Evaluation metrics for temporal preservation in synthetic longitudinal patient data
This work addresses the need for reliable evaluation of synthetic data quality in healthcare, enabling more realistic data generation for research, though it is incremental as it focuses on metrics rather than a new generative method.
The study tackled the problem of evaluating temporal preservation in synthetic longitudinal patient data by introducing a set of metrics that assess key temporal characteristics, revealing that strong marginal-level resemblance can hide distortions in covariance and individual-level trajectories, with factors like data quality and measurement frequency influencing preservation.
This study introduces a set of metrics for evaluating temporal preservation in synthetic longitudinal patient data, defined as artificially generated data that mimic real patients' repeated measurements over time. The proposed metrics assess how synthetic data reproduces key temporal characteristics, categorized into marginal, covariance, individual-level and measurement structures. We show that strong marginal-level resemblance may conceal distortions in covariance and disruptions in individual-level trajectories. Temporal preservation is influenced by factors such as original data quality, measurement frequency, and preprocessing strategies, including binning, variable encoding and precision. Variables with sparse or highly irregular measurement times provide limited information for learning temporal dependencies, resulting in reduced resemblance between the synthetic and original data. No single metric adequately captures temporal preservation; instead, a multidimensional evaluation across all characteristics provides a more comprehensive assessment of synthetic data quality. Overall, the proposed metrics clarify how and why temporal structures are preserved or degraded, enabling more reliable evaluation and improvement of generative models and supporting the creation of temporally realistic synthetic longitudinal patient data.