Rabby Md Fazle, Tu Yazhou, Hossen Md Imran, Lee Insup, Maida Anthony S, Hei Xiali
School of Computing and Informatics, The University of Louisiana at Lafayette, Lafayatte, LA, 70503, USA.
Department of Computer and Information Science, University of Pennsylvania, Philadelphia, PA, 19104, USA.
BMC Med Inform Decis Mak. 2021 Mar 16;21(1):101. doi: 10.1186/s12911-021-01462-5.
Blood glucose (BG) management is crucial for type-1 diabetes patients resulting in the necessity of reliable artificial pancreas or insulin infusion systems. In recent years, deep learning techniques have been utilized for a more accurate BG level prediction system. However, continuous glucose monitoring (CGM) readings are susceptible to sensor errors. As a result, inaccurate CGM readings would affect BG prediction and make it unreliable, even if the most optimal machine learning model is used.
In this work, we propose a novel approach to predicting blood glucose level with a stacked Long short-term memory (LSTM) based deep recurrent neural network (RNN) model considering sensor fault. We use the Kalman smoothing technique for the correction of the inaccurate CGM readings due to sensor error.
For the OhioT1DM (2018) dataset, containing eight weeks' data from six different patients, we achieve an average RMSE of 6.45 and 17.24 mg/dl for 30 min and 60 min of prediction horizon (PH), respectively.
To the best of our knowledge, this is the leading average prediction accuracy for the ohioT1DM dataset. Different physiological information, e.g., Kalman smoothed CGM data, carbohydrates from the meal, bolus insulin, and cumulative step counts in a fixed time interval, are crafted to represent meaningful features used as input to the model. The goal of our approach is to lower the difference between the predicted CGM values and the fingerstick blood glucose readings-the ground truth. Our results indicate that the proposed approach is feasible for more reliable BG forecasting that might improve the performance of the artificial pancreas and insulin infusion system for T1D diabetes management.
血糖（BG）管理对于1型糖尿病患者至关重要，这使得可靠的人工胰腺或胰岛素输注系统成为必要。近年来，深度学习技术已被用于更准确的血糖水平预测系统。然而，连续血糖监测（CGM）读数容易受到传感器误差的影响。因此，即使使用最优的机器学习模型，不准确的CGM读数也会影响血糖预测并使其不可靠。
在这项工作中，我们提出了一种新颖的方法，使用基于堆叠长短期记忆（LSTM）的深度循环神经网络（RNN）模型来预测血糖水平，并考虑传感器故障。我们使用卡尔曼平滑技术来校正由于传感器误差导致的不准确的CGM读数。
对于包含来自六名不同患者的八周数据的OhioT1DM（2018）数据集，在预测时域（PH）为30分钟和60分钟时，我们分别实现了平均均方根误差（RMSE）为6.45和17.24mg/dl。
据我们所知，这是OhioT1DM数据集领先的平均预测准确率。不同的生理信息，例如卡尔曼平滑的CGM数据、餐食中的碳水化合物、大剂量胰岛素以及固定时间间隔内的累计步数，被精心设计以代表有意义的特征，用作模型的输入。我们方法的目标是降低预测的CGM值与指尖血糖读数（真实值）之间的差异。我们的结果表明，所提出的方法对于更可靠的血糖预测是可行的，这可能会改善用于1型糖尿病管理的人工胰腺和胰岛素输注系统的性能。
