Dilated Recurrent Neural Networks for Glucose Forecasting in Type 1 Diabetes.

Dilated Recurrent Neural Networks for Glucose Forecasting in Type 1 Diabetes.
复制标题

扩张递归神经网络在1型糖尿病血糖预测中的应用

DOI:
10.1007/s41666-020-00068-2
复制
发表时间:
2020-09
影响因子:
5.9
通讯作者:
Georgiou P
Georgiou P
中科院分区:
其他
文献类型:
--
作者:
Zhu T;Li K;Chen J;Herrero P;Georgiou P

文献摘要

参考文献

被引文献

相似文献

糖尿病是一种影响全球4.15亿人的慢性疾病。1型糖尿病(T1DM)患者需要自我注射胰岛素来维持血糖(BG)水平在正常范围内,这通常是一项非常具有挑战性的任务。开发一个可靠的血糖预测模型将对糖尿病管理产生深远的影响,因为它可以在低血糖时提供预测血糖警报或胰岛素暂停,以最小化低血糖。近年来,深度学习在医疗保健和医学研究中的诊断、预测和决策方面显示出巨大的潜力。在这项工作中,我们引入了一种基于扩展递归神经网络(DRNN)的深度学习模型,以提供30分钟内未来血糖水平的预测。使用扩张,DRNN模型在神经元方面获得了更大的接受野,旨在捕获长期依赖。迁移学习技术也被应用于利用来自多个学科的数据。该方法优于现有的葡萄糖预测算法,包括自回归模型(ARX)、支持向量回归(SVR)和用于预测葡萄糖(NNPG)的传统神经网络(例如RMSE = NNPG, 22.9 mg/dL; SVR, 21.7 mg/dL; ARX, 20.1 mg/dL; DRNN,在OhioT1DM数据集上,18.9 mg/dL)。结果表明,扩张连接可以有效地提高血糖预测性能。
Diabetes is a chronic disease affecting 415 million people worldwide. People with type 1 diabetes mellitus (T1DM) need to self-administer insulin to maintain blood glucose (BG) levels in a normal range, which is usually a very challenging task. Developing a reliable glucose forecasting model would have a profound impact on diabetes management, since it could provide predictive glucose alarms or insulin suspension at low-glucose for hypoglycemia minimisation. Recently, deep learning has shown great potential in healthcare and medical research for diagnosis, forecasting and decision-making. In this work, we introduce a deep learning model based on a dilated recurrent neural network (DRNN) to provide 30-min forecasts of future glucose levels. Using dilation, the DRNN model gains a much larger receptive field in terms of neurons aiming at capturing long-term dependencies. A transfer learning technique is also applied to make use of the data from multiple subjects. The proposed approach outperforms existing glucose forecasting algorithms, including autoregressive models (ARX), support vector regression (SVR) and conventional neural networks for predicting glucose (NNPG) (e.g. RMSE = NNPG, 22.9 mg/dL; SVR, 21.7 mg/dL; ARX, 20.1 mg/dl; DRNN, 18.9 mg/dL on the OhioT1DM dataset). The results suggest that dilated connections can improve glucose forecasting performance efficiently.
DOI: 10.1162/089976600300015015
发表时间: 2000-10-01
期刊: NEURAL COMPUTATION
影响因子: 2.9
作者:
Gers, FA;Schmidhuber, J;Cummins, F
通讯作者: Cummins, F
DOI: 10.1109/jbhi.2015.2464088
发表时间: 2016-01-01
影响因子: 7.7
作者:
Pesl, Peter;Herrero, Pau;Georgiou, Pantelis
通讯作者: Georgiou, Pantelis
DOI: 10.1561/2200000006
发表时间: 2009-01-01
影响因子: 32.8
作者:
Bengio, Yoshua
通讯作者: Bengio, Yoshua
DOI: 10.1177/0363546510373570
发表时间: 2010-11-01
影响因子: 4.8
作者:
Koga, Hideyuki;Nakamae, Atsuo;Krosshaug, Tron
通讯作者: Krosshaug, Tron
DOI: 10.1016/j.eswa.2006.09.012
发表时间: 2008-01-01
影响因子: 8.5
作者:
Polat, Kemal;Gunes, Salih;Arslan, Ahmet
通讯作者: Arslan, Ahmet