ColaCare: Enhancing Electronic Health Record Modeling through Large Language Model-Driven Multi-Agent Collaboration

2024-10-03

arXiv.org

AI Summary

Existing EHR modeling approaches suffer from a disconnect between structured data and clinical text reasoning, hindering accurate simulation of multidisciplinary clinical decision-making. Method: We propose DoctorAgent-MetaAgent, a multi-agent collaborative framework inspired by Multidisciplinary Team (MDT) consultation. It integrates domain-specific clinical expert models with large language models to generate temporally aware EHR representations, and incorporates a Retrieval-Augmented Generation (RAG) module grounded in the MSD Manual to ensure authoritative, up-to-date medical knowledge. The method jointly leverages temporal EHR modeling, multi-agent coordination, and retrieval-augmented generation. Results: Evaluated on three real-world EHR datasets, our framework achieves 3.2–5.8% absolute AUC improvements in mortality and readmission prediction over state-of-the-art single-model and baseline multi-agent methods. This work is the first to formalize the clinical MDT process as a computationally tractable multi-agent paradigm, offering a novel pathway toward interpretable, auditable, and clinically grounded decision support.

Technology Category

• Multiagent Systems: Modeling other Agents
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

We introduce ColaCare, a framework that enhances Electronic Health Record (EHR) modeling through multi-agent collaboration driven by Large Language Models (LLMs). Our approach seamlessly integrates domain-specific expert models with LLMs to bridge the gap between structured EHR data and text-based reasoning. Inspired by the Multidisciplinary Team (MDT) approach used in clinical settings, ColaCare employs two types of agents: DoctorAgents and a MetaAgent, which collaboratively analyze patient data. Expert models process and generate predictions from numerical EHR data, while LLM agents produce reasoning references and decision-making reports within the MDT-driven collaborative consultation framework. The MetaAgent orchestrates the discussion, facilitating consultations and evidence-based debates among DoctorAgents, simulating diverse expertise in clinical decision-making. We additionally incorporate the Merck Manual of Diagnosis and Therapy (MSD) medical guideline within a retrieval-augmented generation (RAG) module for medical evidence support, addressing the challenge of knowledge currency. Extensive experiments conducted on three EHR datasets demonstrate ColaCare's superior performance in clinical mortality outcome and readmission prediction tasks, underscoring its potential to revolutionize clinical decision support systems and advance personalized precision medicine. All code, case studies and a questionnaire are available at the project website: https://colacare.netlify.app.

Problem

• Enhancing EHR modeling
• Multi-agent collaboration
• Clinical decision support

Innovation

• Multi-agent collaboration with LLMs
• Domain-specific expert models integration
• Retrieval-augmented generation for medical evidence