Performance of large language model artificial intelligence on dermatology board exam questions

被引：3

作者：

Park, Lily ^{[1
,2
]}

Ehlert, Brittany ^{[3
]}

Susla, Lyudmyla ^{[4
]}

Lum, Zachary C. ^{[2
]}

Lee, Patrick K. ^{[5
]}

机构：

[1] Larkin Community Hosp, Dept Dermatol, South Miami, FL 33143 USA

[2] Nova Southeastern Univ, Sch Osteopath Med, Davie, FL 33328 USA

[3] Ohio Univ, Heritage Coll Osteopath Med, Cleveland, OH USA

[4] New York Inst Technol, Coll Osteopath Med, Old Westbury, NY USA

[5] Univ Calif Irvine, Dept Dermatol, Irvine, CA USA

来源：

CLINICAL AND EXPERIMENTAL DERMATOLOGY | 2023年 / 49卷 / 07期

关键词：

D O I：

10.1093/ced/llad355

中图分类号：

R75 [皮肤病学与性病学];

学科分类号：

100206 ;

摘要：

Our study attempted to assess the performance of two large language models: Open AI's ChatGPT and Google's Bard on dermatology board exam-style questions. Based on our study, Google Bard outperformed ChatGPT and achieved the highest scores in general dermatology among dermatology disciplines.

引用

页码：733 / 734

页数：2

共 6 条

[1]

[Anonymous], 2023, Google Bard

[2]

Galderma, DERM101 SELF ASS QUI

[3] AI-Generated Medical Advice-GPT and Beyond [J].

Haupt, Claudia E. ;

Marks, Mason .

JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 2023, 329 (16) :1349-1350

[4] Comparative Evaluation of Diagnostic Accuracy Between Google Bard and Physicians [J].

Hirosawa, Takanobu ;

Mizuta, Kazuya ;

Harada, Yukinori ;

Shimizu, Taro .

AMERICAN JOURNAL OF MEDICINE, 2023, 136 (11) :1119-+

[5]

Open AI, 2022, CHATGPT 3 5

[6]

Sanovaworks, DERM IN REV DASHB

← 1 →