【摘要】 目的探讨适合全国乙肝发病率的预测模型,为乙肝预测预警系统提供参考。方法应用2004-2012年全国乙肝月发病率数据,分别建立ARIMA模型和BP神经网络模型,利用建立的模型预测2013年1-12月乙肝发病率,采用实际发病率验证与比较两种模型的预测效果,评价指标为平均绝对误差(MAE)、平均绝对误差率(MER)和非线性相关系数(RNL)。结果全国2004-2013年乙肝月发病率在2.79/10万~9.44/10万间波动,序列具有明显的长期趋势。建立的乘积ARIMA(0,1,1)(0,1,1)12模型预测的MAE、MER、RNL分别为0.445、0.065、0.909,BP神经网络模型分别为0.635、0.093、0.872。ARIMA模型预测的平均绝对误差和平均绝对误差率要低于BP神经网络模型(△MAE=-0.190,△MER=-0.028),非线性相关系数要高于BP神经网络模型(△RNL=0.037)。结论 ARIMA模型和BP神经网络模型均适用于我国乙肝发病率的预测,且前者的预测效能和非线性拟合能力略优于后者。更多还原

【Abstract】 Objective To explore suitable prediction models for hepatitis B incidence in China;to provide reference for forecasting warning system of hepatitis B.Methods ARIMA model and Back-Propagation(BP)neural network model were established based on monthly incidence of hepatitis B from 2004 to 2012.Predication performance of both models were verified by monthly incidence of hepatitis B in 2013.Mean absolute error(MAE),mean error rate(MER)and nonlinear correlation coefficient(RNL)were used to compare prediction effects of above two models.Results The monthly incidence of hepatitis B from2004 to 2013were in the range of 2.79/105-9.44/105,demonstrating obvious long-term trends.The MAE,MER,RNL between actual values and predicted values of the monthly incidence of hepatitis B in 2013 using the fitting ARIMA(0,1,1)(0,1,1)12model and BP neural network model were 0.445,0.065,0.909 and 0.635,0.093,0.872,respectively.MAE and MER of ARIMA model were lower than those of BP neural network model(△MAE=-0.190,△MER=-0.028),its RNL was higher than that of BP neural network model(△RNL=0.037).Conclusion Both ARIMA model and BP neural network model performed well in predicting hepatitis B incidence in China.The prediction and nonlinear fitting ability of ARIMA model was slightly better than those of BP neural network model.更多还原