Generating Multi-Table Time Series EHR from Latent Space with Minimal Preprocessing

TL;DR

RawMed is a novel framework that synthesizes multi-table, time-series electronic health records with minimal preprocessing, capturing complex structures and temporal dynamics, thereby enabling privacy-preserving healthcare data sharing.

Contribution

It introduces RawMed, the first method to generate raw, multi-table, time-series EHR data with minimal preprocessing, and proposes a new evaluation framework for synthetic EHR quality.

Findings

Outperforms baseline models in fidelity and utility

Successfully captures complex structures and temporal dynamics

Validated on two open-source datasets

Abstract

Electronic Health Records (EHR) are time-series relational databases that record patient interactions and medical events over time, serving as a critical resource for healthcare research and applications. However, privacy concerns and regulatory restrictions limit the sharing and utilization of such sensitive data, necessitating the generation of synthetic EHR datasets. Unlike previous EHR synthesis methods, which typically generate medical records consisting of expert-chosen features (e.g. a few vital signs or structured codes only), we introduce RawMed, the first framework to synthesize multi-table, time-series EHR data that closely resembles raw EHRs. Using text-based representation and compression techniques, RawMed captures complex structures and temporal dynamics with minimal preprocessing. We also propose a new evaluation framework for multi-table time-series synthetic EHRs, assessing distributional similarity, inter-table relationships, temporal dynamics, and privacy. Validated on two open-source EHR datasets, RawMed outperforms baseline models in fidelity and utility. The code is available at https://github.com/eunbyeol-cho/RawMed.