1
Return

Artificial Intelligence vs Human Clinicians in Esophagogastroduodenoscopy Appropriateness: A Comparative Study Using Clinical Vignettes

delete2026-04-01
delete1
PRE
AI
M
Mantia, Beatrice *
R
Randazzo, Adelaide Maria
S
Schettino, Mario
D
De Lisi, Stefania
D
Dell'Era, Alessandra
S
Stefania Carmagnola
S
Salerno, Raffaele
DOI：10.14309/ajg.0000000000003837delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
INTRODUCTION:Large language models are increasingly used in clinical decision-making, but their role in appropriateness-based indications is uncertain.METHODS:We conducted a vignette-based Italian survey comparing esophagogastroduodenoscopy appropriateness by 5 artificial intelligence (AI) (ChatGPT-4.0, ChatGPT-4.5, Gemini, Claude AI, OpenEvidence) at 2 times (April and September 2025) with gastroenterologists, residents, and general practitioners, using American Society for Gastrointestinal Endoscopy and European Society of Gastrointestinal Endoscopy guidelines.RESULTS:A total of 135 physicians participated. AI performance varied over time: accuracies ranged from 50%-90% in April to 63%-80% in September, with ChatGPT-4.5 and ChatGPT-4.0 outperforming physicians in September.DISCUSSION:Temporal and prompt variability highlight the need for multirun, longitudinal evaluation before clinical adoption.
Keywords:
artificial intelligence (AI)
esophagogastroduodenoscopy prescriptions
clinical decision-making
clinical vignettes

Journal

American Journal of Gastroenterology cover
American Journal of Gastroenterology
IF:
7.6
Papers:
5.1W
Citations:
3.3W

Organization

U
University of Milan
Scholars:
5.0W
Papers: 3.9W
Citations: 5.0W
Cited Papers

Cited Papers

Citing Papers

Citing Papers