Type 1 Diabetes Hypoglycemia Prediction Algorithms: Systematic Review

Abstract

Background Diabetes is a chronic condition that necessitates regular monitoring and self-management of the patient’s blood glucose levels. People with type 1 diabetes (T1D) can live a productive life if they receive proper diabetes care. Nonetheless, a loose glycemic control might increase the risk of developing hypoglycemia. This incident can occur because of a variety of causes, such as taking additional doses of insulin, skipping meals, or overexercising. Mainly, the symptoms of hypoglycemia range from mild dysphoria to more severe conditions, if not detected in a timely manner. Objective In this review, we aimed to report on innovative detection techniques and tactics for identifying and preventing hypoglycemic episodes, focusing on T1D. Methods A systematic literature search following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines was performed focusing on the PubMed, GoogleScholar, IEEEXplore, and ACM Digital Library to find articles on technologies related to hypoglycemia detection in patients with T1D. Results The presented approaches have been used or devised to enhance blood glucose monitoring and boost its efficacy in forecasting future glucose levels, which could aid the prediction of future episodes of hypoglycemia. We detected 19 predictive models for hypoglycemia, specifically on T1D, using a wide range of algorithmic methodologies, spanning from statistics (1.9/19, 10%) to machine learning (9.88/19, 52%) and deep learning (7.22/19, 38%). The algorithms used most were the Kalman filtering and classification models (support vector machine, k-nearest neighbors, and random forests). The performance of the predictive models was found to be satisfactory overall, reaching accuracies between 70% and 99%, which proves that such technologies are capable of facilitating the prediction of T1D hypoglycemia. Conclusions It is evident that continuous glucose monitoring can improve glucose control in diabetes; however, predictive models for hypo- and hyperglycemia using only mainstream noninvasive sensors such as wristbands and smartwatches are foreseen to be the next step for mobile health in T1D. Prospective studies are required to demonstrate the value of such models in real-life mobile health interventions.

Use of machine learning to identify characteristics associated with severe hypoglycemia in older adults with type 1 diabetes: a post-hoc analysis of a case–control study

“…Machine learning methods have been used in other studies for a variety of applications for people with type 1 diabetes including for predicting hypoglycemia. Those studies often used CGM data to predict the risk of hypoglycemia in the shorter term 30–32. Additionally, these usually involved individuals who were younger with shorter diabetes duration and aimed to understand the risk of hypoglycemia in the immediate future based on CGM data.…”

Layered Meta-Learning Algorithm for Predicting Adverse Events in Type 1 Diabetes

“…A wide-ranging analysis of the state of the art shows that tests are usually performed on private datasets, therefore it is difficult to make a fair comparison between the various algorithms. In other cases, tests are performed on data from in silico patients [43], [44], generated using T1DM simulators [45], [46]; nonetheless, the results achieved using virtual patients usually overestimate the model predictive capability because real-life complications such as physical activity, stress and illness are not taken into consideration [47]. However, a public dataset composed of data from six real subjects is available since 2018 [14] and that has been afterward enlarged with data from six more subjects [15].…”

Patent analysis of digital sensors for continuous glucose monitoring

“…Achieving optimal and sustained glycemic control is one of the most effective approaches to prevent complications and reduce mortality in patients with DM. Glycemic variability is a key therapeutic focus in the treatment of diabetic patients (2)(3)(4)(5).…”