0

AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator

A multi-agent framework simulates clinical interactions to evaluate large language models' performance in medical diagnostics, highlighting the need for improvements in multi-turn interactions.

Year
2024
Venue
arXiv 2024
Authors
8
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2402.09742v4ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

Artificial intelligence has significantly advanced healthcare, particularly through large language models (LLMs) that excel in medical question answering benchmarks. However, their real-world clinical application remains limited due to the complexities of doctor-patient interactions. To address this, we introduce \textbf{AI Hospital}, a multi-agent framework simulating dynamic medical interactions between \emph{Doctor} as player and NPCs including \emph{Patient}, \emph{Examiner}, \emph{Chief Physician}. This setup allows for realistic assessments of LLMs in clinical scenarios. We develop the Multi-View Medical Evaluation (MVME) benchmark, utilizing high-quality Chinese medical records and NPCs to evaluate LLMs' performance in symptom collection, examination recommendations, and diagnoses. Additionally, a dispute resolution collaborative mechanism is proposed to enhance diagnostic accuracy through iterative discussions. Despite improvements, current LLMs exhibit significant performance gaps in multi-turn interactions compared to one-step approaches. Our findings highlight the need for further research to bridge these gaps and improve LLMs' clinical diagnostic capabilities. Our data, code, and experimental results are all open-sourced at \url{https://github.com/LibertFan/AI_Hospital}.

Authors

8