Nocturnal hypoglycemia (NH) is a dangerous complication of insulin therapy that often goes undetected. In this study, we aimed to generate machine learning (ML)-based models for short-term NH prediction in hospitalized patients with type 1 diabetes (T1D). The models were trained on continuous glucose monitoring (CGM) data obtained from 406 adult patients admitted to a tertiary referral hospital. Eight CGM-derived metrics of glycemic control and glucose variability were included in the models. Combinations of CGM and clinical data (23 parameters) were also assessed. Random Forest (RF), Logistic Linear Regression with Lasso regularization, and Artificial Neuron Networks algorithms were applied. In our models, RF provided the best prediction accuracy with 15 min and 30 min prediction horizons. The addition of clinical parameters slightly improved the prediction accuracy of most models, whereas oversampling and undersampling procedures did not have significant effects. The areas under the curve of the best models based on CGM and clinical data with 15 min and 30 min prediction horizons were 0.97 and 0.942, respectively. Basal insulin dose, diabetes duration, proteinuria, and HbA1c were the most important clinical predictors of NH assessed by RF. In conclusion, ML is a promising approach to personalized prediction of NH in hospitalized patients with T1D.

Glucose management at night is a major challenge for people with type 1 diabetes (T1D), especially for those managed with multiple daily injections (MDIs). In this study, we developed machine learning (ML) and deep learning (DL) models to predict nocturnal glucose within the target range (3.9–10 mmol/L), above the target range, and below the target range in subjects with T1D managed with MDIs. The models were trained and tested on continuous glucose monitoring data obtained from 380 subjects with T1D. Two DL algorithms—multi-layer perceptron (MLP) and a convolutional neural network (CNN)—as well as two classic ML algorithms, random forest (RF) and gradient boosting trees (GBTs), were applied. The resulting models based on the DL and ML algorithms demonstrated high and similar accuracy in predicting target glucose (F1 metric: 96–98%) and above-target glucose (F1: 93–97%) within a 30 min prediction horizon. Model performance was poorer when predicting low glucose (F1: 80–86%). MLP provided the highest accuracy in low-glucose prediction. The results indicate that both DL (MLP, CNN) and ML (RF, GBTs) algorithms operating CGM data can be used for the simultaneous prediction of nocturnal glucose values within the target, above-target, and below-target ranges in people with T1D managed with MDIs.

This review presents the applications of artificial intelligence for the study of the mechanisms of diabetes development and generation of new technologies of its prevention, monitoring and treatment. In recent years, a huge amount of molecular data has been accumulated, revealing the pathogenic mechanisms of diabetes and its complications. Data mining and text mining open up new possibilities for processing this information. Analysis of gene networks makes it possible to identify molecular interactions that are important for the development of diabetes and its complications, as well as to identify new targeted molecules. Based on the big data analysis and machine learning, new platforms have been created for prediction and screening of diabetes, diabetic retinopathy, chronic kidney disease, and cardiovascular disease. Machine learning algorithms are applied for personalized prediction of glucose trends, in the closed-loop insulin delivery systems and decision support systems for lifestyle modification and diabetes treatment. The use of artificial intelligence for the analysis of large databases, registers, and real-world evidence studies seems to be promising. The introduction of artificial intelligence systems is in line with global trends in modern medicine, including the transition to digital and distant technologies, personification of treatment, high-precision forecasting and patient-centered care. There is an urgent need for further research in this field, with an assessment of the clinical effectiveness and economic feasibility.