Assessing the Accuracy of Large Language Models on European Guidelines for Cervical Cancer: An In Silico Benchmarking Study.

Date publication

novembre 2025

Journal

BJOG : an international journal of obstetrics and gynaecology

Auteurs

Membres identifiés du Cancéropôle Est :
Pr MARESCAUX Jacques

Tous les auteurs :
Pavone M, Innocenzi C, Macellari N, Cantarini C, Criscione M, Rosati A, Lecointre L, Carcagnì A, Costantini B, Marescaux J, Fagotti A, Fanfani F, Cibula D, Querleu D, Bizzarri N

Lien Pubmed

https://www.ncbi.nlm.nih.gov/pubmed/41287196

Résumé

Although large language models are increasingly used in clinical and research settings, the validity of the information they provide remains uncertain. This study aimed to evaluate the accuracy, consistency, and reliability of three large language models-ChatGPT 4.0, DeepSeek R1, and Gemini 2.0-in answering cervical cancer-related questions based on the ESGO/ESTRO/ESP guidelines.

Mots clés

artificial intelligence, cervical cancer, chatgpt, deepseek, digital surgery, gemini, large language models

Référence

BJOG. 2025 11 24;: