Uc-PrUn: Uncertainty-Calibrated Machine Unlearning using Vision-Language Models for Clinical Decision Support

Uc-PrUn couples zero-shot uncertainty estimation with selective unlearning to improve calibration and downstream clinical VLM performance.

In this study, we introduce Uc-PrUn, a principled framework designed to improve the reliability of Vision–Language Models (VLMs) in clinical decision-support systems. The first stage focuses on Bayesian-inspired zero-shot uncertainty quantification using Monte Carlo dropout, while the second stage introduces an uncertainty-aware machine-unlearning strategy. Leveraging the Harvard-FairVLMed dataset, which comprises paired SLO fundus images and clinical notes for glaucoma detection, we evaluate VLMs to quantify epistemic uncertainty and identify high-variance training samples. The pruning and unlearning mechanism selectively removes uncertain samples to enhance model calibration and downstream performance. Experiments show that Uc-PrUn reduces predictive uncertainty and yields consistent gains in accuracy and F1 scores across multiple VLMs, supporting uncertainty-aware pruning in medical AI pipelines.