LSTM、SARIMA和SARIMAX模型预测手足口病发病率的效果比较

doi:10.19485/j.cnki.issn2096-5087.2025.03.014

Preventive Medicine

2025, Vol. 37

Issue (3): 280-284,287 DOI: 10.19485/j.cnki.issn2096-5087.2025.03.014

Disease Control

Current Issue | Archive | Adv Search

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

ZHANG Xiaoqiao, ZHANG Xiaodie, ZHAO Zhenxi, XIE Pengliu, DAI Min

Kunming Center for Disease Control and Prevention, Kunming, Yunnan 650000, China

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (974 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract 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.

Key words： hand foot and mouth disease incidence seasonal autoregressive integrated moving average model seasonal autoregressive integrated moving average model with exogenous regressors long short-term memory neural network model prediction

Received: 18 October 2024 Revised: 17 February 2025 Published: 17 March 2025

ZTFLH:

R725.1

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	ZHANG Xiaoqiao
	ZHANG Xiaodie
	ZHAO Zhenxi
	XIE Pengliu
	DAI Min

Cite this article:

ZHANG Xiaoqiao,ZHANG Xiaodie,ZHAO Zhenxi, et al. Comparison of the prediction effects of LSTM, SARIMA and SARIMAX models on the incidence of hand, foot, and mouth disease[J]. Preventive Medicine, 2025, 37(3): 280-284,287.

URL:

http://www.zjyfyxzz.com/EN/10.19485/j.cnki.issn2096-5087.2025.03.014 OR http://www.zjyfyxzz.com/EN/Y2025/V37/I3/280

[1] 庞孟涛,李傅冬,林君芬,等.2016—2019年浙江省手足口病流行特征[J].预防医学,2022,34(3):307-310.
PANG M T,LI F D,LIN J F,et al.Epidemiological characteristics of hand,foot and mouth disease in Zhejiang Province from 2016 to 2019[J].China Prev Med J,2022,34(3):307-310.(in Chinese)
[2] 杨溪,曹亿会,寸建萍,等.2015—2019年云南省手足口病流行及病原学特征分析[J].职业卫生与病伤,2022,37(5):278-282.
YANG X,CAO Y H,CUN J P,et al.Epidemiological and etiological characteristics of hand-foot-mouth disease in Yunnan Province from 2015 to 2019[J].Occup Health Damage,2022,37(5):278-282.(in Chinese)
[3] YU Y,SI X S,HU C H,et al.A review of recurrent neural networks:LSTM cells and network architectures[J].Neural Comput,2019,31(7):1235-1270.
[4] 刘天,吴杨,陈琦,等.SARIMA模型与prophet模型对手足口病周发病率拟合及预测效果比较[J].预防医学情报杂志,2022,38(10):1346-1350.
LIU T,WU Y,CHEN Q,et al.Comparison of SARIMA model and prophet model on the weekly incidence of hand,foot and mouth disease[J].J Prev Med Inf,2022,38(10):1346-1350.(in Chinese)
[5] 杨溪,姜黎黎,曹亿会,等.云南省2009—2019年手足口病流行特征及病原学特征分析[J].现代预防医学,2021,48(5):789-792.
YANG X,JIANG L L,CAO Y H,et al.Epidemiological and etiological characteristics of hand-foot-mouth disease in Yunnan Province,2009-2019[J].Mod Prev Med,2021,48(5):789-792.(in Chinese)
[6] 聂陶然. 手足口病重症及死亡病例流行特征及病原谱的研究[D].北京:中国疾病预防控制中心,2020.
NIE T R.Study on the epidemiological characteristics and etiological spectrum of severe and fatal cases of hand-foot-mouth disease[D].Beijing:Chinese Center for Disease Control and Prevention,2020.(in Chinese)
[7] 王佳琪,王松旺,赵自雄,等.2010—2019年中国南亚热带地区气象因素对手足口病发病的影响[J].疾病监测,2024,39(6):705-710.
WANG J Q,WANG S W,ZHAO Z X,et al.Influence of meteorological factors on incidence of hand,foot and mouth disease in subtropic area in China,2010-2019[J].Dis Surveill,2024,39(6):705-710.(in Chinese)
[8] 康殿巨,斯郎格玛,程秀伟,等.2015—2020年四川省手足口病流行病学特征分析[J].实用预防医学,2022,29(8):920-923.
KANG D J,SILANG G M,CHENG X W,et al.Epidemiological characteristics of hand-foot-mouth disease in Sichuan Province,2015-2020[J].Pract Prev Med,2022,29(8):920-923.(in Chinese)
[9] 杨琳,李勤,赵寒,等.2008—2018年重庆市肠道传染病流行特征分析[J].实用预防医学,2020,27(3):327-329.
YANG L,LI Q,ZHAO H,et al.Analysis of epidemiological characteristics of intestinal infectious diseases in Chongqing from 2008 to 2018[J].Pract Prev Med,2020,27(3):327-329.(in Chinese)
[10] 孙进,刘今,孙明丽,等.结合气象与经济因素应用长短期记忆网络模型预测郑州市手足口病的发病趋势[J].中国医科大学学报,2023,52(6):520-526.
SUN J,LIU J,SUN M L,et al.Using long short term memory model combined with economic and meteorological factors to predict incidence trends of hand-foot-mouth disease in Zhengzhou City[J].J China Med Univ,2023,52(6):520-526.(in Chinese)