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

Heart failure (HF) is a leading cause of rehospitalization. This paper proposes ClinNoteAgents, an LLM multi-agent system to predict and interpret heart failure 30-day readmission from clinical notes, which are often underutilized despite containing rich patient information. Traditional models rely on expert-crafted rules, but ClinNoteAgents aims to leverage LLMs for improved analysis of messy, jargon-filled clinical text.