Automated diagnostic consultation improves accuracy with symptom reasoning
ConsultMind:Towards Automated Diagnostic Consultation via Uncertainty-Aware Reasoning
Artificial Intelligence
Summary
Diagnosing illnesses usually takes many back-and-forth questions between doctors and patients. The authors developed a system that builds a diagnostic network from medical stories and uses uncertainty to decide what questions to ask next. This system steadily updates guesses about the illness as answers come in, aiming to make better diagnoses and give clearer explanations. They tested it across several medical areas and found it improved diagnosis accuracy and explanation quality compared to other methods.
What this means in practice
- •For clinical decision support teams: Build automated tools that interact with patients to gather symptoms adaptively and improve preliminary diagnosis quality with clearer explanations.
- •For chatbot developers: Integrate uncertainty-aware reasoning to guide question sequences for health inquiry chatbots, enhancing their diagnostic relevance and interpretability.
Authors
Xiao Sun, Yuming Yang, Yun Chen, Jiang Zhong, Junnan Zhu, Xinyi Jiang, Haoyang Zeng, Ruirui Chen, Yining Wang, Xinyu Zhou, Rong Tang, Kaiwen Wei
Abstract
Diagnostic consultation is an online sequential decision-making process in which clinicians gather evidence through patient interaction until a diagnosis is sufficiently supported. Automating this process requires adaptive inquiry and interpretable decisions. Bayesian networks offer a natural foundation by updating diagnostic posteriors as evidence accumulates, but their use in open-ended consultation raises two challenges: linking diagnostic hypotheses to potential inquiries and translating evolving posteriors into consultation decisions. We introduce AutoDisym, an automated pipeline that integrates diagnostic knowledge with heterogeneous diagnosis-labeled clinical narratives to construct a Disorder--Symptom Bayesian Network (DSBN). Building on the DSBN, we propose ConsultMind, an uncertainty-aware framework that updates disorder posteriors after each response and uses posterior uncertainty to guide inquiry and diagnosis. We evaluate both methods across psychiatry, respiratory medicine, fever clinics, and three public datasets. The results show that AutoDisym can automatically construct high-quality DSBNs and that ConsultMind consistently improves diagnostic performance and explanation soundness. For example, AutoDisym achieves macro-averaged F1 scores of 81.37 for canonical symptoms and 72.19 for manifestations using GPT-5.6-Sol. ConsultMind improves Top-1 and Top-3 diagnostic accuracy by up to 22.15 and 37.89 percentage points, respectively. Physician evaluation further shows that ConsultMind improves the quality of ranking explanations, differential diagnoses, and diagnosis rationales across LLMs of different scales. This work offers a promising approach to automatic diagnostic consultation.