# From Uncertainty to Clinical Risk: Severity-Aware Conformal Planning for Interactive Medical Diagnosis

arXiv: https://arxiv.org/abs/2608.27847 · HTML: https://mlsanity.com/paper/2608.27847/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 39 references that are in the map.
- First posted on arXiv 28 Aug 2026.

## Builds on (most cited first, 22 of 22)

- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [Classification with Valid and Adaptive Coverage](https://mlsanity.com/paper/2006.02544/) (2020)
- [Adaptive Conformal Inference Under Distribution Shift](https://mlsanity.com/paper/2106.00170/) (2021)
- [Distribution-Free, Risk-Controlling Prediction Sets](https://mlsanity.com/paper/2101.02703/) (2021)
- [MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning](https://mlsanity.com/paper/2406.00922/) (2024)
- [Benchmarking LLMs via Uncertainty Quantification](https://mlsanity.com/paper/2401.12794/) (2024)
- [Class-Conditional Conformal Prediction with Many Classes](https://mlsanity.com/paper/2306.09335/) (2023)
- [AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator](https://mlsanity.com/paper/2402.09742/) (2024)
- [Large language model validity via enhanced conformal prediction methods](https://mlsanity.com/paper/2406.09714/) (2024)
- [DDXPlus: A New Dataset For Automatic Medical Diagnosis](https://mlsanity.com/paper/2205.09148/) (2022)
- [Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents](https://mlsanity.com/paper/2311.00262/) (2023)
- [Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training](https://mlsanity.com/paper/2406.00222/) (2024)
- [Learning to Maximize Mutual Information for Dynamic Feature Selection](https://mlsanity.com/paper/2301.00557/) (2023)
- [Conformal Alignment: Knowing When to Trust Foundation Models with Guarantees](https://mlsanity.com/paper/2405.10301/) (2024)
- [Uncertainty in Language Models: Assessment through Rank-Calibration](https://mlsanity.com/paper/2404.03163/) (2024)
- [BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design](https://mlsanity.com/paper/2508.21184/) (2025)
- [MEDDxAgent: A Unified Modular Agent Framework for Explainable Automatic Differential Diagnosis](https://mlsanity.com/paper/2502.19175/) (2025)
- [Active, anytime-valid risk controlling prediction sets](https://mlsanity.com/paper/2406.10490/) (2024)
- [Early Time Classification with Accumulated Accuracy Gap Control](https://mlsanity.com/paper/2402.00857/) (2024)
- [Timely Clinical Diagnosis through Active Test Selection](https://mlsanity.com/paper/2510.18988/) (2025)

## Abstract (arXiv)

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.