Multiagent system improves explainability and accuracy of differential diagnosis
Ontology-guided multi-agent reasoning for explainable differential diagnosis
Artificial IntelligenceMultiagent Systems
Summary
Making a correct medical diagnosis is tricky when patient information is incomplete or unclear, which can lead to errors. The authors created a computer system that mimics how doctors think step-by-step, using a trusted medical knowledge map to connect symptoms and diseases. This system asks focused questions to get more useful information and explains its reasoning clearly, helping doctors understand why certain diagnoses are suggested. This approach aims to make AI tools for diagnosis more reliable and easier to trust.
What this means in practice
- •For clinical decision support teams: Build AI tools that produce transparent and stepwise diagnostic suggestions grounded in expert medical knowledge.
- •For medical chatbot developers: Create symptom inquiry agents that generate targeted follow-up questions to improve diagnostic certainty during patient interactions.
Authors
Roxana Ramona Szomiu, George Ursu, Adrian Groza
Abstract
Effective differential diagnosis depends on well structured and unambiguous patient case descriptions, since incomplete or ambiguous clinical information readily leads to diagnostic errors and inconsistent reasoning. Large Language Models (LLMs) have recently shown promising capabilities in medical question answering and clinical reasoning; however, even when achieving competitive performance on medical benchmarks, they often rely on pattern recognition learned from training data rather than grounded clinical evidence, and can generate plausible yet unsupported diagnostic conclusions. Their reasoning remains largely opaque, making it difficult for clinicians to assess the evidence and rationale behind a given recommendation. To address this gap, we propose an ontology-guided, multiagent differential diagnosis framework that replicates the iterative reasoning process of physicians. The framework grounds diagnostic inference in a structured, expert-curated medical knowledge base, enabling interpretation of symptoms, clinical findings, or disease relationships, while decomposing diagnosis into explicit, auditable reasoning steps. This ontology-based grounding constrains inference to evidence-backed associations, reducing hallucination and improving diagnostic transparency, traceability, and consistency. The system then identifies the most discriminative missing symptoms and generates targeted follow-up questions to reduce uncertainty through a process that mirrors to clinical inquiry. Together, these components improve the reliability, explainability, and diagnostic accuracy of AI-assisted differential diagnosis. The source code is publicly available.