Forecasting Hand-Foot-and-Mouth Disease Cases Using a Wavelet-based SARIMA-NNAR Hybrid Model

Abstract

Background: Hand-foot-and-mouth disease(HFMD) is one of the most common diseases in children, which has high morbidity. Reliable forecasting is significant for prevention and control. Recently, hybrid models have been becoming popular and wavelet analysis has been widely used. Better prediction accuracy may be achieved with wavelet-based hybrid models. Thus, our aim is to forecast number of HFMD cases with wavelet-based hybrid models.Materials and methods: We fitted a wavelet-based SARIMA(seasonal autoregressive integrated moving average)-NNAR(neural network nonlinear autoregressive) hybrid model with HFMD weekly cases from 2009 to 2016 in Zhengzhou, China. At the same time, single SARIMA model, simplex NNAR model and pure SARIMA-NNAR hybrid model were established as well for comparison and estimation.Results: The wavelet-based SARIMA-NNAR hybrid model had an excellent performance whether in fitting or in forecasting compared to other models. Its fitted and forecasting time series were approximate to the actual observed time series.Conclusions: This wavelet-based SARIMA-NNAR hybrid model that we fitted is suitable for forecasting number of HFMD cases. It will facilitate prevention and control of HFMD.