Neural identification of Type 1 Diabetes Mellitus for care and forecasting of risk events. (30th November 2021)

• Record Type: Journal Article
• Authors: Sanchez, Oscar D.; Alanis, Alma Y.; Ruiz Velázquez, E.; Valencia Murillo, Roberto
• Is Part Of: Expert systems with applications. Volume 183(2021)
• Publication Date: 2021-11-30
• Subjects: Type 1 Diabetes Mellitus -- Neural network -- Identification -- Multi-step ahead predictor -- RHONN; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2021.115367
• Languages: English
• ISSNs: 0957-4174

Abstract

Abstract: Glucose–insulin models, testing glucose sensors and support systems for health care decisions play an important role in synthesis of glucose control algorithms. In this work we propose an online glucose–insulin identification using the Recurrent High Order Neural Network (RHONN). Then, the model obtained is used to predict n -steps forward of glucose levels, also by RHONN. The used data for identification is from a Type 1 Diabetes Mellitus (T1DM) patient, it was collected from the Continuous Monitoring Glucose System (CMGS) by MiniMed Inc ® and an insulin pump by Paradigm Real-time Insulin Pump ®. RHONN is trained online by Extended Kalman Filter (EKF). The results suggest that it is possible to make a prediction of up to 35 min in the future, which it would help to prevent risky events (hypoglycemia and hyperglycemia). Also shows that, it could be directly connected to a CGMS to help the patient improve the glucose control and even an automatic glucose control algorithm. The proposed Neural Network shows good performance compared to baseline methods in terms of evaluation criteria. Highlights: With RHOON we perform identification of the dynamics of blood glucose. 35 min of blood glucose were predicted with RHONN. Training for the identification and prediction network was done online. RHONN predictions are compared with three methods.