Valutazione comparativa di modelli linguistici di grandi dimensioni per il supporto all’educazione sanitaria del paziente con BPCO: uno studio pneumologico internazionale delle risposte generate da ChatGPT-4, Claude 3.5 Sonnet e Gemini 1.5 Advanced.

Abstract

Three LLMs - ChatGPT-4, Claude 3.5 Sonnet and Gemini 1.5 Advanced - were evaluated on COPD questions from the GOLD recommendations. Sixty-one pulmonologists from 6 continents rated 90 AI responses for completeness, accuracy, terminology, accessibility, and safety. Gemini outperformed in completeness, Claude in accuracy and terminology, with no differences in accessibility or safety. While promising, clinical use requires caution and further validation to ensure safe, accurate patient education.