Application of Seasonal Auto-regressive Integrated Moving Average Model in Forecasting the Incidence of Hand-foot-mouth Disease in Wuhan,China

• Published in: Current medical science 2017-12, Vol.37 (6), p.842-848
• Main Authors: 彭颖, 余滨, 汪鹏, 孔德广, 陈邦华, 杨小兵
• Format: Article
• Language: English
• Subjects: Medicine; Medicine & Public Health
• ISSN: 1672-0733; 2096-5230; 1993-1352; 2523-899X
• DOI: 10.1007/s11596-017-1815-8

Outbreaks of hand-foot-mouth disease（HFMD） have occurred many times and caused serious health burden in China since 2008. Application of modern information technology to prediction and early response can be helpful for efficient HFMD prevention and control. A seasonal auto-regressive integrated moving average（ARIMA） model for time series analysis was designed in this study. Eighty-four-month（from January 2009 to December 2015） retrospective data obtained from the Chinese Information System for Disease Prevention and Control were subjected to ARIMA modeling. The coefficient of determination（R~2）, normalized Bayesian Information Criterion（BIC） and Q-test P value were used to evaluate the goodness-of-fit of constructed models. Subsequently, the best-fitted ARIMA model was applied to predict the expected incidence of HFMD from January 2016 to December 2016. The best-fitted seasonal ARIMA model was identified as（1,0,1）（0,1,1）12, with the largest coefficient of determination（R~2=0.743） and lowest normalized BIC（BIC=3.645） value. The residuals of the model also showed non-significant autocorrelations（P_（Box-Ljung（Q））=0.299）. The predictions by the optimum ARIMA model adequately captured the pattern in the data and exhibited two peaks of activity over the forecast interval, including a major peak during April to June, and again a light peak for September to November. The ARIMA model proposed in this study can forecast HFMD incidence trend effectively, which could provide useful support for future HFMD prevention and control in the study area. Besides, further observations should be added continually into the modeling data set, and parameters of the models should be adjusted accordingly.