ARIMA模型和LSTM模型在布鲁菌病发病趋势预测中的应用

职业与健康 ›› 2024, Vol. 40 ›› Issue (17): 2377-2382.

ARIMA模型和LSTM模型在布鲁菌病发病趋势预测中的应用

范奔^1,2, 王童敏², 赵倩², 杨柳根¹, 马晓玲², 李凡卡^1,2

1.石河子大学医学院预防医学系,新疆石河子 832000;
2.新疆生产建设兵团疾病预防控制中心疾病预防控制科,新疆乌鲁木齐 830002

收稿日期:2023-12-13 修回日期:2024-01-08 发布日期:2026-03-17
通信作者: 王童敏,副主任医师,E-mail：wtm1123@163.com;李凡卡,主任医师,E-mail：lifanka@sina.com
作者简介:范奔,女,在读硕士研究生,研究方向为传染病流行病学。
基金资助:
新疆生产建设兵团疾病预防控制中心自主课题（BTCD CKY202203）

Application of ARIMA model and LSTM model in predicting the incidence trend of brucellosis

FAN Ben^1,2, WANG Tongmin², ZHAO Qian², YANG Liugen¹, MA Xiaoling², LI Fanka^1,2

1. Department of Preventive Medicine,School of Medicine,Shihezi University,Shihezi,Xinjiang 832000,China;
2. Disease Prevention and Control Department,Center for Disease Control and Prevention of Xinjiang Production and Construction Corps,Urumqi,Xinjiang 830002,China

Received:2023-12-13 Revised:2024-01-08 Published:2026-03-17
Contact: WANG Tongmin,Associate chief physician,E-mail：wtm1123@163.com;LI Fanka,Chief physician,E-mail：lifanka@sina.com

摘要/Abstract

摘要： 目的分析新疆生产建设兵团（简称兵团）布鲁菌病发病趋势,探讨差分自回归移动平均（autoregressive integrated moving average model,ARIMA）模型和长短期记忆网络（long short-term memory,LSTM）模型在布鲁菌病发病预测中的应用。方法根据2010—2022年兵团布鲁菌病月报告发病病例数据,建立ARIMA模型和LSTM神经网络模型,对兵团布鲁菌病发病数进行拟合及预测,通过比较均方根误差（root mean squared error,RMSE）、平均绝对误差（mean absolute error,MAE）及决定系数（coefficient of determination,R²）的大小对模型进行预测效果评价。结果 ARIMA（1,0,1）（0,1,2）₁₂模型拟合和预测的RMSE和MAE分别为19.72、16.40、12.02和8.16,拟合的R²为82.51,LSTM神经网络模型拟合和预测的RMSE和MAE分别为13.37、10.88、10.26和7.71,拟合的R²为84.70。LSTM模型的拟合及预测效果显著优于ARIMA（1,0,1）（0,1,2）₁₂。ARIMA模型和LSTM模型预测2023—2024年兵团布鲁菌病病例数分别为773和789例。结论兵团13年来布鲁菌病发病总体呈上升趋势,且存在一定的季节性趋势。LSTM模型可较好地拟合和预测兵团布鲁菌病的发病数及趋势,且模型效果优于ARIMA（1,0,1）（0,1,2）₁₂模型,能在一定程度上提高预测精确度,为布鲁菌病的防控提供参考依据。

关键词: 布鲁菌病, 差分自回归移动平均模型, 长短期记忆网络模型, 发病预测

Abstract: Objective To analyze the incidence trend of brucellosis in Xinjiang Production and Construction Corps,and explore the application of autoregressive integrated moving average model（ARIMA） and long short-term memory（LSTM） model in the prediction of brucellosis incidence. Methods Based on monthly reported cases of brucellosis from 2010 to 2022,ARIMA and LSTM models were established to fit and predict the incidence of brucellosis in the Xinjiang Production and Construction Corps. The prediction performance of the models was evaluated by comparing the root mean square error（RMSE）,mean absolute error（MAE）,and coefficient of determination（R²）. Results The RMSE and MAE fitted and predicted by ARIMA（1,0,1）（0,1,2）₁₂ model were 19.72,16.40,12.02 and 8.16,respectively,and the fitted R² was 82.51. The RMSE and MAE fitted and predicted by LSTM neural network model were 13.37,10.88,10.26 and 7.71,respectively,and the fitted R² was 84.70. LSTM model had better fitting and prediction effect than ARIMA（1,0,1）（0,1,2）₁₂. The ARIMA model and LSTM model predict 773 and 789 cases of brucellosis in the Xinjiang Production and Construction Corps from 2023 to 2024,respectively. Conclusion In the past 13 years,the incidence of brucellosis in the Xinjiang Production and Construction Corps had shown an overall upward trend,and there was a certain seasonal trend. LSTM model can better fit and predict the incidence and trend of brucellosis,and the model effect is better than ARIMA（1,0,1）（0,1,2）₁₂ model,which can improve the prediction accuracy to a certain extent and provide reference for the prevention and control of brucellosis.

Key words: Brucellosis, Autoregressive integrated moving average model, Long short-term memory model, Disease prediction

中图分类号:

R181.2

范奔, 王童敏, 赵倩, 杨柳根, 马晓玲, 李凡卡. ARIMA模型和LSTM模型在布鲁菌病发病趋势预测中的应用. [J]职业与健康, 2024, 40(17): 2377-2382.

FAN Ben, WANG Tongmin, ZHAO Qian, YANG Liugen, MA Xiaoling, LI Fanka. Application of ARIMA model and LSTM model in predicting the incidence trend of brucellosis. [J]OCCUPATION AND HEALTH, 2024, 40(17): 2377-2382.

参考文献

[1] JIA P,JOYNER A.Human brucellosis occurrences in inner mongolia,China:A spatio-temporal distribution and ecological niche modeling approach[J].BMC Infect Dis,2015,15:36.
[2] ZHENG R,XIE S,LU X,et al.A systematic review and meta-analysis of epidemiology and clinical manifestations of human brucellosis in China[J].Biomed Res Int,2018,2018:5712920.
[3] 康育慧,崔咏梅,曹文君.2011—2017年我国人间布鲁氏菌病发病的长期趋势和季节性研究[J].中国卫生统计,2018,35(6):895-897.
[4] FRANC K A,KRECEK R C,HSLEr B N,et al.Brucellosis remains a neglected disease in the developing world:a call for interdisciplinary action[J].BMC Public Health,2018,18(1):125.
[5] 张翀. 长短期记忆网络深度学习模型对人布鲁氏菌病预测研究[D].沈阳:中国医科大学,2021.
[6] ZHAO J,DENG F,CAI Y,et al.Long short-term memory-fully connected(LSTM-FC) neural network for PM_2.5 concentration prediction[J].Chemosphere,2019,220:486-492.
[7] PATHAN R K,BISWAS M,KHANDAKER M.Time series prediction of COVID-19 by mutation rate analysis using recurrent neural network-based LSTM model[J].Chaos Solitons Fractals,2020,138:110018.
[8] LIAO Z Y,ZHANG X N,ZHANG Y H,et al.Seasonality and trend forecasting of tuberculosis incidence in Chongqing,China[J].Interdiscip Sci,2019,11(1):77-85.
[9] TIAN C W,WANG H,LUO X M.Time-series modelling and forecasting of hand,foot and mouth disease cases in China from 2008 to 2018[J].Epidemiol Infect,2019,147:e82.
[10] VALENCIA V N,DIAZ Y,PASCALE J M,et al.Assessing the effect of climate variables on the incidence of dengue cases in the metropolitan region of panama city[J].Int J Environ Res Public Health,2021,18(22):12108.
[11] MOLINA L L,ANGÓN E,GARCíA A,et al.Time series analysis of bovine venereal diseases in La Pampa,Argentina[J].PLoS One,2018, 13(8):e0201739.
[12] 李沁林,刘雪娜.2008—2018年中国甲乙类传染病流行病学特征[J].泰山医学院学报,2021,42(1):13-16.
[13] LAI S J,CHEN Q L,LI Z J.Human brucellosis:An ongoing global health challenge[J].China CDC Wkly,2021,3(6):120-123.
[14] 向泽林,顾伟玲,富小飞,等.2010—2021年嘉兴市布鲁氏菌病流行特征[J].预防医学,2023,35(1):41-43.
[15] 陈礼朋,张淼,李新生,等.我国人畜间布鲁氏菌病流行状况[J].中国动物检疫,2018,35(10):1-5.
[16] 于维君,王子江,毛玲玲,等.2016—2020年辽宁省人间布鲁氏菌病流行特征分析[J].疾病监测,2021,36(12):1257-1260.
[17] 包红红,孟巧玲,韩俊锋.灰色模型预测河南省安阳市人布鲁菌病发病趋势[J].中华地方病学杂志,2017,36(10):706-708.
[18] 彭阳. ARIMA模型在预测南阳市人间布鲁氏菌病发病风险中的运用[J].江苏预防医学,2021,32(4):431-433.
[19] 付全. 锡林郭勒盟布鲁氏菌病流行特征分析和ARIMA模型的建立[D].呼和浩特:内蒙古医科大学,2021.
[20] 倪茹玉,胡婉,张恒川,等.ARIMA乘积季节模型与LSTM神经网络模型对我国麻疹发病数预测效果的比较[J].现代预防医学,2023, 50(1):177-182.
[21] TSAN Y T,CHEN D Y,LIU P Y,et al.The prediction of influenza-like illness and respiratory disease using LSTM and ARIMA[J].Int J Environ Res Public Health,2022,19(3):1858.
[22] 高秋菊,周宇畅,赵树青,等.ARIMA乘积季节模型和LSTM深度神经网络对石家庄市手足口病疫情预测效果的比较[J].中华疾病控制杂志,2020,24(1):73-78.
[23] 马晓梅,史鲁斌,其木格,等.基于ARIMA乘积季节模型和Holt-Winters季节模型的梅毒月发病率预测[J].郑州大学学报(医学版),2018,53(1):79-84.
[24] 杨敏雪,于斐,王培生,等.基于ARIMA和LSTM神经网络的乌鲁木齐市乙型肝炎发病预测研究[J].现代预防医学,2022,49(16):2903-2907.