Establishing A Prediction Model With Meteorological Factors Of Hand,Foot,and Mouth Disease Incidence Trend Based On The Automatic Machine Learning Algorithm

Objective: Hand,foot,and mouth disease has been ravaging the world for a long time,especially the Asia-Pacific region,and has become an important public health problem in China.Moreover,the COVID-19 pandemic also increases the difficulty of understanding and predicting the prevalence of hand,foot and mouth disease.The purpose of this study is to prove the usability and applicability of the automatic machine learning(Auto-ML)algorithms in predicting the epidemic of hand,foot and mouth disease and to explore the influence of the COVID-19 on the spread of hand,foot and mouth disease.Methods: The autoregressive integrated moving average(ARIMA)model,the autoregression and Moving Average model with exogenous input(ARIMAX)and the Auto ML algorithms were applied to construct prediction models,based on the monthly incidence numbers of hand,foot and mouth disease and meteorological factors from May2008 to December 2018 in Henan province.The models were validated by the data for the whole year of 2019.Evaluate the performance of the models according to the model evaluation criteria,and select the optimal prediction model.The incidence numbers of hand,foot and mouth disease in 2020 were further predicted based on the optimal model and then compared with the reported cases to analyze changes in the prevalence of hand,foot and mouth disease during the COVID-19 and the possible cause for this phenomenon.Results: ARIMA model,ARIMAX model,Auto-ML model without meteorological factors and Auto-ML model with meteorological factors were constructed respectively,and the Auto-ML models performed well.The Auto-ML model with meteorological factors had minimum Root mean square error(RMSE)and Mean absolute error(MAE)in both the model constructing phase and forecasting phase(training set: RMSE =1424.40 and MAE = 812.55;test set: RMSE = 2107.83,MAE = 1494.41),so this model has the best performance.And,for analysis,2020 was divided into two periods.The predicted incidence numbers followed the same trend as the reported cases of hand,foot and mouth disease before the COVID-19 outbreak;while after the COVID-19 outbreak,the actual incidence numbers have been greatly reduced than expected,and the incidence peak has also been delayed compared with previous years,which has led to significant changes in the seasonal pattern of hand,foot and mouth disease.Overall,there was a very large gap between the predicted incidence numbers and the reported incidence numbers of hand,foot and mouth disease in 2020.Conclusion: The Auto-ML models performed excellently in predicting the incidence numbers of hand,foot and mouth disease in Henan province.The addition of meteorological factors and their lagged terms further improved the prediction accuracy of the Auto-ML model.In brief,the Auto-ML algorithm is an applicable and ideal method to predict the epidemic trend of the hand,foot and mouth disease.Furthermore,it was found that the countermeasures of COVID-19 have a certain influence on suppressing the spread of hand,foot and mouth disease during the period of COVID-19.The results are helpful for health administrative departments to continuously “prevent multi-diseases”,optimize strategies,allocate resources,and formulate and implement more effective measures for prevention and control of hand,foot and mouth disease under the background of normalization of COVID-19.