ClinNoteAgents: An LLM Multi-Agent System for Predicting and Interpreting Heart Failure 30-Day Readmission from Clinical Notes

TL;DR

ClinNoteAgents is presented, an LLM-based multi-agent framework that transforms free-text clinical notes into structured representations of clinical and social risk factors for association analysis and clinician-style abstractions for HF 30-day readmission prediction.

Abstract

Heart failure (HF) is one of the leading causes of rehospitalization among older adults in the United States. Although clinical notes contain rich, detailed patient information and make up a large portion of electronic health records (EHRs), they remain underutilized for HF readmission risk analysis. Traditional computational models for HF readmission often rely on expert-crafted rules, medical thesauri, and ontologies to interpret clinical notes, which are typically written under time pressure and may contain misspellings, abbreviations, and domain-specific jargon. We present ClinNoteAgents, an LLM-based multi-agent framework that transforms free-text clinical notes into (1) structured representations of clinical and social risk factors for association analysis and (2) clinician-style abstractions for HF 30-day readmission prediction. We evaluate ClinNoteAgents on 3,544 notes from 2,065 patients (readmission rate=35.16%), demonstrating strong performance in extracting risk factors from free-text, identifying key contributing factors, and predicting readmission risk. By reducing reliance on structured fields and minimizing manual annotation and model training, ClinNoteAgents provides a scalable and interpretable approach to note-based HF readmission risk modeling in data-limited healthcare systems.

Figures (2)

• Figure 1: Overview of the ClinNoteAgents system for comprehensive clinical note analytics.
• Figure 2: HF 30-day readmission classification performance across summarization methods and model types.