Department of Information Management, Yuan Ze University, Taoyuan, ROC.
Statistics and Informatics Department, University of Economics, The University of Danang, Da Nang, Vietnam.
J Asthma. 2021 Jul;58(7):903-911. doi: 10.1080/02770903.2020.1742352. Epub 2020 Mar 18.
Sleep is a natural activity of humans that affects physical and mental health; therefore, sleep disturbance may lead to fatigue and lower productivity. This study examined 1 million samples included in the Taiwan National Health Insurance Research Database (NHIRD) in order to predict sleep disorder in an asthma cohort from 2002-2010.
The disease histories of the asthma patients were transferred to sequences and matrices for the prediction of sleep disorder by applying machine learning (ML) algorithms, including K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Random Forest (RF), and deep learning (DL) models, including Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), and Convolution Neural Network (CNN).
Among 14,818 new asthma subjects in 2002, there were 4469 sleep disorder subjects from 2002 to 2010. The KNN, SVM, and RF algorithms were demonstrated to be successful sleep disorder prediction models, with accuracies of 0.798, 0.793, and 0.813, respectively (AUC: 0.737, 0.690, and 0.719, respectively). The results of the DL models showed the accuracies of the RNN, LSTM, GRU, and CNN to be 0.744, 0.815, 0.782, and 0.951, respectively (AUC: 0.658, 0.750, 0.732, and 0.934, respectively).
The results showed that the CNN model had the best performance for sleep disorder prediction in the asthma cohort.
睡眠是人类的一种自然活动，影响身心健康；因此，睡眠障碍可能导致疲劳和生产力下降。本研究从 2002 年至 2010 年，对包含在台湾全民健康保险研究数据库（NHIRD）中的 100 万样本进行了分析，以预测哮喘队列中的睡眠障碍。
通过应用机器学习（ML）算法，包括 K 最近邻（KNN）、支持向量机（SVM）和随机森林（RF），以及深度学习（DL）模型，包括递归神经网络（RNN）、长短期记忆（LSTM）、门控循环单元（GRU）和卷积神经网络（CNN），将哮喘患者的病史转换为序列和矩阵，以预测睡眠障碍。
在 2002 年的 14818 名新哮喘患者中，2002 年至 2010 年有 4469 名睡眠障碍患者。KNN、SVM 和 RF 算法被证明是成功的睡眠障碍预测模型，其准确率分别为 0.798、0.793 和 0.813（AUC：0.737、0.690 和 0.719）。DL 模型的结果表明，RNN、LSTM、GRU 和 CNN 的准确率分别为 0.744、0.815、0.782 和 0.951（AUC：0.658、0.750、0.732 和 0.934）。
结果表明，在哮喘队列中，CNN 模型对睡眠障碍的预测性能最佳。
