Gu Kang, Dang Ruoqi, Prioleau Temiloluwa
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:5476-5481. doi: 10.1109/EMBC44109.2020.9176004.
Continuous glucose monitors (CGM) and insulin pumps are becoming increasingly important in diabetes management. Additionally, data streams from these devices enable the prospect of accurate blood glucose prediction to support patients in preventing adverse glycemic events. In this paper, we present Neural Physiological Encoder (NPE), a simple module that leverages decomposed convolutional filters to automatically generate effective features that can be used with a downstream neural network for blood glucose prediction. To our knowledge, this is the first work to investigate a decomposed architecture in the diabetes domain. Our experimental results show that the proposed NPE model can effectively capture temporal patterns and blood glucose associations with other daily activities. For predicting blood glucose 30-mins in advance, NPE+LSTM yields an average root mean square error (RMSE) of 9.18 mg/dL on an in-house diabetes dataset from 34 subjects. Additionally, it achieves state-of-the-art RMSE of 17.80 mg/dL on a publicly available diabetes dataset (OhioT1DM) from 6 subjects.
连续血糖监测仪（CGM）和胰岛素泵在糖尿病管理中变得越来越重要。此外，这些设备的数据流使准确预测血糖成为可能，从而帮助患者预防不良血糖事件。在本文中，我们提出了神经生理编码器（NPE），这是一个简单的模块，它利用分解的卷积滤波器自动生成有效的特征，这些特征可与下游神经网络一起用于血糖预测。据我们所知，这是第一项在糖尿病领域研究分解架构的工作。我们的实验结果表明，所提出的NPE模型可以有效地捕捉时间模式以及血糖与其他日常活动的关联。对于提前30分钟预测血糖，在来自34名受试者的内部糖尿病数据集上，NPE + LSTM的平均均方根误差（RMSE）为9.18 mg/dL。此外，在来自6名受试者的公开可用糖尿病数据集（OhioT1DM）上，它实现了17.80 mg/dL的最新RMSE。
