Differentially Private Synthetic Medical Data Generation using Convolutional GANs

TL;DR

This paper introduces a novel differentially private convolutional GAN framework for generating synthetic medical data that preserves key data characteristics while ensuring privacy, outperforming existing models on benchmark datasets.

Contribution

The paper presents a new differentially private synthetic data generation method using convolutional autoencoders and GANs, capturing temporal and feature correlations in medical data.

Findings

Outperforms state-of-the-art models under the same privacy budget

Preserves temporal information and feature correlations in synthetic data

Effective on multiple benchmark medical datasets

Abstract

Deep learning models have demonstrated superior performance in several application problems, such as image classification and speech processing. However, creating a deep learning model using health record data requires addressing certain privacy challenges that bring unique concerns to researchers working in this domain. One effective way to handle such private data issues is to generate realistic synthetic data that can provide practically acceptable data quality and correspondingly the model performance. To tackle this challenge, we develop a differentially private framework for synthetic data generation using R\'enyi differential privacy. Our approach builds on convolutional autoencoders and convolutional generative adversarial networks to preserve some of the critical characteristics of the generated synthetic data. In addition, our model can also capture the temporal information and feature correlations that might be present in the original data. We demonstrate that our model outperforms existing state-of-the-art models under the same privacy budget using several publicly available benchmark medical datasets in both supervised and unsupervised settings.