# Does Machine Unlearning Preserve Clinical Safety? A Risk Analysis for Medical Image Classification Source: [Does Machine Unlearning Preserve Clinical Safety? A Risk Analysis for Medical Image Classification]() Collection index: [llms.txt]() Data updated: 2026-04-29T05:00:12.215Z Authors: Andreza M. C. Falcao, Filipe R. Cordeiro Published: 2026-04-26T19:47:57.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Machine Unlearning on DermaMNIST 20% removal binary (test)](): Machine Unlearning; DermaMNIST 20% removal binary (test); Specificity: 85. - [Machine Unlearning on DermaMNIST 50% removal binary (test)](): Machine Unlearning; DermaMNIST 50% removal binary (test); Specificity: 83. - [Machine Unlearning on PathMNIST 50% removal binary (test)](): Machine Unlearning; PathMNIST 50% removal binary (test); Specificity: 98. - [Machine Unlearning on PathMNIST 20% removal binary (test)](): Machine Unlearning; PathMNIST 20% removal binary (test); Specificity: 98. ## Original sources and implementation [Original paper]() [PDF]()