A Multi-Agent AI System for Collaborative Differential Diagnosis of Complex Clinical Cases
9/17/2025 • The Lancet Digital Health • License: CC BY
Rajkomar, A.
Abstract
We developed a collaborative multi-agent AI system where individual 'specialist' agents (e.g., Cardiology AI, Pulmonology AI) analyze patient data and then debate and reason together to arrive at a differential diagnosis. When tested on 500 complex diagnostic cases from the New England Journal of Medicine, the multi-agent system's top-3 diagnostic accuracy was 91.2%, a 15.1 percentage point improvement over a single, monolithic AI model.
Source: View original
Clinical implications
A new AI system mimics a consultation between medical specialists. Different AI 'agents' with specific expertise work together to diagnose difficult cases. This collaborative approach made the AI significantly more accurate at diagnosing complex medical problems.
This product uses publicly available data from the U.S. National Library of Medicine (NLM),
National Institutes of Health, Department of Health and Human Services; NLM is not responsible
for the product and does not endorse or recommend this or any other product.
Links to third-party publications are provided for research discovery.