEST
PQQKQ
PQUKI
7X8
5PM
PUEGO
ID FETCH-LOGICAL-c501t-dc0cb17c70edb32b1d7d77d14bad0c600db2d667ec4e7a59c4ccc183c58ce8c03
IEDL.DBID M48
ISSN 2291-9694
IngestDate Wed Aug 27 01:29:04 EDT 2025
Thu Aug 21 18:35:52 EDT 2025
Fri Jul 11 02:59:44 EDT 2025
Fri Jul 25 21:55:56 EDT 2025
Tue Jul 01 01:42:00 EDT 2025
Thu Apr 24 23:05:07 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language English
License This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR Medical Informatics, is properly cited. The complete bibliographic information, a link to the original publication on https://medinform.jmir.org/, as well as this copyright and license information must be included.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c501t-dc0cb17c70edb32b1d7d77d14bad0c600db2d667ec4e7a59c4ccc183c58ce8c03
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0009-0000-8822-7127
0000-0002-5557-0516
0000-0002-5632-3218
0000-0002-3788-487X
0000-0001-6042-7397
0000-0002-0267-9876
0000-0001-9513-6864
0000-0002-3573-8203
OpenAccessLink http://journals.scholarsportal.info/openUrl.xqy?doi=10.2196/48808
PMID 37812468
PQID 2918508072
PQPubID 4997117
ParticipantIDs doaj_primary_oai_doaj_org_article_0c0c9ce78576474486693324942b0aa4
pubmedcentral_primary_oai_pubmedcentral_nih_gov_10594139
proquest_miscellaneous_2874834664
proquest_journals_2918508072
crossref_primary_10_2196_48808
crossref_citationtrail_10_2196_48808
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 20231009
PublicationDateYYYYMMDD 2023-10-09
PublicationDate_xml – month: 10
  year: 2023
  text: 20231009
  day: 9
PublicationDecade 2020
PublicationPlace Toronto
PublicationPlace_xml – name: Toronto
– name: Toronto, Canada
PublicationTitle JMIR medical informatics
PublicationYear 2023
Publisher JMIR Publications
Publisher_xml – name: JMIR Publications
References ref13
ref12
ref15
ref14
ref11
ref10
ref2
ref1
ref17
ref16
ref19
ref18
Balogh, EP (ref4) 2015
ref24
ref23
ref26
ref25
ref20
ref22
ref21
ref27
ref8
ref9
ref3
ref6
ref5
Greenes, R (ref7) 2014
References_xml – ident: ref8
  doi: 10.2196/35225
– ident: ref14
  doi: 10.1097/INF.0000000000003852
– ident: ref23
  doi: 10.1136/bcr-2017-223844
– ident: ref20
  doi: 10.1001/jama.2022.13735
– ident: ref6
  doi: 10.1371/journal.pone.0148991
– ident: ref25
  doi: 10.1111/opo.12131
– ident: ref27
  doi: 10.1515/dx-2023-0116
– ident: ref13
  doi: 10.1148/radiol.223312
– ident: ref9
  doi: 10.1370/afm.2908
– ident: ref1
  doi: 10.1515/dx-2013-0029
– ident: ref15
  doi: 10.1371/journal.pdig.0000198
– ident: ref11
  doi: 10.1056/nejmra2302038
– ident: ref19
  doi: 10.1016/j.amjmed.2023.02.011
– ident: ref3
  doi: 10.2147/ijgm.s96741
– year: 2015
  ident: ref4
  publication-title: Improving Diagnosis in Health Care
  doi: 10.17226/21794
– start-page: 49
  year: 2014
  ident: ref7
  publication-title: Clinical Decision Support (Second Edition)
  doi: 10.1016/B978-0-12-398476-0.00002-6
– ident: ref17
  doi: 10.1016/j.dsx.2023.102744
– ident: ref2
  doi: 10.1136/bmjqs-2022-015436
– ident: ref12
  doi: 10.1038/s41591-023-02289-5
– ident: ref26
  doi: 10.48550/arXiv.2212.00857
– ident: ref5
  doi: 10.2196/31810
– ident: ref18
  doi: 10.1056/nejmsr2214184
– ident: ref22
  doi: 10.3390/ijerph20043378
– ident: ref24
  doi: 10.1111/medu.13382
– ident: ref21
  doi: 10.1001/jama.2023.8288
– ident: ref10
  doi: 10.3390/healthcare10040608
– ident: ref16
  doi: 10.48550/arXiv.2303.08774
SSID ssj0001416667
Score 2.4840326
Snippet Background:The diagnostic accuracy of differential diagnoses generated by artificial intelligence chatbots, including ChatGPT models, for complex clinical...
The diagnostic accuracy of differential diagnoses generated by artificial intelligence chatbots, including ChatGPT models, for complex clinical vignettes...
BackgroundThe diagnostic accuracy of differential diagnoses generated by artificial intelligence chatbots, including ChatGPT models, for complex clinical...
SourceID doaj
pubmedcentral
proquest
crossref
SourceType Open Website
Open Access Repository
Aggregation Database
Enrichment Source
Index Database
StartPage e48808
SubjectTerms Accuracy
Artificial intelligence
Case reports
Chatbots
Multimedia
Original Paper
Patients
Physicians
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3LTtwwFLUqFgipQlCoOrxkJLYReXhihx0ML6G2YgEVu8i-NmWkUQYxMwgkFvwDf8iXcOxkRpNuumGZ-JHE91z53PjqXMb2srRIXCZdpHJ9GwlLIjKFzqLMuCTVCBBuTVD7_J2fX4uLm-7NXKkvnxNWywPXC7cfU0wFOalAjIVEMJHniMERNIjUxFoHJVDseXPBVPi7IvxxmFxkX32uM1C274GqWptP0OhvEct2WuTcPnO6wpYbgsgP6xdbZV9c9Y0t_mqOwNfYS-9Oj88ur6JaMBqEkR83RU7grANchNy5_oj_hAVHHKSUe6cfuCfew5b1_vp2DNQ9YlyjCTrgf_p_K5_yMzqYDsfD-SHR5EHTMz-ZKYKvs-vTk6veedSUUIioGyfjyGL1TCJJxs6aLDWJlVZKmwijbUwgO9akFgvlSDipuwUJIoKXU1eRUxRn39lCNazcD8aTXJOznk4IRDnGFAl6WA12jrmFVB22N13bkhp9cV_mYlAizvAmKIMJOmxn1u2-FtT4t8ORN8ys0etfhxtARdmgovwfKjpsa2rWsnHKUQlYKvDRWKYdtjtrhjv5MxJdueEEfZT0v1fzHFOoFhxaL9Ruqfp3QZjbc1WQgmLjMz5hky350vYhcbDYYgvjh4nbBgEam52A9Q8q1gbJ
  priority: 102
  providerName: Directory of Open Access Journals
– databaseName: Health & Medical Collection (ProQuest)
  dbid: 7X7
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LbxMxELagSBUSqigPNVAqI_VqdR_O2uaCSvoSAsShRbmt7LHbRoo2JZsgkDj0P_Qf9pcw4zgp20OPu37tembsb-zRN4ztloXJQ6mC0JU9F9KDFM7YUpQu5IVFB-HcRbbPb9XJmfw87A_TgVubwiqXa2JcqP0E6Ix8D_vUCCYyVXy8-ikoaxTdrqYUGo_ZE6Iuo5AuNVR3ZyySLsXUOntGEc-oa3ukrrqzBUWm_g687AZH_rfbHD1nGwkm8v2FXDfZo9C8YOtf00X4S_Z3cGlnx99PxYI2GmEjP0ipTtBkx_gQI-hGLf-Ccmw5QlNOpj8Ov_kAN67b65sD1L1f2C4xg475j9FFQ4E_7Ydlcxyc7wPMpxb-8MMVL_grdnZ0eDo4ESmRgoB-ls-EhwxcrkBlwbuycLlXXimfS2d9Bgh5vCs8TlQAGZTtG5AAgLYOfQ1BQ1a-ZmvNpAlbjOeVheAJVEj0dZwzOdbwFjE69i2V7rHd5dzWkFjGKdnFuEZvg0RQRxH02M6q2tWCVuN-hU8kmFUhsWDHF5PpRZ2Mqs7wvwwEpdFpkgodzaoyJSJEIwuXWSt7bHsp1jqZZlvfKVKPvV8Vo1HRTYltwmSOdbSiQ9aqwi50Rx06H9QtaUaXkZ6bECtCA_Pm4dHfsqeUuj4GBppttjabzsM7BDgztxO1-B-UIAAC
  priority: 102
  providerName: ProQuest
Title ChatGPT-Generated Differential Diagnosis Lists for Complex Case–Derived Clinical Vignettes: Diagnostic Accuracy Evaluation
URI https://www.proquest.com/docview/2918508072
https://www.proquest.com/docview/2874834664
https://pubmed.ncbi.nlm.nih.gov/PMC10594139
https://doaj.org/article/0c0c9ce78576474486693324942b0aa4
Volume 11
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwhV1taxQxEB5sC0UQ8RVP6xKhX6P7kttsBJH2erWILUV60m9LMknbg2VP70Va8IP_wX_oL3GSyx1dEfy4m2Q3ycxsnklmnwHYLXKVuUI6XpX6gguLghulC14Yl-WaHIQLE9g-T8qjkfh43r8VTRgncPZP187nkxpNm9fX327ek8G_82HMpEBvvA5WG7BFi5H0tnkcEX7YZhH-XMz_NJ1Tr7gqldiGe52WnRUpEPd30GY3VvLW4nP4AO5H1Mj2lmJ-CHdc-wi2j-O5-GP4MbjS8w-nZ3zJIk0okh3EzCdkwQ1dhIC68Yx9IrHOGCFV5r8EjbtmA1rHfv_8dUCq-J3aRaLQhn0ZX7Y-Dmj2dtWcXs72EBdTjTdsuKYJfwKjw-HZ4IjHvAoc-2k25xZTNJlEmTpritxkVlopbSaMtikSArImtzRpDoWTuq9QICKZPvYrdBWmxVPYbCetewYsKzU66zGGINfHGJVRDasJstOzhax6sLua2xoj6bjPfdHU5Hx4EdRBBD1I1tW-Llk2_q6w7wWzLvSk2OHGZHpZRxurUxqXQicr8qGEJL-zLFVBgFGJ3KRaix7srMRarxStJq2oCKSmMu_Bq3Ux2Zg_ONGtmyyoTiX9nmtZ0iOqjjp0OtQtacdXga3bA1hCCur5_8b4Au76XPYhUlDtwOZ8unAvCfHMTQIb8lwmsLU_PDn9nIR9gyTo-R_X6gYu
linkProvider Scholars Portal
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1fb9MwED-NThpIE-Kv6BjDSOMxWuK4cYKE0NZ2dKyrJtShvWX22dsqVeloWmASD3wHvgcfik_COU06wgNve0z8J4nv5_Pv7MsdwHbIk8CG0npxpM49YVB4OlGhF2obcEUGwrkuon0Oot6J-HDaOl2BX9W_MM6tstKJhaI2E3R75DvUZ0xkwpf83dVnz2WNcqerVQqNBSwO7fVXMtnytwcdku9rzve7w3bPK7MKeNjyg5ln0EcdSJS-NTrkOjDSSGkCoZXxkdZ_o7mJImlRWKlaCQpEJOBjK0Ybox9Sv3dgVYRkyjRgda87OP54s6sj3DGcXIN152NN6N5xEySuLXpFboAaoa27Y_61vu0_gPslMWW7CyQ9hBWbPYK1o_Lo_TF8b1-q2fvjobcIVE1ElXXK5CqkJMZ0UfjsjXLWJ-TkjMgwc8pmbL-xNi2Vv3_87BDav1C7MhbpmH0aXWTO1Sh_UzWnh7NdxPlU4TXrLiORP4GTWxnkp9DIJpl9BiyIFFrjaIwg60rrJKAaRpFVQH0LGTdhuxrbFMu45i69xjgl-8aJIC1E0IStZbWrRSCPfyvsOcEsC13c7eLGZHqRltM49em7ErQyJjNNSDJtoygJiZMmgmtfKdGEzUqsaakM8vQGuk14tSymaezOZlRmJ3OqE0u3rRtF1EVcg0Ptheol2eiyCAjuODKRkWTj_09_CXd7w6N-2j8YHD6He5zoWuGWmGxCYzad2xdEr2Z6q8Q0g7PbnkZ_AG3UQGk
linkToPdf http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1fb9MwED-NIVVIaOKv6DaGkcZj1MRx4gQJodGu29iY9rChvgX77G6VqnRrWmASD3wHvg0fh0_COU26hQfe9pj47CS-P_6dfbkD2A55GthQWi-J1dATBoWnUxV6obYBV-QgDHWZ7fM43j8THwfRYAV-1__CuLDK2iaWhtpM0O2Rd2jMhMCEL3lnWIVFnPT67y-vPFdByp201uU0FiJyaK-_kftWvDvoEa_fcN7fPe3ue1WFAQ8jP5h5Bn3UgUTpW6NDrgMjjZQmEFoZHwkLGM1NHEuLwkoVpSgQkZQAowRtgn5I496D-zKMAqdjciBv9neEO5CTLXjooq1JzjtOVZLG8ldWCWhA22Zg5q2Vrv8I1iqIynYWMvUYVmz-BFqfqkP4p_Cje6Fmeyen3iJlNUFW1qvKrJC5GNNFGb03KtgRyVDBCBYzZ3bG9jvr0qL55-evHsn9V-pXZSUds8-j89wFHRVv6-70cLaDOJ8qvGa7y5zkz-DsTqb4Oazmk9y-ABbECq1xgEaQn6V1GhCFUeQf0NhCJm3Yruc2wyrDuSu0Mc7I03EsyEoWtGFrSXa5SOnxL8EHx5hlo8vAXd6YTM-zSqEzn74rRSsTctiEJCc3jtOQ0GkquPaVEm3YrNmaVWahyG6EuA2vl82k0O6URuV2MieaRLoN3jimIZKGODReqNmSjy7K1OAOLRMsSdf___RX0CLlyY4Ojg834AEn3FbGJ6absDqbzu1LwlkzvVUKNIMvd61BfwFuKUM5
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-Generated+Differential+Diagnosis+Lists+for+Complex+Case%E2%80%93Derived+Clinical+Vignettes%3A+Diagnostic+Accuracy+Evaluation&rft.jtitle=JMIR+medical+informatics&rft.au=Hirosawa%2C+Takanobu&rft.au=Kawamura%2C+Ren&rft.au=Harada%2C+Yukinori&rft.au=Mizuta%2C+Kazuya&rft.date=2023-10-09&rft.issn=2291-9694&rft.eissn=2291-9694&rft.volume=11&rft.spage=e48808&rft_id=info:doi/10.2196%2F48808&rft.externalDBID=n%2Fa&rft.externalDocID=10_2196_48808
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2291-9694&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2291-9694&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2291-9694&client=summon