Stacked LSTM based deep recurrent neural network with kalman smoothing for blood glucose prediction.
Stacked LSTM based deep recurrent neural network with kalman smoothing for blood glucose prediction.
复制标题
DOI：
10.1186/s12911-021-01462-5
复制
发表时间：
2021-03-16
影响因子：
3.5
通讯作者：
Hei X
中科院分区：
文献类型：
--
作者：
Rabby MF;Tu Y;Hossen MI;Lee I;Maida AS;Hei X
血糖(BG)管理对1型糖尿病患者至关重要，因此需要可靠的人工胰腺或胰岛素输注系统。近年来，深度学习技术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BG预测，并使其不可靠。在这项工作中，我们提出了一种新的方法来预测血糖水平堆叠的长期短期记忆(LSTM)的深度递归神经网络(RNN)模型考虑传感器故障。我们使用卡尔曼平滑技术来校正由于传感器误差而导致的CGM读数不准确。对于包含来自六个不同患者的八周数据的OhioT1 DM(2018)数据集，我们在预测时段(PH)的30分钟和60分钟内分别获得了6.45和17.24 mg/dl的平均RMSE。据我们所知，这是ohioT1 DM数据集的领先平均预测精度。制作不同的生理信息，例如卡尔曼平滑的CGM数据、膳食中的碳水化合物、胰岛素推注和固定时间间隔内的累积步数，以表示用作模型输入的有意义的特征。我们方法的目标是降低CGM预测值和手指血糖读数之间的差异-这是基本事实。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，这可能会改善用于治疗T1D糖尿病的人工胰腺和胰岛素输注系统的性能。
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.
登录
查看更多内容
影响因子：
16.2
作者：
通讯作者：
--
影响因子：
158.5
作者：
Bergenstal, Richard M.;Tamborlane, William V.;Wood, Michael A.
通讯作者：
Wood, Michael A.
影响因子：
5.4
作者：
Facchinetti, Andrea;Del Favero, Simone;Cobelli, Claudio
通讯作者：
Cobelli, Claudio
影响因子：
16.2
作者：
通讯作者：
--
影响因子：
4.6
作者：
Facchinetti, Andrea;Del Favero, Simone;Cobelli, Claudio
通讯作者：
Cobelli, Claudio