背景:手,脚,口蹄疫(HFMD)是一种常见的传染病,对全世界的儿童构成严重威胁。然而,目前手足口病的预测模型仍需要提高准确性。在这项研究中,我们提出了一种基于自回归积分移动平均(ARIMA)的混合模型,集成经验模态分解(EEMD)和长短期记忆(LSTM)来预测手足口病的趋势。
方法:本研究中使用的数据来自国家儿童健康和疾病临床研究中心,重庆,中国。收集2015年1月1日至2023年7月27日每日报告的手足口病发病率,以建立ARIMA-EEMD-LSTM混合模型。阿丽玛,LSTM,开发了ARIMA-LSTM和EEMD-LSTM模型,以与提出的混合模型进行比较。均方根误差(RMSE),采用平均绝对误差(MAE)和确定系数(R2)来评估预测模型的性能。
结果:总体而言,ARIMA-EEMD-LSTM模型实现了对手足口病最准确的预测,RMSE,MAPE和R2分别为4.37、2.94和0.996。对残差序列执行EEMD产生11个固有模式函数。EEMD-LSTM模型次优,RMSE,MAPE和R2为6.20、3.98和0.996。
结论:结果显示ARIMA-EEMD-LSTM模型优于ARIMA模型,LSTM模型,ARIMA-LSTM模型和EEMD-LSTM模型。为了预防和控制流行病,提出的混合模型可以提供更有力的帮助。与其他三种型号相比,两者结合EEMD方法显示出预测能力的显著提高,为疾病时间序列建模提供新的见解。
BACKGROUND: Hand, foot, and mouth disease (HFMD) is a common infectious disease that poses a serious threat to children all over the world. However, the current prediction models for HFMD still require improvement in accuracy. In this study, we proposed a hybrid model based on autoregressive integrated moving average (ARIMA), ensemble empirical mode decomposition (
EEMD) and long short-term memory (LSTM) to predict the trend of HFMD.
METHODS: The data used in this study was sourced from the National Clinical Research Center for Child Health and Disorders, Chongqing, China. The daily reported incidence of HFMD from 1 January 2015 to 27 July 2023 was collected to develop an ARIMA-EEMD-LSTM hybrid model. ARIMA, LSTM, ARIMA-LSTM and
EEMD-LSTM models were developed to compare with the proposed hybrid model. Root mean square error (RMSE), mean absolute error (MAE) and coefficient of determination (R2) were adopted to evaluate the performances of the prediction models.
RESULTS: Overall, ARIMA-EEMD-LSTM model achieved the most accurate prediction for HFMD, with RMSE, MAPE and R2 of 4.37, 2.94 and 0.996, respectively. Performing
EEMD on the residual sequence yields 11 intrinsic mode functions.
EEMD-LSTM model is the second best, with RMSE, MAPE and R2 of 6.20, 3.98 and 0.996.
CONCLUSIONS: Results showed the advantage of ARIMA-EEMD-LSTM model over the ARIMA model, the LSTM model, the ARIMA-LSTM model and the
EEMD-LSTM model. For the prevention and control of epidemics, the proposed hybrid model may provide a more powerful help. Compared with other three models, the two integrated with EEMD method showed significant improvement in predictive capability, offering novel insights for modeling of disease time series.