Investigating synthetic medical time-series resemblance - Laboratoire Interdisciplinaire des Sciences du Numérique Access content directly
Journal Articles Neurocomputing Year : 2022

Investigating synthetic medical time-series resemblance

Karan Bhanot
  • Function : Author
  • PersonId : 1354183
Isabelle Guyon
  • Function : Author
  • PersonId : 963159
Kristin P Bennett
  • Function : Author
  • PersonId : 924690

Abstract

Access to private medical data is restricted due to privacy laws, hindering research and real-world use. Synthetic data generation provides a viable solution by generating data with high utility and privacy protection without releasing the real data. Healthcare data records are often longitudinal in nature, being affected by covariates like age, gender, ethnicity, etc. As a result, synthetic healthcare data generation falls in the domain of time-series modeling and requires time-series based measures to investigate real and synthetic data resemblance. Covariate plots can be used for qualitative time-series resemblance but lack an empirical quantitative measure, thus, resulting in interpretations biased towards viewer's perspective. In this paper, we describe four time-series metrics to quantitatively evaluate the real and synthetic time-series resemblance on datasets from previously published healthcare research studies, both public and private. We apply the metrics on covariate plots for synthetic datasets to investigate the resemblance and compare the results with baseline synthetic datasets. We infer that the metrics effectively capture the time-series resemblance between real and synthetic datasets. The results highlight varying degrees of resemblance across subgroups of covariates and multivariate time-series.
No file

Dates and versions

hal-04465658 , version 1 (19-02-2024)

Identifiers

Cite

Karan Bhanot, Joseph Pedersen, Isabelle Guyon, Kristin P Bennett. Investigating synthetic medical time-series resemblance. Neurocomputing, 2022, 494, pp.368-378. ⟨10.1016/j.neucom.2022.04.097⟩. ⟨hal-04465658⟩
3 View
3 Download

Altmetric

Share

Gmail Facebook X LinkedIn More