差分自回归移动平均模型在南通市手足口病疫情预测中的应用

Application of autoregressive integrated moving average model in prediction of hand-footmouth disease epidemic in Nantong

目的:应用差分自回归移动平均模型(ARIMA)预测南通市手足口病疫情趋势。方法:以2010年1月—2019年6月南通市手足口病分月报告病例数据为基础,构建符合季节性时间序列的ARIMA(p,d,q)×(P,D,Q)S模型,用2019年7—12月全市手足口病月发病率为验证数据进行验证,检验模型的预测效果。结果:2010—2019年南通市共报告手足口病90 766例,年平均发病率为124.36/10万,疫情有明显季节性,呈双峰特征,为夏季(5、6、7月)高峰和冬季(11、12月)次高峰;近年来南通市手足口病的病原谱以其他肠道病毒为主;利用ARIMA(1,0,1)(1,1,1)12模型,预测2019年7—12月手足口病发病率分别为7.08/10万、1.81/10万、3.74/10万、7.21/10万、10.71/10万和11.29/10万,与实际发病率相比,两者差异无统计学意义(Z=0.48,P=0.63)。结论:差分自回归移动平均模型能较好地预测手足口病的发病趋势,可用于短期的预警监测。

Objective:To predict the trend of hand-foot-mouth disease in Nantong by using the autoregressive integrated moving average(ARIMA)model. Methods:Based on the monthly reported case data of hand-foot-mouth disease in Nantong from January 2010 to June 2019,a ARIMA(p,d,q)×(P,D,Q)Smodel was constructed in accordance with the seasonal time series. The monthly incidence of hand-foot-mouth disease in the city from July to December 2019 was used as verification data to test the prediction effect of the model. Results:A total of 90 766 cases of hand-foot-mouth disease were reported in Nantong from 2010 to 2019. The average annual incidence rate was 124.36/100 000. The epidemic showed seasonality of incidence with two peaks. One was the summer peak and the other was the winter sub-peak. In recent years,the pathogenic spectrum of hand-foot-mouth disease in Nantong was dominated by other intestinal viruses. Using the ARIMA(1,0,1)(1,1,1)12 model,the incidence of hand-foot-mouth disease from July to December 2019 wss predicted to be 7.08/100 000,1.81/100 000,3.74/100 000,7.21/100 000,10.71/100 000,and 11.29/100 000.Compared with the actual incidence,there was no significant difference. Conclusion:The autoregressive integrated moving average model can better predict the incidence of hand-foot-mouth disease,and can be used for short-term early warning and monitoring.