Does Machine Unlearning Preserve Clinical Safety? A Risk Analysis for Medical Image Classification
The application of Deep Learning in medical diagnosis must balance patient safety with compliance with data protection regulations. Machine Unlearning enables the selective removal of training data from deployed models. However, most methods are validated primarily through efficiency and privacy-oriented metrics, with limited attention to clinically asymmetric error costs. In this work, we investigate how unlearning affects clinical risk in binary medical image classification. We show that standard unlearning strategies (Fine-Tuning, Random Labeling, and SalUn) may reduce test utility while increasing false-negative rates, thereby amplifying clinical risk. To mitigate this, we propose SalUn-CRA (Clinical Risk-Aware), a variant of SalUn that replaces random relabeling with entropy-based forgetting for malignant samples in the forget set, preventing the model from learning harmful benign associations. We evaluate on DermaMNIST and PathMNIST medical image datasets under 20% and 50% data removal. Using Global Risk metrics with asymmetric costs, SalUn-CRA achieves lower or comparable clinical risk to full retraining while preserving unlearning effectiveness. These results suggest that clinical risk should be an integral component of unlearning validation in medical systems.
Full article excerpt tap to expand
Computer Science > Artificial Intelligence arXiv:2604.23854 (cs) [Submitted on 26 Apr 2026] Title:Does Machine Unlearning Preserve Clinical Safety? A Risk Analysis for Medical Image Classification Authors:Andreza M. C. Falcao, Filipe R. Cordeiro View a PDF of the paper titled Does Machine Unlearning Preserve Clinical Safety? A Risk Analysis for Medical Image Classification, by Andreza M. C. Falcao and Filipe R. Cordeiro View PDF HTML (experimental) Abstract:The application of Deep Learning in medical diagnosis must balance patient safety with compliance with data protection regulations. Machine Unlearning enables the selective removal of training data from deployed models. However, most methods are validated primarily through efficiency and privacy-oriented metrics, with limited attention to clinically asymmetric error costs. In this work, we investigate how unlearning affects clinical risk in binary medical image classification. We show that standard unlearning strategies (Fine-Tuning, Random Labeling, and SalUn) may reduce test utility while increasing false-negative rates, thereby amplifying clinical risk. To mitigate this, we propose SalUn-CRA (Clinical Risk-Aware), a variant of SalUn that replaces random relabeling with entropy-based forgetting for malignant samples in the forget set, preventing the model from learning harmful benign associations. We evaluate on DermaMNIST and PathMNIST medical image datasets under 20% and 50% data removal. Using Global Risk metrics with asymmetric costs, SalUn-CRA achieves lower or comparable clinical risk to full retraining while preserving unlearning effectiveness. These results suggest that clinical risk should be an integral component of unlearning validation in medical systems. Comments: Accepted at SBCAS'26 Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2604.23854 [cs.AI] (or arXiv:2604.23854v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2604.23854 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Filipe Cordeiro [view email] [v1] Sun, 26 Apr 2026 19:47:57 UTC (63 KB) Full-text links: Access Paper: View a PDF of the paper titled Does Machine Unlearning Preserve Clinical Safety? A Risk Analysis for Medical Image Classification, by Andreza M. C. Falcao and Filipe R. CordeiroView PDFHTML (experimental)TeX Source view license Current browse context: cs.AI < prev | next > new | recent | 2026-04 Change to browse by: cs References & Citations NASA ADSGoogle Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers…
This excerpt is published under fair use for community discussion. Read the full article at arXiv.org.
Discussion
0 commentsMore from arXiv.org