Synthetic data generation methods for longitudinal and time series health data: a systematic review

This systematic review surveys methods for generating synthetic longitudinal and time-series health data, where repeated measurements over time create temporal dependencies that cross-sectional synthesis methods do not address. Following a structured review protocol, it catalogues the available approaches, the metrics used to judge fidelity and utility, and the privacy considerations specific to sequential records. It identifies where current methods are strong and where important gaps remain, particularly for complex clinical trajectories. Published in BMC Medical Informatics and Decision Making, it provides a reference for researchers building or evaluating synthetic health data over time.