A review of Generative Adversarial Networks for Electronic Health Records: applications, evaluation measures and data sources

TL;DR

This review paper discusses how Generative Adversarial Networks (GANs) are used to generate synthetic Electronic Health Records (EHRs), highlighting applications, evaluation metrics, datasets, challenges, and future research directions.

Contribution

It provides a comprehensive overview of GAN-based methods for EHRs, including methodologies, evaluation practices, and benchmark datasets, to guide future research in healthcare machine learning.

Findings

GANs effectively generate synthetic EHR data with high fidelity.

Evaluation metrics and datasets are compiled as benchmarks for future studies.

Challenges and best practices for GAN development in healthcare are discussed.

Abstract

Electronic Health Records (EHRs) are a valuable asset to facilitate clinical research and point of care applications; however, many challenges such as data privacy concerns impede its optimal utilization. Deep generative models, particularly, Generative Adversarial Networks (GANs) show great promise in generating synthetic EHR data by learning underlying data distributions while achieving excellent performance and addressing these challenges. This work aims to review the major developments in various applications of GANs for EHRs and provides an overview of the proposed methodologies. For this purpose, we combine perspectives from healthcare applications and machine learning techniques in terms of source datasets and the fidelity and privacy evaluation of the generated synthetic datasets. We also compile a list of the metrics and datasets used by the reviewed works, which can be utilized as benchmarks for future research in the field. We conclude by discussing challenges in GANs for EHRs development and proposing recommended practices. We hope that this work motivates novel research development directions in the intersection of healthcare and machine learning.