From Uncertainty to Clinical Risk: Severity-Aware Conformal Planning for Interactive Medical Diagnosis
Artificial Intelligence
Summary
The authors studied how to improve interactive medical diagnosis, which means asking patients questions step-by-step to decide what's wrong. They noticed that past methods didn't really consider how risky it is to miss serious diseases or when to stop asking and make a decision. So, they created a new system that checks risks related to disease severity and plans the question-asking process more smartly. Their tests showed this approach helps make better diagnoses with fewer questions and fewer serious mistakes. This work highlights the importance of using clinical risk rather than just uncertainty when deciding how to get more patient information.
Authors
Yue Zhou, Haiyang Zhou, Jin Zhang, Kong Wang, Yongxin Ni, Youhua Li, Hanwen Du
Abstract
Interactive medical diagnosis dynamically acquires patient information through multiple rounds of questioning, supporting accurate, efficient, and safe clinical decisions under incomplete evidence. Existing methods commonly guide information acquisition with predictive uncertainty or label ambiguity, but overlook the asymmetric clinical risk of missing severe diseases and lack unified long-horizon planning over whether to continue asking questions or commit to a diagnosis. To address these limitations, we propose Severity-Aware Conformal Clinical Planning, which formulates interactive diagnosis as a risk-sensitive sequential decision problem. The framework maintains complementary diagnostic, safety, and masked-evidence beliefs; calibrates turn-specific diagnostic prediction sets and severity-weighted differential-diagnosis risk on held-out diagnostic trajectories; and introduces the calibrated clinical risk into Monte Carlo Tree Search to jointly evaluate long-horizon Ask and Commit trajectories. Experiments on DDXPlus and MediQ show that our method achieves more accurate diagnoses with fewer questions across multiple large language models, while improving differential-diagnosis quality and reducing high-risk errors in severe cases. These findings validate the value of using clinical risk, rather than predictive uncertainty alone, as a planning signal and demonstrate the effectiveness of the proposed framework for information acquisition and risk-aware diagnostic decision making. They also motivate future work on clinical-risk-oriented interactive diagnosis and information-acquisition methods.