Synthetic data generation methods for longitudinal and time series health data: a systematic review
Marko Miletic, Murat Sariyar · 2025
Read Synthetic data generation methods for longitudinal and time series health data: a systematic review by Marko Miletic, Murat Sariyar (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12849454.txt.
Description
Marko Miletic and Murat Sariyar reviewed in 2025 how fake health data sets that unfold over time are made and judged. Fake data can free health research from privacy binds, but time-based records are tangled, gappy, and sensitive. The team ran a structured sweep of four databases for work from 2017 to 2025 and kept 115 studies. A five-part sorting frame helps readers place each method.
Deep generative models led the field, above all adversarial nets, autoencoders, and diffusion methods. Event-style records drew most work; smooth and gappy series lagged. Usefulness checks were common but uneven. Privacy checks were sparse, present in under a third and rigorous in few. The team maps where the field must firm up.
Catalog record
| CREATOR | Marko Miletic, Murat Sariyar |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 90 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |