Predicting the incidence of hand, foot, and mouth disease in Beijing with SARIMA

Abstract

Objective To discuss the prediction method for the incidence of hand, food, and mouth disease (HFMD) in Beijing by SARIMA model. Methods The SARIMA model was established based on the monthly incidence of HFMD in Beijing from 2010 to 2017 collected from China Information System for Disease Control and Prevention, using SPSS 19.0 software. The SARIMA model was used to predict the incidence of HFMD in 2018. Results The annual incidence peak appeared during April to August, and the second peak was during September to October. The average annual incidence of HFMD from 2010 to 2017 was 166.83/100 000. The Stationary R-squared was 0.705, Mean Absolute Percentage Error (MAPE) was 33.217 and Bayesian Information Criterion (BIC) was 2.862. Through the test of parameters and goodness of fit as well as white-noise residuals, SARIMA (1,0,1) (0,1,1) 12 was proved to be an optimal model for the observed values. The incidence of HFMD in Beijing 2018 was predicted to be 120.19/100,000, which will exceed the incidence of 2017. The annual incidence peak of HFMD from April to August will have a significant increase than 2017. Conclusions The results show that the SARIMA model provided a better fit to the incidence of HFMD in Beijing. This model can provide scientific basis for developing prevention and control strategies in advance. Key words: Hand-foot-mouth Disease; SARIMA model; Prediction