Mitigating algorithmic unfairness arising from forgetfulness of medical records in clinical artificial intelligence

Nature Communications, Published online: 04 May 2026; doi:10.1038/s41467-026-72601-7 Applying the right to be forgotten to electronic health records that have been used to train artificial intelligence models could compromise model accuracy and fairness. Here, the authors develop a machine unlearning model that aims to remove data whilst preserving algorithmic fairness across subgroups.