GluGAN: Generating Personalized Glucose Time Series Using Generative Adversarial Networks
- 3 May 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 27 (10) , 5122-5133
Abstract
Time series data generated by continuous glucose monitoring sensors offer unparalleled opportunities for developing data-driven approaches, especially deep learning-based models, in diabetes management. Although these approaches have achieved state-of-the-art performance in various fields such as glucose prediction in type 1 diabetes (T1D), challenges remain in the acquisition of large-scale individual data for personalized modeling due to the elevated cost of clinical trials and data privacy regulations. In this work, we introduce GluGAN, a framework specifically designed for generating personalized glucose time series based on generative adversarial networks (GANs). Employing recurrent neural network (RNN) modules, the proposed framework uses a combination of unsupervised and supervised training to learn temporal dynamics in latent spaces. Aiming to assess the quality of synthetic data, we apply clinical metrics, distance scores, and discriminative and predictive scores computed by post-hoc RNNs in evaluation. Across three clinical datasets with 47 T1D subjects (including one publicly available and two proprietary datasets), GluGAN achieved better performance for all the considered metrics when compared with four baseline GAN models. The performance of data augmentation is evaluated by three machine learning-based glucose predictors. Using the training sets augmented by GluGAN significantly reduced the root mean square error for the predictors over 30 and 60-minute horizons. The results suggest that GluGAN is an effective method in generating high-quality synthetic glucose time series and has the potential to be used for evaluating the effectiveness of automated insulin delivery algorithms and as a digital twin to substitute for pre-clinical trials.Keywords
Funding Information
- Engineering and Physical Sciences Research Council (EP/P00993X/1)
- President's Ph.D. Scholarship at Imperial College London,
This publication has 35 references indexed in Scilit:
- The changing face of diabetes complicationsThe Lancet Diabetes & Endocrinology, 2016
- One-Day Bayesian Cloning of Type 1 Diabetes Subjects: Toward a Single-Day UVA/Padova Type 1 Diabetes SimulatorIEEE Transactions on Biomedical Engineering, 2016
- The UVA/PADOVA Type 1 Diabetes SimulatorJournal of Diabetes Science and Technology, 2014
- Multivariate Prediction of Subcutaneous Glucose Concentration in Type 1 Diabetes Patients Based on Support Vector RegressionIEEE Journal of Biomedical and Health Informatics, 2013
- Comparative Analysis of the Efficacy of Continuous Glucose Monitoring and Self-Monitoring of Blood Glucose in Type 1 Diabetes MellitusJournal of Diabetes Science and Technology, 2012
- A history of blood glucose meters and their role in self-monitoring of diabetes mellitusBritish Journal of Biomedical Science, 2012
- Estimating Plasma Glucose from Interstitial Glucose: The Issue of Calibration Algorithms in Commercial Continuous Glucose Monitoring DevicesSensors, 2010
- Principal component analysisWIREs Computational Statistics, 2010
- Continuous Glucose Monitoring and Intensive Treatment of Type 1 DiabetesNew England Journal of Medicine, 2008
- Self-Monitoring of Blood Glucose: The BasicsClinical Diabetes, 2002