MEDDxAgent: A Unified Modular Agent Framework for Explainable Automatic Differential Diagnosis

TL;DR

MEDDxAgent is a modular, explainable framework for interactive differential diagnosis that improves accuracy and reasoning transparency by iteratively refining diagnoses without assuming complete patient data.

Contribution

The paper introduces MEDDxAgent, a novel modular framework for interactive DDx that emphasizes iterative reasoning and explainability, addressing limitations of prior single-attempt models.

Findings

Over 10% accuracy improvement in interactive DDx

Effective integration of modular components for reasoning

Enhanced explainability of diagnostic process

Abstract

Differential Diagnosis (DDx) is a fundamental yet complex aspect of clinical decision-making, in which physicians iteratively refine a ranked list of possible diseases based on symptoms, antecedents, and medical knowledge. While recent advances in large language models (LLMs) have shown promise in supporting DDx, existing approaches face key limitations, including single-dataset evaluations, isolated optimization of components, unrealistic assumptions about complete patient profiles, and single-attempt diagnosis. We introduce a Modular Explainable DDx Agent (MEDDxAgent) framework designed for interactive DDx, where diagnostic reasoning evolves through iterative learning, rather than assuming a complete patient profile is accessible. MEDDxAgent integrates three modular components: (1) an orchestrator (DDxDriver), (2) a history taking simulator, and (3) two specialized agents for knowledge retrieval and diagnosis strategy. To ensure robust evaluation, we introduce a comprehensive DDx benchmark covering respiratory, skin, and rare diseases. We analyze single-turn diagnostic approaches and demonstrate the importance of iterative refinement when patient profiles are not available at the outset. Our broad evaluation demonstrates that MEDDxAgent achieves over 10% accuracy improvements in interactive DDx across both large and small LLMs, while offering critical explainability into its diagnostic reasoning process.