A convolutional recurrent neural network forecasted blood glucose levels in real Type 1 diabetes patients with an RMSE of 21.07 mg/dL over a 30-minute horizon and 33.27 mg/dL over a 60-minute horizon.
Does a convolutional recurrent neural network improve glucose prediction accuracy in simulated and real type 1 diabetes cases compared to benchmark algorithms?
A deep learning model using convolutional recurrent neural networks provides accurate and computationally efficient short-term glucose prediction for type 1 diabetes management.
Control of blood glucose is essential for diabetes management. Current digital therapeutic approaches for subjects with type 1 diabetes mellitus such as the artificial pancreas and insulin bolus calculators leverage machine learning techniques for predicting subcutaneous glucose for improved control. Deep learning has recently been applied in healthcare and medical research to achieve state-of-the-art results in a range of tasks including disease diagnosis, and patient state prediction among others. In this paper, we present a deep learning model that is capable of forecasting glucose levels with leading accuracy for simulated patient cases (root-mean-square error (RMSE) = 9.38 ± 0.71 mg/dL over a 30-min horizon, RMSE = 18.87 ± 2.25 mg/dL over a 60-min horizon) and real patient cases (RMSE = 21.07 ± 2.35 mg/dL for 30 min, RMSE = 33.27 ± 4.79% for 60 min). In addition, the model provides competitive performance in providing effective prediction horizon (Formula: see text) with minimal time lag both in a simulated patient dataset (Formula: see text = 29.0 ± 0.7 for 30 min and Formula: see text = 49.8 ± 2.9 for 60 min) and in a real patient dataset (Formula: see text = 19.3 ± 3.1 for 30 min and Formula: see text = 29.3 ± 9.4 for 60 min). This approach is evaluated on a dataset of ten simulated cases generated from the UVA/Padova simulator and a clinical dataset of ten real cases each containing glucose readings, insulin bolus, and meal (carbohydrate) data. Performance of the recurrent convolutional neural network is benchmarked against four algorithms. The proposed algorithm is implemented on an Android mobile phone, with an execution time of 6 ms on a phone compared to an execution time of 780 ms on a laptop.
Li et al. (Mon,) conducted a other in Type 1 diabetes mellitus (n=20). Convolutional Recurrent Neural Network (CRNN) vs. NNPG, SVR, LVX, and ARX algorithms was evaluated on Root-mean-square error (RMSE) for 30-minute glucose prediction in real patients. A convolutional recurrent neural network forecasted blood glucose levels in real Type 1 diabetes patients with an RMSE of 21.07 mg/dL over a 30-minute horizon and 33.27 mg/dL over a 60-minute horizon.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: