ConsultMind：基于不确定性推理的自动化诊断咨询
ConsultMind:Towards Automated Diagnostic Consultation via Uncertainty-Aware Reasoning
- College of Computer Science, Chongqing University（重庆大学计算机科学学院）
- College of Computer Science, Hunan University（湖南大学计算机科学学院）
- AI Labs, Unisound（云知声AI实验室）
- Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
- Psycharity, Chongqing Medical University（重庆医科大学精神医学中心）
- School of Computer Science and Engineering, University of New South Wales（新南威尔士大学计算机科学与工程学院）
- Institute of Advanced Intelligence and Computing (IAIC), Agency for Science, Technology and Research (A*STAR), Singapore（新加坡科技研究局先进智能与计算研究所）
- Technological Information, Chongqing Center for Disease Control and Prevention（重庆市疾病预防控制中心科技信息处）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
本文提出AutoDisym和ConsultMind，利用贝叶斯网络与不确定性推理实现自动化诊断咨询，显著提升诊断准确率与解释质量。
中文摘要 AI 辅助
诊断咨询是一个在线顺序决策过程，在此过程中，临床医生通过患者互动收集证据，直到诊断得到充分支持。自动化这一过程需要自适应询问和可解释的决策。贝叶斯网络通过随着证据积累更新诊断后验概率，为此提供了自然基础，但其在开放式咨询中的应用带来了两个挑战：将诊断假设与潜在询问联系起来，以及将不断演变的后验概率转化为咨询决策。我们引入了AutoDisym，一个自动化流程，它将诊断知识与异质性诊断标签的临床叙述相结合，以构建疾病-症状贝叶斯网络（DSBN）。基于DSBN，我们提出了ConsultMind，一个不确定性感知框架，它在每次响应后更新疾病后验概率，并使用后验不确定性来指导询问和诊断。我们在精神病学、呼吸内科、发热门诊以及三个公共数据集上评估了这两种方法。结果表明，AutoDisym能够自动构建高质量的DSBN，且ConsultMind持续提高了诊断性能和解释合理性。例如，使用GPT-5.6-Sol，AutoDisym在典型症状上实现了81.37的宏平均F1分数，在表现上实现了72.19。ConsultMind将Top-1和Top-3诊断准确率分别提高了最多22.15和37.89个百分点。医生评估进一步表明，ConsultMind在不同规模的大语言模型中提高了排名解释、鉴别诊断和诊断理由的质量。这项工作为自动诊断咨询提供了一种有前景的方法。
英文摘要
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.
