Automated Clinical Problem Detection from SOAP Notes using a Collaborative Multi-Agent LLM Architecture
By: Yeawon Lee, Xiaoyang Wang, Christopher C. Yang
Potential Business Impact:
Helps doctors find sickness faster by teamwork.
Accurate interpretation of clinical narratives is critical for patient care, but the complexity of these notes makes automation challenging. While Large Language Models (LLMs) show promise, single-model approaches can lack the robustness required for high-stakes clinical tasks. We introduce a collaborative multi-agent system (MAS) that models a clinical consultation team to address this gap. The system is tasked with identifying clinical problems by analyzing only the Subjective (S) and Objective (O) sections of SOAP notes, simulating the diagnostic reasoning process of synthesizing raw data into an assessment. A Manager agent orchestrates a dynamically assigned team of specialist agents who engage in a hierarchical, iterative debate to reach a consensus. We evaluated our MAS against a single-agent baseline on a curated dataset of 420 MIMIC-III notes. The dynamic multi-agent configuration demonstrated consistently improved performance in identifying congestive heart failure, acute kidney injury, and sepsis. Qualitative analysis of the agent debates reveals that this structure effectively surfaces and weighs conflicting evidence, though it can occasionally be susceptible to groupthink. By modeling a clinical team's reasoning process, our system offers a promising path toward more accurate, robust, and interpretable clinical decision support tools.
Similar Papers
Multi-agent Self-triage System with Medical Flowcharts
Artificial Intelligence
Helps AI give safe health advice like a doctor.
Enhancing Clinical Decision-Making: Integrating Multi-Agent Systems with Ethical AI Governance
Artificial Intelligence
Helps doctors predict patient health better.
MedAgentAudit: Diagnosing and Quantifying Collaborative Failure Modes in Medical Multi-Agent Systems
Computation and Language
Checks if AI doctors explain their thinking.