ARIMA模型在深圳市法定传染病发病趋势预测的应用  

Application of ARIMA model to predicting the incidence tendency of notifiable communicable diseases in Shenzhen City

作　　者：郑慧敏[1] 薛允莲[1] 黄燕飞[1] 戴传文[1] 姜世强[1] 

机构地区：[1]深圳市南山区疾病预防控制中心,广东深圳518054

出　　处：《实用预防医学》2016年第2期240-243,共4页Practical Preventive Medicine

基　　金：2014年度深圳市卫生计生系统科研项目(项目编号:201402140)

摘　　要：目的通过探讨单纯求和自回归滑动平均模型(ARIMA模型)应用于法定传染病发病率预测的可行性,为传染病防控工作提供科学依据。方法采用SAS9.2软件对深圳市2004-2014年的病毒性肝炎、细菌性痢疾的月发病率进行ARIMA模型的建模拟合,预测2015年病毒性肝炎、细菌性痢疾的月发病率。结果 ARIMA模型对病毒性肝炎、细菌性痢疾的拟合效果较好。结论 ARIMA模型对深圳市几种传染病发病的时间序列变动趋势能进行较好的模拟,因此可以为法定传染病的预测提供依据。2015年预测结果提示病毒性肝炎的发病有上升趋势,需进一步调整相应防控策略。Objective To explore the feasibility of ARIMA model in predicting the incidence of communicable diseases so as to provide scientific evidence for control and prevention of communicable diseases. Methods The monthly incidence of viral hep- atitis and bacillary dysentery in Shenzhen City was collected from 2004 to 2014 and the autoregressive integrated moving average （ARIMA） modal was fit by SAS 9.2 software. The constructed modal was used to predict the monthly incidence of viral hepatitis and bacillary dysentery in 2015. Results ARIMA model had good fitting effects in the prediction of viral hepatitis and bacil- lary dysentery. Conclusions The changes of time series of the prevalence of communicable diseases can be simulated with ARIMA modal; and hence, it can provide evidence for the prediction of notifiable communicable diseases. The predicted results in 2015 suggest that the incidence of viral hepatitis shows an increasing trend and the prevention and control strategies on viral hepatitis should be further improved.

关 键 词：ARIMA模型 时间序列 预测 传染病 

分 类 号：R51[医药卫生—内科学]