Generating Synthetic but Plausible Healthcare Record Datasets
This work addresses the need for plausible synthetic data in healthcare applications, offering an interpretable alternative to GANs, though it appears incremental as it builds on prior clustering methods.
The authors tackled the problem of generating realistic synthetic healthcare record datasets by proposing a new latent variable method for binary data, which outperformed a GAN-based approach (MedGan) in terms of indistinguishability by Random Forests and MMD statistics, likely due to avoiding mode collapse.
Generating datasets that "look like" given real ones is an interesting tasks for healthcare applications of ML and many other fields of science and engineering. In this paper we propose a new method of general application to binary datasets based on a method for learning the parameters of a latent variable moment that we have previously used for clustering patient datasets. We compare our method with a recent proposal (MedGan) based on generative adversarial methods and find that the synthetic datasets we generate are globally more realistic in at least two senses: real and synthetic instances are harder to tell apart by Random Forests, and the MMD statistic. The most likely explanation is that our method does not suffer from the "mode collapse" which is an admitted problem of GANs. Additionally, the generative models we generate are easy to interpret, unlike the rather obscure GANs. Our experiments are performed on two patient datasets containing ICD-9 diagnostic codes: the publicly available MIMIC-III dataset and a dataset containing admissions for congestive heart failure during 7 years at Hospital de Sant Pau in Barcelona.