Abstract
AbstractThe ability to anticipate changes in blood glucose (BG) concentration would have a great impact on Type 1 diabetics (T1D). In order to create T1D treatment plans, patients collect a BG concentration time series. It has been demonstrated that various types of recurrent neural networks, such as Long Short Term Memory (LSTM), have success forecasting T1D BG concentrations. However, limited work has been done to characterize the T1D time series or set limits on neural network’s predictive capacity. In this work, a T1D patient’s 14 day BG concentration time series is studied. First, I test the time series stationarity. Then I use auto-correlation analysis, spectral analysis, and Gaussian process regression to characterize the T1D BG time series. Finally, the LSTM’s prediction quality is quantified and interpreted at different prediction intervals. The success or failure of the LSTM’s predictions are interpreted using the characterization of the time series.
Publisher
Cold Spring Harbor Laboratory
Reference21 articles.
1. CEUR Workshop Proceedings. Automatic blood glucose prediction with confidence using recurrent neural networks, 2018.
2. S. Pappada , B. Cameron , and P. Rosman . Development of a neural network for prediction of glucose concentration in type 1 diabetes patients. J Diabetes Sci Technol, page 792–801, 2008.
3. 14th Symposium on Neural Networks and Applications (NEUREL) Belgrade. Predicting Blood Glucose with an LSTM and Bi-LSTM Based Deep Neural Network, 2018.
4. ICMLC ‘19: Proceedings of the 2019 11th International Conference on Machine Learning and Computing. Blood Glucose Level Prediction with Minimal Inputs Using Feedforward Neural Network for Diabetic Type 1 Patients, 2019.
5. Continuous blood glucose level prediction of type 1 diabetes based on artificial neural network;Biocybernetics and Biomedical Engineering,2018