Comparative Evaluation of Large Language Models for Surgical Case Creation

Connie Gan

doi:10.1016/j.jsurg.2026.104034

Comparative Evaluation of Large Language Models for Surgical Case Creation

2026-06-27

0

PRE

AI

C

Connie Gan *

M

Megan Chan

N

Nitasha Sharma

S

Simeng Wang

L

Lisa Flynn

E

Edward F. Melcer

C

Cara A. Liebert

D

Dana T. Lin

A

Andrea S. Parker

M

Malerie Pratt

DOI：10.1016/j.jsurg.2026.104034

Original

Original request for help

Save

Abstract

En 中文

• Five large language models were compared for surgical education case creation. • Evaluated with modified HumanELY framework, Claude produced highest quality cases. • Claude outputs required the least editing to create usable cases. • Large language model outputs differed in relevance, coherence, and usability.

Comparative Evaluation of Large Language Models for Surgical Case Creation

Abstract

Journal

Organization