Generating Multi-Table Time Series EHR from Latent Space with Minimal Preprocessing
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Clinical utility evaluation | MIMIC IV | Micro-averaged AUROC87 | 10 | |
| Clinical utility evaluation | eICU | Micro-averaged AUROC83 | 10 | |
| Next event prediction | MIMIC IV | -- | 6 | |
| Multi-table and time-series EHR generation | EHR Datasets | Number of Features3.34e+5 | 5 | |
| Next event prediction | eICU | F1 Score25 | 5 | |
| Single-table data generation fidelity | MIMIC IV | ER19.69 | 5 | |
| Single-table data generation fidelity | eICU | ER45.58 | 5 | |
| Synthetic Medical Data Generation | MIMIC-IV-ED | AUROC (Utility)79 | 5 | |
| Time Gap Estimation | MIMIC IV | Time Gap0.01 | 4 | |
| Event Count Estimation | eICU | Event Count0.05 | 4 |