Beyond the Individual: Virtualizing Multi-Disciplinary Reasoning for Clinical Intake via Collaborative Agents

TL;DR

Aegle is a virtual multi-disciplinary team framework that enhances outpatient clinical consultations by integrating specialist reasoning through a graph-based multi-agent system, improving diagnosis accuracy and documentation quality.

Contribution

It introduces a structured, multi-agent architecture for real-time clinical reasoning that formalizes evidence collection and diagnostic processes, outperforming existing models.

Findings

Outperforms state-of-the-art models in documentation quality.

Improves diagnosis accuracy across multiple departments.

Demonstrates scalability and effectiveness on real-world datasets.

Abstract

The initial outpatient consultation is critical for clinical decision-making, yet it is often conducted by a single physician under time pressure, making it prone to cognitive biases and incomplete evidence capture. Although the Multi-Disciplinary Team (MDT) reduces these risks, they are costly and difficult to scale to real-time intake. We propose Aegle, a synchronous virtual MDT framework that brings MDT-level reasoning to outpatient consultations via a graph-based multi-agent architecture. Aegle formalizes the consultation state using a structured SOAP representation, separating evidence collection from diagnostic reasoning to improve traceability and bias control. An orchestrator dynamically activates specialist agents, which perform decoupled parallel reasoning and are subsequently integrated by an aggregator into a coherent clinical note. Experiments on ClinicalBench and a real-world RAPID-IPN dataset across 24 departments and 53 metrics show that Aegle consistently outperforms state-of-the-art proprietary and open-source models in documentation quality and consultation capability, while also improving final diagnosis accuracy. Our code is available at https://github.com/HovChen/Aegle.