CDR-Agent: Intelligent Selection and Execution of Clinical Decision Rules Using Large Language Model Agents

TL;DR

CDR-Agent leverages large language models to autonomously identify and apply appropriate clinical decision rules in emergency departments, improving decision accuracy and efficiency while reducing cognitive load and unnecessary interventions.

Contribution

This paper introduces CDR-Agent, a novel LLM-based system that automates clinical decision rule selection, demonstrating significant accuracy gains and efficiency improvements over baseline methods.

Findings

Achieves 56.3% accuracy gain on synthetic dataset

Reduces computational overhead compared to baseline

Outperforms traditional LLM prompting in CDR selection

Abstract

Clinical decision-making is inherently complex and fast-paced, particularly in emergency departments (EDs) where critical, rapid and high-stakes decisions are made. Clinical Decision Rules (CDRs) are standardized evidence-based tools that combine signs, symptoms, and clinical variables into decision trees to make consistent and accurate diagnoses. CDR usage is often hindered by the clinician's cognitive load, limiting their ability to quickly recall and apply the appropriate rules. We introduce CDR-Agent, a novel LLM-based system designed to enhance ED decision-making by autonomously identifying and applying the most appropriate CDRs based on unstructured clinical notes. To validate CDR-Agent, we curated two novel ED datasets: synthetic and CDR-Bench, although CDR-Agent is applicable to non ED clinics. CDR-Agent achieves a 56.3\% (synthetic) and 8.7\% (CDR-Bench) accuracy gain relative to the standalone LLM baseline in CDR selection. Moreover, CDR-Agent significantly reduces computational overhead. Using these datasets, we demonstrated that CDR-Agent not only selects relevant CDRs efficiently, but makes cautious yet effective imaging decisions by minimizing unnecessary interventions while successfully identifying most positively diagnosed cases, outperforming traditional LLM prompting approaches. Code for our work can be found at: https://github.com/zhenxianglance/medagent-cdr-agent