This paper is in the following e-collection/theme issue:

Theme Issue: ChatGPT and Generative Language Models in Medical Education (98) Generative Language Models Including ChatGPT (476) Artificial Intelligence (AI) in Medical Education (120) Clinical Information and Decision Making (1627) Clinical Informatics (1147) Computer-Aided Diagnosis (179) Decision Support for Health Professionals (1328) Chatbots and Conversational Agents (621) Validity, Reliability, and Bias (103)

Published on in Vol 9 (2023)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/47532, first published .
The Accuracy and Potential Racial and Ethnic Biases of GPT-4 in the Diagnosis and Triage of Health Conditions: Evaluation Study

The Accuracy and Potential Racial and Ethnic Biases of GPT-4 in the Diagnosis and Triage of Health Conditions: Evaluation Study

The Accuracy and Potential Racial and Ethnic Biases of GPT-4 in the Diagnosis and Triage of Health Conditions: Evaluation Study

Authors of this article:

Naoki Ito1, 2 Author Orcid Image ;   Sakina Kadomatsu1, 3 Author Orcid Image ;   Mineto Fujisawa1, 2 Author Orcid Image ;   Kiyomitsu Fukaguchi1, 4 Author Orcid Image ;   Ryo Ishizawa1, 5 Author Orcid Image ;   Naoki Kanda1, 6 Author Orcid Image ;   Daisuke Kasugai1, 7 Author Orcid Image ;   Mikio Nakajima1, 8 Author Orcid Image ;   Tadahiro Goto1 Author Orcid Image ;   Yusuke Tsugawa9, 10 Author Orcid Image
Article Authors Cited by (28) Tweetations (15) Metrics
All Time | Last Month | Last Six Months | Last Year
JMIR Publications JMIR Publications @jmirpub

New in JMIR MedEdu: The Accuracy and Potential Racial and Ethnic Biases of GPT-4 in the Diagnosis and Triage of Health Conditions: Evaluation Study https://t.co/hQwpWCxkv8 https://t.co/1Df0MS0Q89

2:23 PM · Nov 02, 2023

1
2
JMIR Medical Education JMIR Medical Education @JMIR_MedicalEd

RT @jmirpub: New in JMIR MedEdu: The Accuracy and Potential Racial and Ethnic Biases of GPT-4 in the Diagnosis and Triage of Health Conditi…

2:23 PM · Nov 02, 2023

1
2
SBMDigitalHealth SBMDigitalHealth @SBMDigitalHlth

RT @jmirpub: New in JMIR MedEdu: The Accuracy and Potential Racial and Ethnic Biases of GPT-4 in the Diagnosis and Triage of Health Conditi…

4:10 PM · Nov 02, 2023

1
2
Dr Andrew O'Malley Dr Andrew O'Malley @OMalleyFife

JMIR Medical Education - The Accuracy and Potential Racial and Ethnic Biases of GPT-4 in the Diagnosis and Triage of Health Conditions: Evaluation Study https://t.co/nO7gOTxE5g

9:28 AM · Nov 07, 2023

0
0
Medical Xpress Medical Xpress @medical_xpress

#AI model can accurately diagnose and triage #health conditions, without introducing racial and ethnic biases https://t.co/q9ps7fMifu https://t.co/9JkPm7aKz1

3:37 PM · Nov 09, 2023

3
3
john morley john morley @drjohnmorley

Check out this fascinating article https://t.co/ieTxcdW9WE

3:40 PM · Nov 09, 2023

0
0
Yusuke Tsugawa Yusuke Tsugawa @Yusuke_Tsugawa

Our new study published in JMIR Med Educ found that GPT-4 perform as well as board-certified physicians (n=3) in making medical diagnosis, without introducing racial and ethnic bias. @UCLAGIM @DOM_UCLA https://t.co/TlvGRy3BbE https://t.co/BwqYEjPEoG

10:28 PM · Nov 10, 2023

8
1
てとら てとら @Mimi36404195

RT @Yusuke_Tsugawa: Our new study published in JMIR Med Educ found that GPT-4 perform as well as board-certified physicians (n=3) in making…

2:17 AM · Nov 11, 2023

8
1
NP AGARWAL世界一フォローを目指しますAiming best in world. NP AGARWAL世界一フォローを目指しますAiming best in world. @np_grwl

RT @medical_xpress: #AI model can accurately diagnose and triage #health conditions, without introducing racial and ethnic biases https://t…

8:59 AM · Nov 11, 2023

3
3
April Capellan, RHIT, CCS April Capellan, RHIT, CCS @aprilcapellan

“GPT-4’s (AI’s) ability to diagnose and triage typical clinical vignettes was comparable to that of board-certified physicians.” https://t.co/KKpekh1MT5

11:16 PM · Nov 17, 2023

0
0
Gerry McGivern Gerry McGivern @GerryMcGivern

'GPT-4’s ability to diagnose & triage typical clinical vignettes was comparable to that of board-certified physicians. The performance of GPT-4 did not vary by patient race & ethnicity' https://t.co/nqFu8DNFJT

4:54 PM · Nov 28, 2023

1
0
William Viney William Viney @WillViney

AI healthcare can produce 'diagnosis' as a computational event – delightful to evaluators – and this departs from diagnosis as a process along a clinical pathway involving multple decisions, corrections, revisions etc. https://t.co/D2dytWHiiy

5:21 PM · Nov 28, 2023

1
2
Livia Garofalo Livia Garofalo @livgar_

RT @WillViney: AI healthcare can produce 'diagnosis' as a computational event – delightful to evaluators – and this departs from diagnosis…

6:12 PM · Nov 28, 2023

1
2
HeLEX Oxford HeLEX Oxford @HeLEXOxford

RT @WillViney: AI healthcare can produce 'diagnosis' as a computational event – delightful to evaluators – and this departs from diagnosis…

6:49 PM · Nov 28, 2023

1
2
大角知也,MBA|ヘルスケアイノベーター 大角知也,MBA|ヘルスケアイノベーター @tomoyaookado

The Accuracy and Potential Racial and Ethnic Biases of GPT-4 in the Diagnosis and Triage of Health Conditions: Evaluation Study https://t.co/KpJyxCWDGT https://t.co/IcIGbRuoMZ

4:06 PM · Dec 12, 2023

0
0
Yasutaka Yanagita | MD, PhD Yasutaka Yanagita | MD, PhD @1009yasutaka

トリアージはGPT-4と医師で同等。 GPT-4は97％で医師は91.1%の精度。 The Accuracy and Potential Racial and Ethnic Biases of GPT-4 in the Diagnosis and Triage of Health Conditions: Eval… https://t.co/dagXv6UHnt

1:42 PM · Dec 31, 2023

0
0