Enhancing diagnostic capability with multi-agents conversational large language models

Large Language Models (LLMs) show promise in healthcare tasks but face challenges in complex medical scenarios. We developed a Multi-Agent Conversation (MAC) framework for disease diagnosis, inspired by clinical Multi-Disciplinary Team discussions. Using 302 rare disease cases, we evaluated GPT-3.5, GPT-4, and MAC on medical knowledge and clinical reasoning. MAC outperformed single models in both primary and follow-up consultations, achieving higher accuracy in diagnoses and suggested tests. Optimal performance was achieved with four doctor agents and a supervisor agent, using GPT-4 as the base model. MAC demonstrated high consistency across repeated runs. Further comparative analysis showed MAC also outperformed other methods including Chain of Thoughts (CoT), Self-Refine, and Self-Consistency with higher performance and more output tokens. This framework significantly enhanced LLMs' diagnostic capabilities, effectively bridging theoretical knowledge and practical clinical application. Our findings highlight the potential of multi-agent LLMs in healthcare and suggest further research into their clinical implementation.

Authors

Institutions

Publication Details

Journal
npj Digital Medicine
Published
2025-03-13
DOI
https://doi.org/10.1038/s41746-025-01550-0
Citations
54
Primary Topic
Topic Modeling
Type
article
Field-Weighted Citation Impact
133.97
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Enhancing diagnostic capability with multi-agents conversational large language models

Mingke You, Qicheng Lao, Weili Fu, Hairui Li et al.
54 citations
npj Digital Medicine
Topic Modeling
133.97
article

Enhancing diagnostic capability with multi-agents conversational large language models

Mingke You, Qicheng Lao, Weili Fu, Hairui Li, Lei Fan, Huahui Yi, Xi Chen, Wang Li, Xue Zhang, Kang Li, Gang Chen, Yingman Guo, Jian Li, Weizhi Liu
article en
54 citations

Abstract

Large Language Models (LLMs) show promise in healthcare tasks but face challenges in complex medical scenarios. We developed a Multi-Agent Conversation (MAC) framework for disease diagnosis, inspired by clinical Multi-Disciplinary Team discussions. Using 302 rare disease cases, we evaluated GPT-3.5, GPT-4, and MAC on medical knowledge and clinical reasoning. MAC outperformed single models in both primary and follow-up consultations, achieving higher accuracy in diagnoses and suggested tests. Optimal performance was achieved with four doctor agents and a supervisor agent, using GPT-4 as the base model. MAC demonstrated high consistency across repeated runs. Further comparative analysis showed MAC also outperformed other methods including Chain of Thoughts (CoT), Self-Refine, and Self-Consistency with higher performance and more output tokens. This framework significantly enhanced LLMs' diagnostic capabilities, effectively bridging theoretical knowledge and practical clinical application. Our findings highlight the potential of multi-agent LLMs in healthcare and suggest further research into their clinical implementation.

npj Digital MedicineVol. 8(1)
Beijing University of Posts and Telecommunications (CN), Sichuan University (CN), West China Medical Center of Sichuan University (CN), West China Hospital of Sichuan University (CN), Beijing Academy of Artificial Intelligence (CN), Shanghai Artificial Intelligence Laboratory (CN), Zhejiang University (CN)
Quality Education
Openalex Percentile: Top 0%
Topic Modeling
133.97
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.