Abstract
Continuous monitoring of blood glucose (BG) levels is a key aspect of diabetes management. Patients with Type-1 diabetes (T1D) require an effective tool to monitor these levels in order to make appropriate decisions regarding insulin administration and food intake to keep BG levels in target range. Effectively and accurately predicting future BG levels at multi-time steps ahead benefits a patient with diabetes by helping them decrease the risks of extremes in BG including hypo- and hyperglycemia. In this study, we present a novel multi-component deep learning model BG-Predict that predicts the BG levels in a multi-step look ahead fashion. The model is evaluated both quantitatively and qualitatively on actual blood glucose data for 97 patients. For the prediction horizon (PH) of 30 mins, the average values for root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and normalized mean squared error (NRMSE) are 23.22 pm 6.39 mg/dL, 16.77 ± 4.87 mg/dL, 12.84 pm 3.68 and 0.08 pm 0.01 respectively. When Clarke and Parkes error grid analyses were performed comparing predicted BG with actual BG, the results showed average percentage of points in Zone A of 80.17 pm 9.20 and 84.81 pm 6.11, respectively. We offer this tool as a mechanism to enhance the predictive capabilities of algorithms for patients with T1D.
Highlights
Continuous monitoring of blood glucose (BG) levels is a key aspect of diabetes management
The experiments were conducted on Tidepool (More information on https://www.tidepool.org/) datasets provided by the Juvenile Diabetes Research Foundation (JDRF) (More information on https://www.jdrf.org/)
We present here a novel deep learning based model to predict future BG of Type-1 diabetes (T1D) patients in a multi-step ahead manner
Summary
Continuous monitoring of blood glucose (BG) levels is a key aspect of diabetes management. Emotional stress can trigger hyperglycemia while physical activity can enhance insulin sensitivity thereby causing hypoglycemia for several hours Capturing such variations in itself poses a unique challenge for any model to have enough predictive power to forecast BG levels. The study[3] provides a more comprehensive review on the use of physiological based approaches for modeling glucose-insulin systems These approaches[4,5,6] use insulin, meal intake, CGM signals and other variables such as physical activity, heart rate as inputs. Compartments that best explain the behavioural process between certain sub-system such as measuring glucose production and utilization, insulin action and meal absorption These approaches pose certain disadvantages such as identifying and establishing many parameters prior to making any predictions related to blood glucose values, making the model more cumbersome. Some of the ways to alleviate this issue is to make use of minimized version of these models[9,10] or make use of machine learning techniques for identification of parameters[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.
