TriAgent: Automated Biomarker Discovery with Deep Research Grounding for Triage in Acute Care by LLM-Based Multi-Agent Collaboration

2025-10-17

AI Summary

To address insufficient biomarker discovery, poor decision interpretability, and fragmentation between clinical and literature knowledge in emergency triage, this study proposes a large language model–driven multi-agent collaboration framework. A supervised research agent orchestrates specialized sub-agents to jointly perform clinical data–driven candidate biomarker identification, cross-source literature evidence retrieval, knowledge fusion–based validation, and novelty assessment. The method integrates quantitative analysis with qualitative reasoning, supporting task decomposition, confidence scoring, and provenance tracing. Evaluated on real-world clinical queries and triage data, the framework achieves a topic coherence F1-score of 55.7±5.0%—exceeding baseline methods by over 10%—and a faithfulness score of 0.42±0.39, outperforming comparative approaches by more than 50%. It demonstrates superior performance in biomarker interpretability and novelty identification.

Technology Category

• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust
• Multiagent Systems: Modeling other Agents
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Emergency departments worldwide face rising patient volumes, workforce shortages, and variability in triage decisions that threaten the delivery of timely and accurate care. Current triage methods rely primarily on vital signs, routine laboratory values, and clinicians' judgment, which, while effective, often miss emerging biological signals that could improve risk prediction for infection typing or antibiotic administration in acute conditions. To address this challenge, we introduce TriAgent, a large language model (LLM)-based multi-agent framework that couples automated biomarker discovery with deep research for literature-grounded validation and novelty assessment. TriAgent employs a supervisor research agent to generate research topics and delegate targeted queries to specialized sub-agents for evidence retrieval from various data sources. Findings are synthesized to classify biomarkers as either grounded in existing knowledge or flagged as novel candidates, offering transparent justification and highlighting unexplored pathways in acute care risk stratification. Unlike prior frameworks limited to existing routine clinical biomarkers, TriAgent aims to deliver an end-to-end framework from data analysis to literature grounding to improve transparency, explainability and expand the frontier of potentially actionable clinical biomarkers. Given a user's clinical query and quantitative triage data, TriAgent achieved a topic adherence F1 score of 55.7 +/- 5.0%, surpassing the CoT-ReAct agent by over 10%, and a faithfulness score of 0.42 +/- 0.39, exceeding all baselines by more than 50%. Across experiments, TriAgent consistently outperformed state-of-the-art LLM-based agentic frameworks in biomarker justification and literature-grounded novelty assessment. We share our repo: https://github.com/CellFace/TriAgent.

Problem

• Automating biomarker discovery for acute care triage
• Addressing limitations in current clinical risk prediction methods
• Validating biomarkers through literature-grounded novelty assessment

Innovation

• LLM-based multi-agent framework for automated biomarker discovery
• Supervisor agent delegates queries for literature-grounded validation
• Synthesizes findings to classify biomarkers as known or novel