LSTM、SARIMA和SARIMAX模型预测手足口病发病率的效果比较  

Comparison of the prediction effects of LSTM,SARIMA and SARIMAX models on the incidence of hand,foot,and mouth disease

作　　者：张小乔 张筱碟 赵振希 谢鹏留 代敏[1] ZHANG Xiaoqiao;ZHANG Xiaodie;ZHAO Zhenxi;XIE Pengliu;DAI Min(Kunming Center for Disease Control and Prevention,Kunming,Yunnan 650000,China)

机构地区：[1]昆明市疾病预防控制中心,云南昆明650000

出　　处：《预防医学》2025年第3期280-283,287,共5页China Preventive Medicine Journal

基　　金：昆明市卫生健康委员会卫生科研课题(2023-12-05-003)。

摘　　要：目的比较季节性差分自回归滑动平均(SARIMA)、含外生变量的季节性差分自回归滑动平均(SARIMAX)、长短期记忆神经网络(LSTM)模型预测手足口病发病率的效果。方法收集2010—2019年昆明市手足口病月发病率资料,采用2010—2018年手足口病月发病率分别建立SARIMA、SARIMAX和LSTM模型,预测2019年1—12月手足口病月发病率;采用均方误差(MSE)、均方根误差(RMSE)、平均绝对误差(MAE)和平均绝对百分比误差(MAPE)比较3种模型预测效果,根据MSE、RMSE、MAE和MAPE最小原则选择最优预测模型。结果2010—2019年昆明市各月均有手足口病病例报告,发病率在188.27/10万~363.15/10万之间波动,发病呈隔年高发双峰分布。LSTM模型在训练集和测试集中的4项评价指标较小,MSE分别为63.182和102.745,RMSE分别为7.949和10.136,MAE分别为6.535和7.620,MAPE分别为46.726%和31.138%,预测效果较好;其次为SARIMA模型;SARIMAX模型的预测效果相对较差。结论LSTM模型预测手足口病发病率的效果优于SARIMA和SARIMAX模型。Objective To compare the effects of seasonal autoregressive integrated moving average(SARIMA),seasonal autoregressive integrated moving average with exogenous regressors(SARIMAX)and long short-term memory neural network(LSTM)models in predicting the incidence of hand,foot,and mouth disease(HFMD).Methods Monthly incidence data of HFMD in Kunming City from 2010 to 2019 were collected.SARIMA,SARIMAX and LSTM models were established using the monthly incidence of HFMD from 2010 to 2018 to predict the monthly incidence of HFMD from January to December 2019.The prediction performance of the three models was compared using mean squared error(MSE),root mean squared error(RMSE),mean absolute error(MAE)and mean absolute percentage error(MAPE).The optimal prediction model was selected based on the principle of minimizing MSE,RMSE,MAE and MAPE.Results The HFMD cases were reported every month in Kunming City from 2010 to 2019,with the incidence fluctuating between 188.27/105 and 363.15/105.The disease exhibited a biennial high-incidence bimodal distribution.Among the four evaluation indicators for the training and testing sets,the LSTM model had the smaller values:MSE was 63.182 and 102.745,RMSE was 7.949 and 10.136,MAE was 6.535 and 7.620,and MAPE was 46.726% and 31.138%.The LSTM model performed the better,followed by the SARIMA model,while the SARIMAX model had the relatively poorest performance.Conclusion The LSTM model outperforms the SARIMA and SARIMAX models in predicting the incidence of HFMD.

关 键 词：手足口病 发病率 季节性差分自回归滑动平均模型 含外生变量的季节性差分自回归滑动平均模型 长短期记忆神经网络模型 预测 

分 类 号：R725.1[医药卫生—儿科]