Developing an Individual Glucose Prediction Model Using Recurrent Neural Network

被引:7
|
作者
Kim, Dae-Yeon [1 ]
Choi, Dong-Sik [2 ]
Kim, Jaeyun [3 ]
Chun, Sung Wan [1 ]
Gil, Hyo-Wook [1 ]
Cho, Nam-Jun [1 ]
Kang, Ah Reum [4 ]
Woo, Jiyoung [3 ]
机构
[1] Soonchunhyang Univ, Dept Internal Med, Cheonan Hosp, Cheonan 31151, South Korea
[2] Soonchunhyang Univ, Dept Med Sci, Asan 31538, South Korea
[3] Soonchunhyang Univ, Dept Big Data Engn, Asan 31538, South Korea
[4] Soonchunhyang Univ, SCH Convergence Sci Inst, Asan 31538, South Korea
基金
新加坡国家研究基金会;
关键词
continuous glucose monitoring; diabetic inpatient; glucose prediction model; deep learning; HYPERGLYCEMIA; MANAGEMENT; TIME;
D O I
10.3390/s20226460
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
In this study, we propose a personalized glucose prediction model using deep learning for hospitalized patients who experience Type-2 diabetes. We aim for our model to assist the medical personnel who check the blood glucose and control the amount of insulin doses. Herein, we employed a deep learning algorithm, especially a recurrent neural network (RNN), that consists of a sequence processing layer and a classification layer for the glucose prediction. We tested a simple RNN, gated recurrent unit (GRU), and long-short term memory (LSTM) and varied the architectures to determine the one with the best performance. For that, we collected data for a week using a continuous glucose monitoring device. Type-2 inpatients are usually experiencing bad health conditions and have a high variability of glucose level. However, there are few studies on the Type-2 glucose prediction model while many studies performed on Type-1 glucose prediction. This work has a contribution in that the proposed model exhibits a comparative performance to previous works on Type-1 patients. For 20 in-hospital patients, we achieved an average root mean squared error (RMSE) of 21.5 and an Mean absolute percentage error (MAPE) of 11.1%. The GRU with a single RNN layer and two dense layers was found to be sufficient to predict the glucose level. Moreover, to build a personalized model, at most, 50% of data are required for training.
引用
收藏
页码:1 / 15
页数:15
相关论文
共 50 条
  • [41] Convolutional Recurrent Neural Networks for Glucose Prediction
    Li, Kezhi
    Daniels, John
    Liu, Chengyuan
    Herrero, Pau
    Georgiou, Pantelis
    [J]. IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2020, 24 (02) : 603 - 613
  • [42] A Blood Glucose Level Prediction System Using Machine Learning Based on Recurrent Neural Network for Hypoglycemia Prevention
    Doike, Takuyoshi
    Hayashi, Kenya
    Arata, Shigeki
    Mohammad, Karim Nissar
    Kobayashi, Atsuki
    Niitsu, Kiichi
    [J]. 2018 16TH IEEE INTERNATIONAL NEW CIRCUITS AND SYSTEMS CONFERENCE (NEWCAS), 2018, : 291 - 295
  • [43] Social Messages Outbreak Prediction Model Based on Recurrent Neural Network
    Gou C.-C.
    Qin Y.-J.
    Tian T.
    Wu D.-Y.
    Liu Y.
    Cheng X.-Q.
    [J]. Ruan Jian Xue Bao/Journal of Software, 2017, 28 (11): : 3030 - 3042
  • [44] FINANCIAL TIME SERIES PREDICTION MODEL BASED RECURRENT NEURAL NETWORK
    Cheng Chaozhi
    Gao Yachun
    Ni Jingwei
    [J]. 2020 17TH INTERNATIONAL COMPUTER CONFERENCE ON WAVELET ACTIVE MEDIA TECHNOLOGY AND INFORMATION PROCESSING (ICCWAMTIP), 2020, : 33 - 38
  • [45] Prediction model for stock price trend based on recurrent neural network
    Zhao, Jinghua
    Zeng, Dalin
    Liang, Shuang
    Kang, Huilin
    Liu, Qinming
    [J]. JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING, 2021, 12 (01) : 745 - 753
  • [46] Prediction model of a hybrid recurrent neural network based on sequence decomposition
    Zhao, Jia
    Li, Changxiang
    Han, Longzhe
    Wu, Yannian
    Wu, Lieyang
    [J]. INTERNATIONAL JOURNAL OF COMPUTING SCIENCE AND MATHEMATICS, 2023, 18 (03) : 286 - 298
  • [47] Prediction model for stock price trend based on recurrent neural network
    Jinghua Zhao
    Dalin Zeng
    Shuang Liang
    Huilin Kang
    Qinming Liu
    [J]. Journal of Ambient Intelligence and Humanized Computing, 2021, 12 : 745 - 753
  • [48] Distribution network planning method: Integration of a recurrent neural network model for the prediction of scenarios
    Saldana-Gonzalez, Antonio E.
    Aragues-Penalba, Monica
    Sumper, Andreas
    [J]. ELECTRIC POWER SYSTEMS RESEARCH, 2024, 229
  • [49] Application of NARX dynamic neural network in blood glucose prediction model
    Xu, Menglin
    Song, Ruizhuo
    Zhao, Yong
    Song, Biao
    Tang, Juan
    [J]. PROCEEDINGS OF 2020 IEEE 9TH DATA DRIVEN CONTROL AND LEARNING SYSTEMS CONFERENCE (DDCLS'20), 2020, : 178 - 183
  • [50] Solar radiation prediction using recurrent neural network and artificial neural network: A case study with comparisons
    Pang, Zhihong
    Niu, Fuxin
    O'Neill, Zheng
    [J]. RENEWABLE ENERGY, 2020, 156 (156) : 279 - 289