Forecasting the Tuberculosis Incidence Using a Novel Ensemble Empirical Mode Decomposition-Based Data-Driven Hybrid Model in Tibet, China

Jizhen Li,1 Yuhong Li,2 Ming Ye,3 Sanqiao Yao,1 Chongchong Yu,1 Lei Wang,4 Weidong Wu,1 Yongbin Wang1 1Department of Epidemiology and Health Statistics, School of Public Health, Xinxiang Medical University, Xinxiang, Henan Province, People’s Republic of China; 2National Center for Tuberculosis Control and Prevention, China Center for Disease Control and Prevention, Beijing, People’s Republic of China; 3Preventive Medicine Clinic, Xinxiang Center for Disease Control and Prevention, Xinxiang, Henan Province, People’s Republic of China; 4Center for Musculoskeletal Surgery, Charité–Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt–Universität Zu Berlin and Berlin Institute of Health, Berlin, GermanyCorrespondence: Yongbin WangDepartment of Epidemiology and Health Statistics, School of Public Health, Xinxiang Medical University, Xinxiang, Henan Province, 453000, People’s Republic of ChinaEmail wybwho@163.comObjective: The purpose of this study is to develop a novel data-driven hybrid model by fusing ensemble empirical mode decomposition (EEMD), seasonal autoregressive integrated moving average (SARIMA), with nonlinear autoregressive artificial neural network (NARNN), called EEMD-ARIMA-NARNN model, to assess and forecast the epidemic patterns of TB in Tibet.Methods: The TB incidence from January 2006 to December 2017 was obtained, and then the time series was partitioned into training subsamples (from January 2006 to December 2016) and testing subsamples (from January to December 2017). Among them, the training set was used to develop the EEMD-SARIMA-NARNN combined model, whereas the testing set was used to validate the forecasting performance of the model. Whilst the forecasting accuracy level of this novel method was compared with the basic SARIMA model, basic NARNN model, error-trend-seasonal (ETS) model, and traditional SARIMA-NARNN mixtur