Uc-PrUn : Uncertainty-Calibrated Machine Unlearning Using Vision–Language Models for Clinical Decision Support
ACM Transactions on Computing for Healthcare · 31.10.2026 · 7 (4) · 1-31
DOI: 10.1145/3820497 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Computing for Healthcare, online erschienen am 19.08.2026. Verfasst von Farhan Sheth und 4 weiteren Autor:innen. Die Arbeit nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Unites States-Ireland-Northern Ireland R&D Partnership Programme, ARUK, EPSRC.
Abstract (Originalsprache)
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. Recognizing the critical importance of uncertainty estimation in high-stakes domains, we introduce a two-stage methodology; the first stage focuses on Bayesian-inspired zero-shot uncertainty quantification using Monte Carlo dropout, while the second stage introduces a novel uncertainty-aware machine unlearning strategy, termed Uc-PrUn . Leveraging the Harvard-FairVLMed dataset, which comprises paired SLO fundus images and clinical notes for glaucoma detection, we systematically evaluate various VLMs to quantify epistemic uncertainty and identify high-variance training samples. Our pruning and unlearning mechanism selectively removes uncertain samples to enhance model calibration and improve downstream performance. Experimental results demonstrate that the Uc-PrUn approach not only reduces predictive uncertainty but also yields consistent gains in accuracy and F 1 -scores across multiple VLMs. These findings support incorporating uncertainty-aware pruning mechanisms in medical AI pipelines where model reliability is essential.
Förderung
- Unites States-Ireland-Northern Ireland R&D Partnership Programme
- ARUK
- EPSRC
Zitieren
APA
Sheth, F., Akhtar, M. M., Girish, Singh, M., & Davey, A. (2026). Uc-PrUn : Uncertainty-Calibrated Machine Unlearning Using Vision–Language Models for Clinical Decision Support. ACM Transactions on Computing for Healthcare, 7(4), 1-31. https://doi.org/10.1145/3820497
Vancouver
Sheth F, Akhtar MM, Girish, Singh M, Davey A. Uc-PrUn : Uncertainty-Calibrated Machine Unlearning Using Vision–Language Models for Clinical Decision Support. ACM Transactions on Computing for Healthcare. 2026;7(4):1-31. doi:10.1145/3820497
BibTeX
@article{Sheth2026,
author = {Sheth, Farhan and Akhtar, Mohd Mujtaba and Girish and Singh, Muskaan and Davey, Alexander},
title = {Uc-PrUn : Uncertainty-Calibrated Machine Unlearning Using Vision–Language Models for Clinical Decision Support},
journal = {ACM Transactions on Computing for Healthcare},
year = {2026},
volume = {7},
number = {4},
pages = {1--31},
doi = {10.1145/3820497}
}
EUVIMED