Protect and Extend -- Using GANs for Synthetic Data Generation of Time-Series Medical Records

TL;DR

This paper evaluates GAN-based models for generating synthetic time-series medical records, focusing on privacy preservation and data quality, to enable safe data sharing in sensitive healthcare contexts.

Contribution

It compares state-of-the-art GAN models for privacy-preserving synthetic medical data generation and introduces a model that balances privacy with data quality.

Findings

PPGAN outperforms other models in privacy preservation

Generated data maintains acceptable quality for predictive tasks

Membership inference attacks reveal reduced data leakage risks

Abstract

Preservation of private user data is of paramount importance for high Quality of Experience (QoE) and acceptability, particularly with services treating sensitive data, such as IT-based health services. Whereas anonymization techniques were shown to be prone to data re-identification, synthetic data generation has gradually replaced anonymization since it is relatively less time and resource-consuming and more robust to data leakage. Generative Adversarial Networks (GANs) have been used for generating synthetic datasets, especially GAN frameworks adhering to the differential privacy phenomena. This research compares state-of-the-art GAN-based models for synthetic data generation to generate time-series synthetic medical records of dementia patients which can be distributed without privacy concerns. Predictive modeling, autocorrelation, and distribution analysis are used to assess the Quality of Generating (QoG) of the generated data. The privacy preservation of the respective models is assessed by applying membership inference attacks to determine potential data leakage risks. Our experiments indicate the superiority of the privacy-preserving GAN (PPGAN) model over other models regarding privacy preservation while maintaining an acceptable level of QoG. The presented results can support better data protection for medical use cases in the future.