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 $\pm$ 0.71 [mg/dL] over a 30-min horizon, RMSE = 18.87 $\pm$ 2.25 [mg/dL] over a 60-min horizon) and real patient cases (RMSE = 21.07 $\pm$ 2.35 [mg/dL] for 30 min, RMSE = 33.27 $\pm$ 4.79% for 60 min). In addition, the model provides competitive performance in providing effective prediction horizon ($\text{PH}_{\text{eff}}$) with minimal time lag both in a simulated patient dataset ($\text{PH}_{\text{eff}}$ = 29.0 $\pm$ 0.7 for 30 min and $\text{PH}_{\text{eff}}$ = 49.8 $\pm$ 2.9 for 60 min) and in a real patient dataset ($\text{PH}_{\text{eff}}$ = 19.3 $\pm$ 3.1 for 30 min and $\text{PH}_{\text{eff}}$ = 29.3 $\pm$ 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.

中文翻译：

---

卷积递归神经网络用于葡萄糖预测

血糖控制对于糖尿病管理至关重要。当前用于患有1型糖尿病的受试者的数字治疗方法（例如人工胰腺和胰岛素推注计算器）利用机器学习技术来预测皮下葡萄糖，以改善控制效果。深度学习最近已在医疗保健和医学研究中应用，以在包括疾病诊断和患者状态预测在内的一系列任务中获得最先进的结果。在本文中，我们提出了一种深度学习模型，该模型能够以模拟患者的领先准确度预测血糖水平（均方根误差（RMSE）= 9.38 $ \ pm $ 在30分钟的视线范围内为0.71 [mg / dL]，RMSE = 18.87 $ \ pm $ 60分钟内为2.25 [mg / dL]）和实际患者病例（RMSE = 21.07） $ \ pm $ 2.35 [mg / dL]，持续30分钟，RMSE = 33.27 $ \ pm $60分钟的4.79％）。此外，该模型在提供有效的预测范围（$ \ text {PH} _ {\ text {eff}} $）在模拟的患者数据集中都具有最小的时间滞后（$ \ text {PH} _ {\ text {eff}} $ = 29.0 $ \ pm $ 0.7 30分钟，然后 $ \ text {PH} _ {\ text {eff}} $ = 49.8 $ \ pm $ 2.9分钟（60分钟）并在真实的患者数据集中（$ \ text {PH} _ {\ text {eff}} $ = 19.3 $ \ pm $ 3.1 30分钟，然后 $ \ text {PH} _ {\ text {eff}} $ = 29.3 $ \ pm $9.4分钟）。在从UVA / Padova模拟器生成的10个模拟病例的数据集和10个真实病例的临床数据集上评估了该方法，每个病例包含葡萄糖读数，胰岛素推注和膳食（碳水化合物）数据。循环卷积神经网络的性能针对四种算法进行了基准测试。所提出的算法是在Android手机上实现的，手机上的执行时间为6毫秒，而笔记本电脑上的执行时间为780毫秒。