MedBayes-Lite: Bayesian Uncertainty Quantification for Safe Clinical Decision Support
By: Elias Hossain , Md Mehedi Hasan Nipu , Maleeha Sheikh and more
Potential Business Impact:
Makes AI doctors know when they are unsure.
We propose MedBayes-Lite, a lightweight Bayesian enhancement for transformer-based clinical language models designed to produce reliable, uncertainty-aware predictions. Although transformers show strong potential for clinical decision support, they remain prone to overconfidence, especially in ambiguous medical cases where calibrated uncertainty is critical. MedBayes-Lite embeds uncertainty quantification directly into existing transformer pipelines without any retraining or architectural rewiring, adding no new trainable layers and keeping parameter overhead under 3 percent. The framework integrates three components: (i) Bayesian Embedding Calibration using Monte Carlo dropout for epistemic uncertainty, (ii) Uncertainty-Weighted Attention that marginalizes over token reliability, and (iii) Confidence-Guided Decision Shaping inspired by clinical risk minimization. Across biomedical QA and clinical prediction benchmarks (MedQA, PubMedQA, MIMIC-III), MedBayes-Lite consistently improves calibration and trustworthiness, reducing overconfidence by 32 to 48 percent. In simulated clinical settings, it can prevent up to 41 percent of diagnostic errors by flagging uncertain predictions for human review. These results demonstrate its effectiveness in enabling reliable uncertainty propagation and improving interpretability in medical AI systems.
Similar Papers
The challenge of uncertainty quantification of large language models in medicine
Artificial Intelligence
Helps doctors know when AI is unsure about health advice.
Bayesian--AI Fusion for Epidemiological Decision Making: Calibrated Risk, Honest Uncertainty, and Hyperparameter Intelligence
Machine Learning (Stat)
Makes AI better at predicting health risks.
BayesQ: Uncertainty-Guided Bayesian Quantization
Machine Learning (CS)
Makes computer programs run faster using less memory.