The Study On Epidemic Situation And Prediction Of Hand-foot-mouth Disease In China

Hand-Foot-Mouth disease is a common infectious disease caused by human enterovirus infections such as coxsackievirus A16 and human enterovirus 71.This disease spreads rapidly and infects people easily,which has received widespread attention from the public health statistics community.And the analysis of the epidemic situation and the prediction of the number of cases have become one of the hotspots in current research.Based on the data of HFMD incidence in China from 2008 to 2018 provided by the China Centers for Disease Control and Prevention,this paper uses Python and Arc GIS software to conduct a detailed analysis of the prevalence of HFMD in China from different dimensions,and three models that can effectively predict the incidence of HFMD are set up.The specific research results are as follows:First,from 2008 to 2018,the overall incidence of HFMD in China showed an upward trend,and the mortality rate showed a downward trend.And the incidence of HFMD varies widely among provinces in China.The incidence of HFMD is lower in the northeast,northwest and southwest of China,while it is higher in the east and south of China.Besides,The incidence of different age groups is significantly different.Children aged 0-5 are at the high incidence of HFMD.As the age increases,the number of HFMD cases gradually decreases.After the age of 55,the number of cases is less than 100 every year.Meanwhile,there is also a large difference in onset time.Most of the onset time is between April and July,and the incidence rate is the lowest from January to March.Second,in order to predict the incidence of HFMD,three models were established,which can more accurately describe and predict the incidence of HFMD.According to the data of HFMD incidence from July 2007 to December 2018 provided by the Chinese Center for Disease Control and Prevention,the LSTM model,Prophet model and ARIMA model were used to predict the incidence of HFMD in China.Later,the prediction performance of the three models is compared.The experiments show that the ARIMA model has the best prediction performance,the Prophet model ranks second,and the LSTM model has the worst performance.Finally,after careful analysis,it is proved that the peak period of HFMD in China is from April to July and September to October in a year.There are obvious differences in the incidence of HFMD among regions.Eastern and Southern China are the regions with high incidence of HFMD.Also,the incidence of HFMD differs significantly among different age groups,and the age of the affected population is concentrated between 0-5.When using LSTM,Prophet and ARIMA models to predict the incidence of HFMD in China,we found that all the three models can predict the incidence of HFMD.However,the ARIMA model has the best prediction performance.