Application of seasonal auto regressive integrated moving average model in predicting incidence of hand foot and mouth disease in Nanyang

  Objective  To establish the prediction model for hand foot and mouth disease (HFMD) in Nanyang, Henan province, using time series analysis and provide the scientific evidence for the control strategies.

  Methods  The monthly incidence data of HFMD in Nanyang from 2010 to 2018 were collected to establish a time series. SARIMA model was constructed using expert modeler to predict the incidence of HFMD in 2019, which was compared with the observed data.

  Results  The monthly incidence of HFMD in Nanyang from 2010 to 2018 showed obvious seasonality. The optimal model was ARIMA(2, 0, 0)(0, 1, 1)₁₂, with R² of 0.827, RMSE of 2.240, MAE of 1.207 and BIC of 1.755. The prediction of the model for the incidence of HFMD in 2019 showed that the predicted values were consistent with the observed values. The absolute value of relative error was 0.01 at the minimum and 6.14 at the maximum.

  Conclusion  SARIMA model could fit the incidence of HFMD in Nanyang and predict the incidence trend in the future and provide the basis for prevention and control of HFMD.