Abstract
In the daily management of type 1 diabetes (T1D), determining the correct insulin dose to be injected at meal-time is fundamental to achieve optimal glycemic control. Wearable sensors, such as continuous glucose monitoring (CGM) devices, are instrumental to achieve this purpose. In this paper, we show how CGM data, together with commonly recorded inputs (carbohydrate intake and bolus insulin), can be used to develop an algorithm that allows classifying, at meal-time, the post-prandial glycemic status (i.e., blood glucose concentration being too low, too high, or within target range). Such an outcome can then be used to improve the efficacy of insulin therapy by reducing or increasing the corresponding meal bolus dose. A state-of-the-art T1D simulation environment, including intraday variability and a behavioral model, was used to generate a rich in silico dataset corresponding to 100 subjects over a two-month scenario. Then, an extreme gradient-boosted tree (XGB) algorithm was employed to classify the post-prandial glycemic status. Finally, we demonstrate how the XGB algorithm outcome can be exploited to improve glycemic control in T1D through real-time adjustment of the meal insulin bolus. The proposed XGB algorithm obtained good accuracy at classifying post-prandial glycemic status (AUROC = 0.84 [0.78, 0.87]). Consequently, when used to adjust, in real-time, meal insulin boluses obtained with a bolus calculator, the proposed approach improves glycemic control when compared to the baseline bolus calculator. In particular, percentage time in target [70, 180] mg/dL was improved from 61.98 (±13.89) to 67.00 (±11.54; p < 0.01) without increasing hypoglycemia.
Highlights
Type 1 diabetes (T1D) is a lifelong condition characterized by the destruction of the pancreatic beta cells responsible for insulin production
In type 1 diabetes (T1D) management, continuous glucose monitors, insulin pumps, and activity monitors, together with additional physiological data streams can be used to develop new algorithms aimed at improving standard insulin therapy [33,34]
A new methodology based on a state-of-the-art machine learning model, i.e., the extreme gradient-boosted tree (XGB) model, is used to predict at meal-time postprandial glycemic status
Summary
Type 1 diabetes (T1D) is a lifelong condition characterized by the destruction of the pancreatic beta cells responsible for insulin production. Insulin is exogenously injected either via multiple daily injections (MDI), consisting of fast-acting insulin performed at meal-time (bolus insulin) and a long-acting dose once (or twice) per day, or via an infusion pump (i.e., continuous subcutaneous insulin infusion). Titration of such doses is usually done. CGM and additional data streams obtained from wearable devices, such as activity monitors, can provide important real-time information on the current status of the diabetic individual, and appear to be suitable to develop new “smarter” tools to empower people with T1D with decision support to improve the management of their condition [6,7]. Additional improvements can be achieved if, in addition to using information at meal-time, a prediction of postprandial glycemic status, i.e., future BG being too low, too high, or within a target range; is accounted for [10,11]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
