Long-Term Prediction of Blood Glucose Levels in Type 1 Diabetes Using a CNN-LSTM-Based Deep Neural Network
JOURNAL OF DIABETES SCIENCE AND TECHNOLOGY(2023)
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.
MoreTranslated text
Key words
glucose forecasting,decision support systems,continuous glucose monitoring (CGM),artificial deep neural networks,convolutional neural network (CNN),long short-term memory (LSTM)
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined