# MedBayes-Lite: A Clinical Uncertainty Governance Layer for Risk-Aware Medical Decision Support

arXiv: https://arxiv.org/abs/2511.16625 · HTML: https://mlsanity.com/paper/2511.16625/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 34 references that are in the map.
- First posted on arXiv 20 Nov 2025.

## Builds on (most cited first, 20 of 20)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges](https://mlsanity.com/paper/2011.06225/) (2020)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [A Simple Baseline for Bayesian Uncertainty in Deep Learning](https://mlsanity.com/paper/1902.02476/) (2019)
- [Can large language models reason about medical questions?](https://mlsanity.com/paper/2207.08143/) (2022)
- [Benchmarking LLMs via Uncertainty Quantification](https://mlsanity.com/paper/2401.12794/) (2024)
- [Towards Accurate Differential Diagnosis with Large Language Models](https://mlsanity.com/paper/2312.00164/) (2023)
- [Being Bayesian about Categorical Probability](https://mlsanity.com/paper/2002.07965/) (2020)
- [LLM-MedQA: Enhancing Medical Question Answering through Case Studies in Large Language Models](https://mlsanity.com/paper/2501.05464/) (2024)
- [A Comprehensive Survey on Evidential Deep Learning and Its Applications](https://mlsanity.com/paper/2409.04720/) (2024)
- [Transformers in Healthcare: A Survey](https://mlsanity.com/paper/2307.00067/) (2023)
- [Uncertainty Quantification in Large Language Models Through Convex Hull Analysis](https://mlsanity.com/paper/2406.19712/) (2024)
- [MedInsight: A Multi-Source Context Augmentation Framework for Generating Patient-Centric Medical Responses using Large Language Models](https://mlsanity.com/paper/2403.08607/) (2024)
- [CLINICSUM: Utilizing Language Models for Generating Clinical Summaries from Patient-Doctor Conversations](https://mlsanity.com/paper/2412.04254/) (2024)
- [Streamlining evidence based clinical recommendations with large language models](https://mlsanity.com/paper/2505.10282/) (2025)

## Built on by (most cited first, 1 of 1)

- [TAM-Chain: Multi-Scale Thyroid Cytology Classification via Absorbing Markov Chains and Shannon Entropy Uncertainty Quantification for False-Negative Suppression and Domain-Shift Adaptation](https://mlsanity.com/paper/2609.28590/) (2026)

## Abstract (arXiv)

Clinical language models often assign high confidence to incorrect predictions, particularly in high-severity and out-of-distribution cases. We present MedBayes-Lite, a retraining-free uncertainty governance layer for transformer-based clinical predictors. It combines Monte Carlo dropout, predictive calibration, and confidence-guided abstention to defer low-confidence predictions for human review, adding no trainable parameters. Evaluated on MedMCQA and MedQA-USMLE, MedBayes-Lite reduces expected calibration error by 0.23 to 0.33 and drives harmful overconfident errors (confident, incorrect, high-severity predictions) toward zero. Under domain shift from MedMCQA to MedQA-USMLE, it reduces confident high-severity errors from about 21% to near zero while roughly halving calibration drift. We also introduce the Clinical Uncertainty Score (CUS), which strongly correlates with harmful overconfidence (r approximately 0.88). Although the framework does not improve risk-coverage ranking, and temperature scaling or deep ensembles may provide advantages in calibration cost or risk ranking, MedBayes-Lite offers a practical calibration-and-abstention layer that reduces confident high-severity errors in clinical question-answering benchmarks.