A systematic evaluation of the performance of GPT‐4 and PaLM2 to diagnose comorbidities in MIMIC‐IV patients

• Autori principali: Peter Sarvari (Autore), Zaid Al‐fagih (Autore), Abdullatif Ghuwel (Autore), Othman Al‐fagih (Autore)
• Natura: Libro
• Pubblicazione: Wiley, 2024-02-01T00:00:00Z.
• Soggetti: article
• Accesso online: Connect to this object online.

Abstract Background Given the strikingly high diagnostic error rate in hospitals, and the recent development of Large Language Models (LLMs), we set out to measure the diagnostic sensitivity of two popular LLMs: GPT‐4 and PaLM2. Small‐scale studies to evaluate the diagnostic ability of LLMs have sho...