Machine learning-based glucose prediction with use of continuous glucose and physical activity monitoring data: The Maastricht Study

Abstract

Background Closed-loop insulin delivery systems, which integrate continuous glucose monitoring (CGM) and algorithms that continuously guide insulin dosing, have been shown to improve glycaemic control. The ability to predict future glucose values can further optimize such devices. In this study, we used machine learning to train models in predicting future glucose levels based on prior CGM and accelerometry data. Methods We used data from The Maastricht Study, an observational population‐based cohort that comprises individuals with normal glucose metabolism, prediabetes, or type 2 diabetes. We included individuals who underwent >48h of CGM (n = 851), most of whom (n = 540) simultaneously wore an accelerometer to assess physical activity. A random subset of individuals was used to train models in predicting glucose levels at 15- and 60-minute intervals based on either CGM data or both CGM and accelerometer data. In the remaining individuals, model performance was evaluated with root-mean-square error (RMSE), Spearman’s correlation coefficient (rho) and surveillance error grid. For a proof-of-concept translation, CGM-based prediction models were optimized and validated with the use of data from individuals with type 1 diabetes (OhioT1DM Dataset, n = 6). Results Models trained with CGM data were able to accurately predict glucose values at 15 (RMSE: 0.19mmol/L; rho: 0.96) and 60 minutes (RMSE: 0.59mmol/L, rho: 0.72). Model performance was comparable in individuals with type 2 diabetes. Incorporation of accelerometer data only slightly improved prediction. The error grid results indicated that model predictions were clinically safe (15 min: >99%, 60 min >98%). Our prediction models translated well to individuals with type 1 diabetes, which is reflected by high accuracy (RMSEs for 15 and 60 minutes of 0.43 and 1.73 mmol/L, respectively) and clinical safety (15 min: >99%, 60 min: >91%). Conclusions Machine learning-based models are able to accurately and safely predict glucose values at 15- and 60-minute intervals based on CGM data only. Future research should further optimize the models for implementation in closed-loop insulin delivery systems.

Wearable chemical sensors for biomarker discovery in the omics era

“…Looking at regression models, long short-term memory (a neural network algorithm capable of learning sequenced dependencies) was used to predict future blood glucose levels based on continuous monitoring data 159 . Biophysical markers recorded from wearable sensors (heart rate, blood pressure), physical characteristics (weight, age, gender) and blood glucose data measured from a glucometer over 6 h were combined to predict blood glucose concentration with a 15-min horizon (predicting the concentration 15 min ahead of the actual measurement) and an average error of 15.43 mg dl –1 (ref.…”

Chinese diabetes datasets for data-driven machine learning

“…T2DM datasets were less common than T1DM datasets 27 , 28 . A CGM data from both the T1DM and T2DM patients were employed to predict future BG levels for preventing hyperglycemia or hypoglycemia 29 , which was collected over a period ranging from 1.3 to 7 days.…”

Identifying Differential Equations to predict Blood Glucose using Sparse Identification of Nonlinear Systems

“…The evolution of blood glucose levels of diabetic patients has already been modelled using different machine learning methods such as support vector machines, gradient-boosting, or different types of neural networks. To better represent and analyse the dynamic behaviour of blood glucose, methods that provide less complex and more interpretable models are preferable [4]. Additionally to those static models the advantage of the usage of differential equations to predict the blood glucose dynamics is part of various research approaches.…”