我国病毒性肝炎感染和死亡人数预测分析  

Prediction of Viral Hepatitis Infection and Death in China

作　　者：李海兰 张涛 

机构地区：[1]广西科技大学,广西 柳州

出　　处：《建模与仿真》2021年第4期937-945,共9页Modeling and Simulation

摘　　要：病毒性肝炎是一种危害肝脏的极具传染性的疾病,可有多种肝炎相关病毒诱发。在我国每年感染病毒性肝炎的人数都在1百万以上,且病毒性肝炎的传染性较强,对于我国这样一个世界人口大国而言,对病毒性肝炎的预防工作尤为重要。于是本研究以2011~2019年我国病毒性肝炎感染人数和死亡人数为基础,分别采用传统的GM(1,1)预测模型、BP神经网络预测模型和一元线性回归预测模型对2020~2029年病毒性肝炎感染人数和死亡人数进行预测,并在考虑到模型本身产生的系统性误差的基础上,利用各模型预测平均完全误差二次方根占比为权重将3种预测模型的预测结果进行加权平均作为最终的预测结果。最终得出结论病毒性肝炎感染人数在未来10年呈现显著的下降趋势,但病毒性肝炎死亡人数却呈现上涨趋势。Viral hepatitis is a very infectious disease that endangers the liver and can be induced by a variety of hepatitis related viruses. The number that infects virus hepatitis in our country every year is in 1 million above, and the infectivity of virus hepatitis is stronger, to our country such a world’s most populous country, the preventive work to virus hepatitis is particularly important. Therefore, based on the number of viral hepatitis infections and deaths in China from 2011 to 2019, this study used the traditional GM(1,1) prediction model, BP neural network prediction model and univariate linear regression prediction model respectively to predict the number of viral hepatitis infections and deaths from 2020 to 2029. On the basis of considering the systematic error of the model itself, the quadratic root ratio of the average complete error of each model is used as the weight and the weighted average of the prediction results of the three models is taken as the final prediction result. It is concluded that the number of viral hepatitis infection will decrease significantly in the next 10 years, but the number of viral hepatitis deaths will increase.

关 键 词：病毒性肝炎 灰色GM(1 1)模型 BP神经网络 线性回归 

分 类 号：S85[农业科学—兽医学]