Long-Term Prediction of Blood Glucose Levels in Type 1 Diabetes Using a CNN-LSTM-Based Deep Neural Network

Abstract

Background: In this work, we leverage state-of-the-art deep learning–based algorithms for blood glucose (BG) forecasting in people with type 1 diabetes. Methods: We propose stacks of convolutional neural network and long short-term memory units to predict BG level for 30-, 60-, and 90-minute prediction horizon (PH), given historical glucose measurements, meal information, and insulin intakes. The evaluation was performed on two data sets, Replace-BG and DIAdvisor, representative of free-living conditions and in-hospital setting, respectively. Results: For 90-minute PH, our model obtained mean absolute error of 17.30 ± 2.07 and 18.23 ± 2.97 mg/dL, root mean square error of 23.45 ± 3.18 and 25.12 ± 4.65 mg/dL, coefficient of determination of 84.13 ± 4.22% and 82.34 ± 4.54%, and in terms of the continuous glucose-error grid analysis 94.71 ± 3.89% and 91.71 ± 4.32% accurate predictions, 1.81 ± 1.06% and 2.51 ± 0.86% benign errors, and 3.47 ± 1.12% and 5.78 ± 1.72% erroneous predictions, for Replace-BG and DIAdvisor data sets, respectively. Conclusion: Our investigation demonstrated that our method achieved superior glucose forecasting compared with existing approaches in the literature, and thanks to its generalizability showed potential for real-life applications.

Machine Learning and Deep Learning Models for Nocturnal High- and Low-Glucose Prediction in Adults with Type 1 Diabetes

“…In many studies, the authors focused on forecasting events such as nocturnal hypoglycemia [11][12][13][14][15][16][17]. Other studies predicted interstitial glucose values [21][22][23][24][25][26][27][28]. In this study, we proposed a different approach for glucose prediction by classifying the predicted values into three ranges.…”

“…In studies forecasting nocturnal hypoglycemia, the values of ROC-AUC exceeded 70%, indicating an acceptable sensitivity and specificity [11][12][13][14][15][16][17]. In studies predicting glucose levels, the root mean squared error varied from 0.36 to 1.95 mmol/L (6.45-35.10 mg/dL) at PH values up to 120 minutes [21][22][23][24][25][26][27][28]. In the aforementioned study by Guemes et al, which addressed the problem of classifying future glucose levels into the target and non-target ranges, the model was able to predict the quality of overnight glycemic control with reasonable accuracy (AUC-ROC = 0.7) [41].…”

“…Song et al developed a method of forecast that combines empirical mode decomposition with long short-term memory (LSTM) [21]. Jaloli and Cescon proposed stacks of convolutional neural networks (CNNs) and LSTM units to predict glucose levels, taking into account historical glucose data, meal information, and insulin intakes [22]. Zhu et al introduced a DL model based on a dilated recurrent neural network and, later, a fast-adaptive and confident neural network for glucose prediction in patients with T1D [23,24].…”

Glu-Ensemble: An ensemble deep learning framework for blood glucose forecasting in type 2 diabetes patients

“…This, in turn, facilitates better control of blood glucose and mitigates the risk of complications associated with diabetes [ [22] , [23] , [24] ]. Various approaches, including statistical models [ [25] , [26] , [27] ], machine learning algorithms [ [28] , [29] , [30] , [31] ], and artificial neural networks [ [32] , [33] , [34] , [35] , [36] , [37] , [38] , [39] ], have been explored for predicting blood glucose levels. Statistical models, which utilize mathematical equations to project future blood glucose levels based on past data, insulin doses, and other pertinent factors, are among the simplest and most prevalent methods.…”

A Hybrid Big Data Analytics Approach for Predicting Type II Diabetes Using H-SMOTE Tree

“…According to the World Health Organization, eighty percent or more of the deaths in Ebola-affected countries occur in low-and middle-income countries that lack both basic and sophisticated healthcare services. The "diabetes capital of the world" is located in India, a growing country with a huge diabetic population [20][21][22][23].…”