For people with Type 1 diabetes (T1D), forecasting of blood glucose (BG) can be used to effectively avoid hyperglycemia, hypoglycemia and associated complications. The latest continuous glucose monitoring (CGM) technology allows people to observe glucose in real-time. However, an accurate glucose forecast remains a challenge. In this work, we introduce GluNet, a framework that leverages on a personalized deep neural network to predict the probabilistic distribution of short-term (30–60 minutes) future CGM measurements for subjects with T1D based on their historical data including glucose measurements, meal information, insulin doses, and other factors. It adopts the latest deep learning techniques consisting of four components: data pre-processing, label transform/recover, multi-layers of dilated convolution neural network (CNN), and post-processing. The method is evaluated in-silico for both adult and adolescent subjects. The results show significant improvements over existing methods in the literature through a comprehensive comparison in terms of root mean square error (RMSE) ($\text{8.88} \pm \text{0.77}$ mg/dL) with short time lag ($\text{0.83}\pm \text{0.40}$ minutes) for prediction horizons (PH) = 30 mins (minutes), and RMSE ($\text{19.90} \pm \text{3.17}$ mg/dL) with time lag ($\text{16.43}\pm \text{4.07}$ mins) for PH = 60 mins for virtual adult subjects. In addition, GluNet is also tested on two clinical data sets. Results show that it achieves an RMSE ($\text{19.28} \pm \text{2.76}$ mg/dL) with time lag ($\text{8.03}\pm \text{4.07}$ mins) for PH = 30 mins and an RMSE ($\text{31.83} \pm \text{3.49}$ mg/dL) with time lag ($\text{17.78}\pm \text{8.00}$ mins) for PH = 60 mins. These are the best reported results for glucose forecasting when compared with other methods including the neural network for predicting glucose (NNPG), the support vector regression (SVR), the latent variable with exogenous input (LVX), and the auto regression with exogenous input (ARX) algorithm.

中文翻译：

---

GluNet：准确预测葡萄糖的深度学习框架

对于患有1型糖尿病（T1D）的人，血糖预测（BG）可用于有效避免高血糖，低血糖和相关并发症。最新的连续葡萄糖监测（CGM）技术使人们可以实时观察葡萄糖。但是，准确的血糖预测仍然是一个挑战。在这项工作中，我们介绍了GluNet，该框架利用个性化深度神经网络来预测T1D受试者的短期（30–60分钟）未来CGM测量的概率分布，这些受试者基于他们的历史数据（包括血糖测量，膳食）信息，胰岛素剂量和其他因素。它采用了最新的深度学习技术，该技术由四个部分组成：数据预处理，标签转换/恢复，多层卷积神经网络（CNN），和后处理。方法评估电脑内适用于成人和青少年受试者。结果表明，通过对均方根误差（RMSE）进行全面比较，可以对文献中的现有方法进行重大改进（$ \ text {8.88} \ pm \ text {0.77} $ 毫克/分升）短时滞（$ \ text {0.83} \ pm \ text {0.40} $ 预测范围（PH）= 30分钟（分钟），RMSE（$ \ text {19.90} \ pm \ text {3.17} $ 毫克/分升），具有时滞（$ \ text {16.43} \ pm \ text {4.07} $对于虚拟成人受试者，PH = 60分钟）。此外，GluNet还通过​​两个临床数据集进行了测试。结果表明，它达到了RMSE（$ \ text {19.28} \ pm \ text {2.76} $ 毫克/分升），具有时滞（$ \ text {8.03} \ pm \ text {4.07} $ PH = 30分钟和RMSE（分钟）$ \ text {31.83} \ pm \ text {3.49} $ 毫克/分升），具有时滞（$ \ text {17.78} \ pm \ text {8.00} $ PH = 60分钟。与其他方法（包括用于预测葡萄糖的神经网络（NNPG），支持向量回归（SVR），具有外源输入的潜变量（LVX）和具有外源输入的自动回归等方法相比，这些是葡萄糖预测的最佳报告结果（ARX）算法。