Multi-Agent Approach for Sepsis Management

Abstract

Objectives: The high incidence of sepsis necessitates the development of practical decision-making tools for intensivists,especially during the early, critical phases of management. This study evaluates a multi-agent system intended to assist clinicianswith antibiotic therapy and adherence to current sepsis management guidelines before diagnostic results become available. Methods: A multi-agent system incorporating three specialized agents was developed: a sepsis management agent, anantibiotic recommendation agent, and a sepsis guidelines compliance agent. A sepsis case from the MIMIC IV database, organizedas a clinical vignette, was used to integrate and test these agents for generating management recommendations. Thesystem leverages retrieval-augmented generation to improve decision-making through the integration of current literatureand guidelines. Results: The application produced management recommendations for a sepsis case associated with pneumonia,including early initiation of broad-spectrum antibiotics and close monitoring for clinical deterioration. Two expertintensivists evaluated these recommendations as “acceptable” and reported moderate interrater agreement (Cohen’s kappa =0.622, p = 0.003) across various aspects of recommendation usefulness. Conclusions: The multi-agent system shows promisein enhancing decision-making for sepsis management by optimizing antibiotic therapy and ensuring guideline compliance. However, reliance on a single case study limits the generalizability of the findings, highlighting the need for broader validationin diverse clinical settings to improve patient outcomes.