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

2026-04-10

AI Summary

This study addresses the limitations of initial outpatient consultations, which are often constrained by time pressure and cognitive biases, hindering the real-time, scalable deployment of traditional multidisciplinary teams (MDTs). To overcome this, the authors propose Aegle, a novel framework that virtualizes and synchronously integrates MDT mechanisms into outpatient settings. Aegle employs a graph-based multi-agent system that decouples evidence gathering from diagnostic reasoning within a structured SOAP representation. A dynamic coordinator activates specialty-specific agents on demand for parallel inference, while an aggregator synthesizes their outputs into a coherent clinical note. Evaluated on ClinicalBench and the real-world RAPID-IPN dataset—spanning 24 specialties and 53 clinical metrics—the approach demonstrates superior performance over state-of-the-art open- and closed-source models in diagnostic accuracy, consultation quality, and clinical documentation, while significantly enhancing diagnostic traceability and robustness against bias.

Technology Category

• Multiagent Systems: Modeling other Agents
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization

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.

Problem

• clinical intake
• cognitive bias
• multi-disciplinary team
• outpatient consultation
• evidence capture

Innovation

• multi-agent system
• clinical reasoning
• SOAP representation
• virtual MDT
• bias mitigation