Why patient data cannot be easily forgotten?
This addresses the challenge of data privacy rights for patients in healthcare AI, but it is incremental as it builds on existing forgetting methods.
The paper tackles the problem of forgetting patient data from AI models, showing it is not easily achievable, and proposes a targeted forgetting approach that improves performance over a state-of-the-art method on the Automated Cardiac Diagnosis Challenge dataset.
Rights provisioned within data protection regulations, permit patients to request that knowledge about their information be eliminated by data holders. With the advent of AI learned on data, one can imagine that such rights can extent to requests for forgetting knowledge of patient's data within AI models. However, forgetting patients' imaging data from AI models, is still an under-explored problem. In this paper, we study the influence of patient data on model performance and formulate two hypotheses for a patient's data: either they are common and similar to other patients or form edge cases, i.e. unique and rare cases. We show that it is not possible to easily forget patient data. We propose a targeted forgetting approach to perform patient-wise forgetting. Extensive experiments on the benchmark Automated Cardiac Diagnosis Challenge dataset showcase the improved performance of the proposed targeted forgetting approach as opposed to a state-of-the-art method.