Large Language Models in Emergency Medicine: A Critical Appraisal of Validity, Reproducibility, and Clinical Utility (2020-2025)

Eurasian Journal of Emergency Medicine 2026 Open access

Read full text
Authors: Ahmet Aykut, Cem Yıldırım, Ertuğ Günsoy
DOI: 10.4274/eajem.galenos.2025.28412
Cited by: 2

Abstract

Despite these well-described failure modes, published LLM evaluations in medicine, including those appearing in core EM journals, frequently omit core methodological details.Model/ version identifiers, release dates, full prompt templates, and data provenance are inconsistently reported; synthetic prompts, exam-

Fields of Study & Subjects

Artificial Intelligence in Healthcare and Education Genomics and Rare Diseases Topic Modeling

Publication details

Journal / source
Eurasian Journal of Emergency Medicine
Publisher
Galenos Yayinevi
Volume
25
Issue
1
Pages
117–124
Publication date
27 January 2026
Language
EN