A Machine Learning Approach to Minimize Nocturnal Hypoglycemic Events in Type 1 Diabetic Patients under Multiple Doses of Insulin

• Published in: Sensors (Basel, Switzerland) Switzerland), 2022-02, Vol.22 (4), p.1665
• Main Authors: Parcerisas, Adrià, Contreras, Ivan, Delecourt, Alexia, Bertachi, Arthur, Beneyto, Aleix, Conget, Ignacio, Viñals, Clara, Giménez, Marga, Vehi, Josep
• Format: Article
• Language: English
• Subjects: Algorithms; Analysis; Blood Glucose; Blood Glucose Self-Monitoring; Blood sugar monitoring; Carbohydrates; Care and treatment; Control algorithms; Dextrose; Diabetes; Diabetes Mellitus, Type 1 - drug therapy; Diabetes therapy; Diabetics; Exercise; Glucose; Humans; Hyperglycemia; Hypoglycemia; Hypoglycemic Agents - therapeutic use; Insulin; Insulin - therapeutic use; Insulin Infusion Systems; Machine Learning; Meals; multiple daily injections; Patients; Physicians; prediction model; Quality of life; Sleep; support vector machine; Type 1 diabetes
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s22041665

Nocturnal hypoglycemia (NH) is one of the most challenging events for multiple dose insulin therapy (MDI) in people with type 1 diabetes (T1D). The goal of this study is to design a method to reduce the incidence of NH in people with T1D under MDI therapy, providing a decision-support system and improving confidence toward self-management of the disease considering the dataset used by Bertachi et al. Different machine learning (ML) algorithms, data sources, optimization metrics and mitigation measures to predict and avoid NH events have been studied. In addition, we have designed population and personalized models and studied the generalizability of the models and the influence of physical activity (PA) on them. Obtaining 30 g of rescue carbohydrates (CHO) is the optimal value for preventing NH, so it can be asserted that this is the value with which the time under 70 mg/dL decreases the most, with almost a 35% reduction, while increasing the time in the target range by 1.3%. This study supports the feasibility of using ML techniques to address the prediction of NH in patients with T1D under MDI therapy, using continuous glucose monitoring (CGM) and a PA tracker. The results obtained prove that BG predictions can not only be critical in achieving safer diabetes management, but also assist physicians and patients to make better and safer decisions regarding insulin therapy and their day-to-day lives.