# Generating Synthetic but Plausible Healthcare Record Datasets

arXiv: https://arxiv.org/abs/1807.01514 · HTML: https://mlsanity.com/paper/1807.01514/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jul 2018.

## Built on by (most cited first, 12 of 12)

- [STaSy: Score-based Tabular data Synthesis](https://mlsanity.com/paper/2210.04018/) (2022)
- [CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesis](https://mlsanity.com/paper/2304.12654/) (2023)
- [TabuLa: Harnessing Language Models for Tabular Data Synthesis](https://mlsanity.com/paper/2310.12746/) (2023)
- [OCT-GAN: Neural ODE-based Conditional Tabular GANs](https://mlsanity.com/paper/2105.14969/) (2021)
- [Invertible Tabular GANs: Killing Two Birds with OneStone for Tabular Data Synthesis](https://mlsanity.com/paper/2202.03636/) (2022)
- [On the Utility Recovery Incapability of Neural Net-based Differential Private Tabular Training Data Synthesizer under Privacy Deregulation](https://mlsanity.com/paper/2211.15809/) (2022)
- [AIGT: AI Generative Table Based on Prompt](https://mlsanity.com/paper/2412.18111/) (2024)
- [FCT-GAN: Enhancing Table Synthesis via Fourier Transform](https://mlsanity.com/paper/2210.06239/) (2022)
- [DP-2Stage: Adapting Language Models as Differentially Private Tabular Data Generators](https://mlsanity.com/paper/2412.02467/) (2024)
- [Synthesizing time-series wound prognosis factors from electronic medical records using generative adversarial networks](https://mlsanity.com/paper/2105.01159/) (2021)
- [A Unified Framework for Tabular Generative Modeling: Loss Functions, Benchmarks, and Improved Multi-objective Bayesian Optimization Approaches](https://mlsanity.com/paper/2405.16971/) (2024)
- [Stage-Diff: Stage-wise Long-Term Time Series Generation Based on Diffusion Models](https://mlsanity.com/paper/2508.21330/) (2025)

## Abstract (arXiv)

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.