Abstract
(1) Background: nocturnal hypoglycemia (NH) is one of the most challenging side effects of multiple doses of insulin (MDI) therapy in type 1 diabetes (T1D). This work aimed to investigate the feasibility of a machine-learning-based prediction model to anticipate NH in T1D patients on MDI. (2) Methods: ten T1D adults were studied during 12 weeks. Information regarding T1D management, continuous glucose monitoring (CGM), and from a physical activity tracker were obtained under free-living conditions at home. Supervised machine-learning algorithms were applied to the data, and prediction models were created to forecast the occurrence of NH. Individualized prediction models were generated using multilayer perceptron (MLP) and a support vector machine (SVM). (3) Results: population outcomes indicated that more than 70% of the NH may be avoided with the proposed methodology. The predictions performed by the SVM achieved the best population outcomes, with a sensitivity and specificity of 78.75% and 82.15%, respectively. (4) Conclusions: our study supports the feasibility of using ML techniques to address the prediction of nocturnal hypoglycemia in the daily life of patients with T1D on MDI, using CGM and a physical activity tracker.
Highlights
Hypoglycemia is the most common side effect of insulin therapy in type 1 diabetes (T1D) and its frequency increases with tight glucose control
The glucometrics, including coefficient of variation (CV) and time within and above different target glucose ranges, demonstrate that the participants enrolled in our study correspond to a high glycemic variability and hypoglycemia prone group of T1D patients
Our results suggest that this prediction model seems to be helpful to anticipate nocturnal hypoglycemia in T1D patients on multiple doses of insulin (MDI), using continuous glucose monitoring (CGM) and a physical activity tracker during challenging, real-life situations
Summary
Hypoglycemia is the most common side effect of insulin therapy in type 1 diabetes (T1D) and its frequency increases with tight glucose control. It is associated with a range of morbidities, including cardiovascular events and even death due to arrhythmias [1,2]. The fear of hypoglycemia may cause some patients to deliberately maintain undesirable hyperglycemia to minimize the risk and severity of further episodes precluding the benefits of tight glycemic control [4,5]. In addition to this, repeated episodes of hypoglycemia induce so-called impaired awareness hypoglycemic (IAH) syndrome, which can lead to severe episodes [6].
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have