Key result
Conditional Generative Adversarial Network generates 40,000 days of synthetic CGM data capturing real-world features.
Why the study?
Heterogeneous data sources constitute a challenge for comparison of predictive continuous glucose monitoring models, motivating synthesis of realistic CGM signals.
A CGAN can synthesize realistic continuous glucose monitoring data, providing a large public database of synthetic signals for future predictive modeling studies.
This report describes how a Conditional Generative Adversarial Network (CGAN) was used to synthesize realistic continuous glucose monitoring systems (CGM) from healthy individuals and individuals with type 1 diabetes over a range of different HbA1c levels. The results showed that even though the CGAN generated data, did not perfectly reflect real world CGM, many of the important features were captured and reflected in the synthetic signals. It is briefly discussed how heterogenous data sources constitutes a challenge for comparison of predictive CGM models. Therefore 40,000 CGM days were generated by the trained CGAN, equivalent to 940,000 hours of synthetic CGM measurements. These data have been made available in a public database, which can be used as a reference in future studies.
No takes yet. Share an insight, caveat, or question.
Cichosz et al. (2021) studied Type 1 diabetes. Conditional Generative Adversarial Network (CGAN) vs. Real world CGM was evaluated on Synthesis of realistic continuous glucose monitoring signals. A Conditional Generative Adversarial Network generated 40,000 days of synthetic continuous glucose monitoring data that captured many important features of real-world signals.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: