Traj-CoA: Patient Trajectory Modeling via Chain-of-Agents for Lung Cancer Risk Prediction

2025-10-12

AI Summary

Longitudinal electronic health record (EHR) data pose significant challenges for long-term lung cancer risk prediction due to their extended temporal span and high noise levels. To address this, we propose a patient trajectory modeling framework based on a multi-agent chain. The framework comprises a collaborative worker-agent chain, a memory module (EHRMem) with temporal summarization capability, and a manager agent responsible for global reasoning—enabling key clinical event extraction, noise suppression, and interpretable long-term inference. Our approach integrates large language models, chain-of-thought reasoning, zero-shot learning, and a shared memory mechanism, requiring no fine-tuning to process five-year EHR sequences. In zero-shot one-year lung cancer risk prediction, our method significantly outperforms four baseline models, demonstrating superior robustness and strong cross-institutional generalization. This work establishes a novel paradigm for clinically trustworthy temporal modeling of EHRs.

Technology Category

• Multiagent Systems: Modeling other Agents
• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Large language models (LLMs) offer a generalizable approach for modeling patient trajectories, but suffer from the long and noisy nature of electronic health records (EHR) data in temporal reasoning. To address these challenges, we introduce Traj-CoA, a multi-agent system involving chain-of-agents for patient trajectory modeling. Traj-CoA employs a chain of worker agents to process EHR data in manageable chunks sequentially, distilling critical events into a shared long-term memory module, EHRMem, to reduce noise and preserve a comprehensive timeline. A final manager agent synthesizes the worker agents' summary and the extracted timeline in EHRMem to make predictions. In a zero-shot one-year lung cancer risk prediction task based on five-year EHR data, Traj-CoA outperforms baselines of four categories. Analysis reveals that Traj-CoA exhibits clinically aligned temporal reasoning, establishing it as a promisingly robust and generalizable approach for modeling complex patient trajectories.

Problem

• Modeling long noisy EHR data for patient trajectories
• Improving temporal reasoning in lung cancer risk prediction
• Addressing data fragmentation in electronic health records

Innovation

• Multi-agent system processes EHR data sequentially
• Worker agents distill events into shared memory module
• Manager agent synthesizes summaries for final predictions