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

Elias Hossain; Md Mehedi Hasan Nipu; Maleeha Sheikh; Tasfia Nuzhat; Rajib Rana; Subash Neupane; Björn W. Schuller; Niloofar Yousefi

cs.AINov 20, 2025

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

Authors: Elias Hossain, Md Mehedi Hasan Nipu, Maleeha Sheikh, Tasfia Nuzhat, Rajib Rana, Subash Neupane, Björn W. Schuller, Niloofar Yousefi

Organizations: College of Engineering and Computer Science, University of Central Florida, Orlando, FL 32816, USA · Department of Computer Science and Engineering, North South University, Dhaka 1229, Bangladesh · Department of Electrical and Computer Engineering, Purdue University Fort Wayne, Fort Wayne, IN 46805, USA · School of Mathematics, Physics and Computing, University of Southern Queensland, Springfield Central, QLD 4300, Australia · Meharry Medical College, Nashville, TN 37208, USA · CHI – Chair of Health Informatics, Technical University of Munich (TUM), Munich, Germany · GLAM – Group on Language, Audio, & Music, Imperial College London, London, UK

Abstract

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.

Explore similar work

When Confidence Fails: Overconfidence in LLMs under Uncertainty and Missing Clinical Information
Aug 10, 2026Maryam Tahermazandarani, Adnan Mahmood, Fahmida Islam +1Large Language Model Uncertainty Overconfidence
CURA: Clinical Uncertainty Risk Alignment for Language Model-Based Risk Prediction
Apr 16, 2026Sizhe Wang, Ziqi Xu, Claire Najjuuko +2Clinical Prediction Large Language Model Uncertainty
Medical Model Synthesis Architectures: A Case Study
May 10, 2026Katherine M. Collins, Marlene Berke, Ilia Sucholutsky +6Clinical Prediction Artificial Intelligence Systems

Aug 10, 2026 · cs.CLJ/K move · Enter open · S save

When Confidence Fails: Overconfidence in LLMs under Uncertainty and Missing Clinical Information

Maryam Tahermazandarani, Adnan Mahmood, Fahmida Islam, Quan Z. Sheng

School of Computing, Macquarie University, Sydney, NSW 2109, Australia

Large Language Models (LLMs) have achieved strong performance in medical question answering and clinical reasoning tasks. However, their reliability under uncertainty remains poorly understood which raises critical concerns for deployment in high-stakes clinical settings. In such environments, incorrect predictions are inherently risky, but confident incorrect predictions can be particularly harmful as they may mislead clinical decision-making. In this paper, we conduct a systematic behavioral analysis of LLMs under clinical information uncertainty. We propose an evaluation framework based on the MedMCQA dataset consisting of two complementary uncertainty settings. First, we introduce linguistic uncertainty cues through prompt modifications to simulate ambiguous clinical contexts. Second, we construct an answer removal setting, wherein the correct option is deliberately excluded mandating the model to recognize insufficient information and abstain. We analyze both model accuracy and confidence behavior using multiple calibration metrics including calibration gap, Expected Calibration Error (ECE), and Unsafe Confident Error Rate (UCER) across 500 medical questions. Our results reveal a consistent failure mode, i.e., although accuracy degrades under increasing uncertainty, model confidence remains misaligned with accuracy. This leads to a substantial increase in unsafe confident errors, indicating that model confidence remains largely insensitive to clinically meaningful information loss. Furthermore, we observe significant variation across models in their ability to abstain when the correct answer is unavailable, with some models persistently producing high confidence hallucinated answers. These findings expose critical limitations in the epistemic reliability of current LLMs and highlight the need for uncertainty aware evaluation methods prior to their deployment in clinical workflows.

Large Language Model Uncertainty Overconfidence Linguistics

Open paper Ask about it PDF

Abstract

Explore similar work

When Confidence Fails: Overconfidence in LLMs under Uncertainty and Missing Clinical Information

CURA: Clinical Uncertainty Risk Alignment for Language Model-Based Risk Prediction

Medical Model Synthesis Architectures: A Case Study