# Why patient data cannot be easily forgotten?

arXiv: https://arxiv.org/abs/2206.14541 · HTML: https://mlsanity.com/paper/2206.14541/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 25 references that are in the map.
- First posted on arXiv 29 Jun 2022.

## Builds on (most cited first, 15 of 15)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [A systematic study of the class imbalance problem in convolutional neural networks](https://mlsanity.com/paper/1710.05381/) (2017)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [Remember What You Want to Forget: Algorithms for Machine Unlearning](https://mlsanity.com/paper/2103.03279/) (2021)
- [Variational Bayesian Unlearning](https://mlsanity.com/paper/2010.12883/) (2020)
- [Survey: Leakage and Privacy at Inference Time](https://mlsanity.com/paper/2107.01614/) (2021)
- [Have you forgotten? A method to assess if machine learning models have forgotten data](https://mlsanity.com/paper/2004.10129/) (2020)
- [Evaluation of Inference Attack Models for Deep Learning on Medical Data](https://mlsanity.com/paper/2011.00177/) (2020)
- [Controllable cardiac synthesis via disentangled anatomy arithmetic](https://mlsanity.com/paper/2107.01748/) (2021)
- [Unintended memorisation of unique features in neural networks](https://mlsanity.com/paper/2205.10079/) (2022)

## Built on by (most cited first, 3 of 3)

- [Privacy Distillation: Reducing Re-identification Risk of Multimodal Diffusion Models](https://mlsanity.com/paper/2306.01322/) (2023)
- [Enhancing the Utility of Privacy-Preserving Cancer Classification using Synthetic Data](https://mlsanity.com/paper/2407.12669/) (2024)
- [Erase to Enhance: Data-Efficient Machine Unlearning in MRI Reconstruction](https://mlsanity.com/paper/2405.15517/) (2024)

## Abstract (arXiv)

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.