Multivariate Prediction of Subcutaneous Glucose Concentration in Type 1 Diabetes Patients Based on Support Vector Regression

Abstract

Data-driven techniques have recently drawn significant interest in the predictive modeling of subcutaneous (s.c.) glucose concentration in type 1 diabetes. In this study, the s.c. glucose prediction is treated as a multivariate regression problem, which is addressed using support vector regression (SVR). The proposed method is based on variables concerning: (i) the s.c. glucose profile, (ii) the plasma insulin concentration, (iii) the appearance of meal-derived glucose in the systemic circulation, and (iv) the energy expenditure during physical activities. Six cases corresponding to different combinations of the aforementioned variables are used to investigate the influence of the input on the daily glucose prediction. The proposed method is evaluated using a dataset of 27 patients in free-living conditions. 10-fold cross validation is applied to each dataset individually to both optimize and test the SVR model. In the case where all the input variables are considered, the average prediction errors are 5.21, 6.03, 7.14 and 7.62 mg/dl for 15, 30, 60 and 120 min prediction horizons, respectively. The results clearly indicate that the availability of multivariable data and their effective combination can significantly increase the accuracy of both short-term and long-term predictions.

How Much Is Short-Term Glucose Prediction in Type 1 Diabetes Improved by Adding Insulin Delivery and Meal Content Information to CGM Data? A Proof-of-Concept Study

“…Gaussian processes using a variety of inputs, such as glucose history, time of the day, plasma insulin concentration, effect of food intake, and energy expenditure [17][18][19] -neural networks using insulin and CHO information; 15 self-monitoring of blood glucose (SMBG) readings; information on insulin, CHO, and hypo-and hyperglycemic symptoms; lifestyle, activity, and emotions; 20 and information on CHO only 21,22 None of these studies systematically evaluated how much each individual input can improve the prediction of glucose concentration.…”

Interpretation of Long-Term Clinical Diabetes Data and Prediction of Glycemic Control Based on Data Mining Techniques

“…support vector regression (SVR) and Gaussian processes (GP) [12]. In both techniques, a non-linear function of the form:…”

“…In particular, both linear [8], [9] and non-linear data driven approaches [10]- [12] have been proposed for the short-term (up to 60 min) prediction of the subcutaneous (s.c.) glucose concentration using information on meals, insulin therapy and physical activity in tandem with the glucose time series. In [13], the fusion of recurrent neural networks and autoregressive models resulted in 100% prediction accuracy of hypoglycemic events with 16.7 min time lag and 0.8 daily false alarms.…”

“…In this paper, our recent work on the short-term prediction of glucose concentration [12] and hypoglycemic events in type 1 diabetes [14] is presented. In addition, we delineate the data mining techniques used for extracting new medical knowledge and predicting long-term glucose control.…”

An Early Warning System for Hypoglycemic/Hyperglycemic Events Based on Fusion of Adaptive Prediction Models

“…In all cases, they outperformed the feed-forward ANNs. 19 A new method has been proposed in which glucose prediction is based on support vector regression 20 using information of insulin food and physical activity.…”