基于时空大数据的甲型肝炎发病率分布特征分析及预测模型

Analysis of distribution characteristics and prediction model of hepatitis A incidence based on spatiotemporal big data

目的了解我国甲型病毒性肝炎(以下简称甲肝)发病率在时间和空间上的分布特征,探讨乘积季节模型在甲肝发病率预测中的可行性。方法收集我国2006-2017年甲肝发病数据和人口学资料,利用MapInfo11. 0绘制甲肝发病率时空分布柱状图;并采用SPSS 23. 0对2006-2016年数据建立自回归移动平均模型(autoregressive integrated moving average model,ARIMA),选取2017年数据评价模型的预测效果。结果 2006-2016年,全国共报告甲肝病例430 962例,发病率逐年递减,且西部地区明显高于东部地区。经数据平稳化处理、定阶、参数估计与模型检验后建立了最优模型ARIMA(0,2,2)(0,1,1)12。且对2017年1～12月的预测值和实际发病率基本吻合,相对误差在2. 0%～39. 7%之间。结论我国甲肝发病率逐年递减且东西部地区甲肝发病率表现出明显差异。ARIMA乘积季节模型对我国甲肝发病率具有很好的短期预测能力。

Objective To understand the spatiotemporal distribution of hepatitis A incidence in China, and to assess the feasibility of ARIMA product season model in the prediction of hepatitis A incidence. Methods Data about hepatitis A incidence and demography from 2006 to 2017 were collected, spatiotemporal distribution diagram of hepatitis A incidence was drawn by using Maplnfo 11.0, and ARIMA model for the 2006-2016 incidence series was established by using SPSS 23.0. Data of 2017 incidence were used to evaluate the prediction accuracy of the model. Results In 2006-2016, a total of 430 962 cases of hepatitis A were reported nationwide, the incidence declined with each passing year, and the western was significantly higher than the eastern region. The optimal model ARIMA（0, 2, 2） （0, 1, 1 ）12 was established after data smoothing, leveling, parameter estimation and model test. The prediction results of hepatitis A incidence were roughly consistent with the observations in 2017, and the relative error was between 2. 0% and 39. 7%. Conclusions The incidence of hepatitis A has been decreasing by years and shown significant differences between the eastern and western regions in China. The ARIMA product season model is suitable for forecasting the hepatitis Aineidence in short-term.