Application of SARIMA-GRNN combined model in forecasting the monthly incidence of typhoid fever and paratyphoid fever

LI Wen-hao; ZENG Yu-xing; LI Xiao-yan; PENG Yuan-zhou; ZHANG Yan-wei; CHEN Qing-shan; CHENG Jin-quan

doi:10.16462/j.cnki.zhjbkz.2021.11.019

Volume 25 Issue 11

Nov. 2021

Turn off MathJax

Article Contents

Article Navigation > CHINESE JOURNAL OF DISEASE CONTROL & PREVENTION > 2021 > 25(11): 1341-1346

LI Wen-hao, ZENG Yu-xing, LI Xiao-yan, PENG Yuan-zhou, ZHANG Yan-wei, CHEN Qing-shan, CHENG Jin-quan. Application of SARIMA-GRNN combined model in forecasting the monthly incidence of typhoid fever and paratyphoid fever[J]. CHINESE JOURNAL OF DISEASE CONTROL & PREVENTION, 2021, 25(11): 1341-1346. doi: 10.16462/j.cnki.zhjbkz.2021.11.019

Citation:

LI Wen-hao, ZENG Yu-xing, LI Xiao-yan, PENG Yuan-zhou, ZHANG Yan-wei, CHEN Qing-shan, CHENG Jin-quan. Application of SARIMA-GRNN combined model in forecasting the monthly incidence of typhoid fever and paratyphoid fever[J]. CHINESE JOURNAL OF DISEASE CONTROL & PREVENTION, 2021, 25(11): 1341-1346. doi: 10.16462/j.cnki.zhjbkz.2021.11.019

Citation:

LI Wen-hao, ZENG Yu-xing, LI Xiao-yan, PENG Yuan-zhou, ZHANG Yan-wei, CHEN Qing-shan, CHENG Jin-quan. Application of SARIMA-GRNN combined model in forecasting the monthly incidence of typhoid fever and paratyphoid fever[J]. CHINESE JOURNAL OF DISEASE CONTROL & PREVENTION, 2021, 25(11): 1341-1346. doi: 10.16462/j.cnki.zhjbkz.2021.11.019

PDF( 3322 KB)

Application of SARIMA-GRNN combined model in forecasting the monthly incidence of typhoid fever and paratyphoid fever

doi: 10.16462/j.cnki.zhjbkz.2021.11.019

1.
Department of Epidemiology, College of Basic Medicine and Public Health, Jinan University, Guangzhou 510630, China
2.
Department of Epidemiology and Statistics, College of Public Health, Sun Yat-sen University, Shenzhen 518000, China
3.
Institute of Immunization Program, Shenzhen Center for Disease Control and Prevention, Shenzhen 518000, China

Funds:

Major science and technology projects of the 13th Five-Year plan 2018ZX10715004

More Information

Corresponding author: CHENG Jin-quan, E-mail: cjinquan@szcdc.net
Received Date: 2020-12-07
Rev Recd Date: 2021-05-20

Available Online: 2021-12-04

Publish Date: 2021-11-10

Abstract

Abstract

Objective This study aimed to establish a seasonal autoregressive integrated moving average (SARIMA)-general regression neural network (GRNN) combined model, so as to provide new methodological ideas for forecasting the incidence of typhoid fever and paratyphoid fever. Methods Using data of typhoid fever and paratyphoid fever from January 2011 to December 2019, the SARIMA model and the SARIMA-GRNN combined model were constructed respectively, and the fitting and forecasting effects of the two models were compared. Results The optimal SARIMA model was SARIMA (2, 1, 1) (0, 1, 1)₁₂ and the optimal smoothing factor of SARIMA-GRNN combined model was 0.21. The root mean squared error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) of the SARIMA-GRNN combined model fitting effect were 90.08, 71.44, and 7.07%, which were smaller than the SARIMA model's 99.44, 79.15, and 7.86% respectively. The RMSE, MAE, and MAPE of the forecasting effect were 100.86, 75.94, 9.57%, which were all smaller than 125.44, 97.33, 10.89% of the SARIMA model. Conclusions The SARIMA-GRNN combined model has a better fitting effect and higher forecasting effect than the traditional SARIMA model to forecast the monthly incidence of typhoid fever and paratyphoid fever in China. It can be used to predict the monthly incidence of typhoid fever and paratyphoid fever.
- Typhoid fever and paratyphoid fever,
- SARIMA Model,
- GRNN,
- Combined Model

FullText(HTML)

References(13)

References

[1]	张莹, 张静. 伤寒、副伤寒疾病负担研究现状[J]. 中华疾病控制杂志, 2011, 15(5): 437-440. http://zhjbkz.ahmu.edu.cn/article/id/JBKZ201105024 Zhang Y, Zhang J. The current research status of typhoid and paratyphoid disease burden[J]. Chin J Dis Control Prev, 2011, 15(5): 437-440. http://zhjbkz.ahmu.edu.cn/article/id/JBKZ201105024
[2]	Fattah J, Ezzine L, Aman Z, et al. Forecasting of demand using ARIMA model[J]. International Journal of Engineering Business Management, 2018, 10: 1-9. DOI: 10.1177/1847979018808673.
[3]	卞子龙, 汤佳琪, 倪春辉, 等. 应用ARIMA-GRNN组合模型分析江苏尘肺病发病情况[J]. 环境与职业医学, 2019, 36(8): 755-760. DOI: 10.13213/j.cnki.jeom.2019.19046. Bian ZL, Tang JQ, Ni CH, et al. Application of ARIMA-GRNN combined model to analyze the incidence of pneumoconiosis in Jiangsu[J]. Journal of Environmental and Occupational Medicine, 2019, 36(8): 755-760. DOI: 10.13213/j.cnki.jeom.2019.19046.
[4]	叶晓军, 沈毅, 任茹香, 等. 基于GRNN的组合预测模型在传染病发病率预测中的应用[J]. 浙江预防医学, 2012, 24(1): 8-13. DOI:10.19485/j.cnki.issn1007-0931.2012.0 1.003. Ye XJ, Shen Y, Ren RX, et al. Application of combined forecasting model based on GRNN in forecasting the incidence of infectious diseases[J]. Zhejiang Preventive Medicine, 2012, 24(1): 8-13. DOI: 10.19485/j.cnki.issn1007-0931.2012.01.003.
[5]	彭志行, 鲍昌俊, 赵杨, 等. 乘积季节模型在伤寒副伤寒发病预测中的应用探析[J]. 中华疾病控制杂志, 2007, 11(6): 560-563. http://zhjbkz.ahmu.edu.cn/article/id/JBKZ200706009 Peng ZX, Bao CJ, Zhao Y, et al. Application of product seasonal model in predicting the incidence of typhoid and paratyphoid[J]. Chin J Dis Control Prev, 2007, 11(6): 560-563. http://zhjbkz.ahmu.edu.cn/article/id/JBKZ200706009
[6]	周敏, 李世玲. 广义回归神经网络在非线性系统建模中的应用[J]. 计算机测量与控制, 2007, 15(9): 1189-1191. DOI: 10.16526/j.cnki.11-4762/tp.2007.09.032. Zhou M, Li SL. Application of generalized regression neural network in modeling of nonlinear system[J]. Computer Measurement & Control, 2007, 15(9): 1189-1191. DOI: 10.16526/j.cnki.11-4762/tp.2007.09.032.
[7]	Wei W, Jiang J, Gao L, et al. A new hybrid model using an autoregressive integrated moving average and a generalized regression neural network for the incidence of tuberculosis in Heng county, China[J]. Am J Trop Med Hyg, 2017, 97(3): 799-805. DOI: 10.1371/journal.pone.0156768.
[8]	王雅文, 沈忠周, 严宝湖, 等. ARIMA模型和ARIMA-GRNN模型在AIDS发病预测中的应用[J]. 中华疾病控制杂志, 2018, 22(12): 1287-1290. DOI:10.1646 2/j.cnki.zhjbkz.2018.12.020. Wang YW, Shen ZZ, Yan BH, et al. Application of ARIMA model and ARIMA-GRNN model in predicting the incidence of AIDS[J]. Chin J Dis Control Prev, 2018, 22(12): 1287-1290. DOI:10.1646 2/j.cnki.zhjbkz.2018.12.020.
[9]	王鲁茜, 阚飙. 伤寒、副伤寒的全球流行概况及其预防控制[J]. 疾病监测, 2007, 22(7): 492-494. doi: 10.3784/j.issn.1003-9961.2007.07.022 Wang LX, Kan B. The global epidemic situation of typhoid and paratyphoid fever and its prevention and control[J]. Disease Surveillance, 2007, 22(7): 492-494. doi: 10.3784/j.issn.1003-9961.2007.07.022
[10]	刘凤凤, 赵善露, 陈琦, 等. 2015年中国伤寒、副伤寒流行病学特征和空间聚类分析[J]. 中华流行病学杂志, 2017, 38(6): 754-758. DOI:10.3760/cma.j.issn.0254 -6450.2017.06.013. Liu FF, Zhao SL, Chen Q, et al. Epidemiological characteristics and spatial cluster analysis of typhoid fever and paratyphoid fever nationwide in 2015[J]. Chin J Epidemiol, 2017, 38(6): 754-758. DOI:10.3760/cma.j.issn.0254 -6450.2017.06.013.
[11]	黎景雪, 王培承, 邱瑞香, 等. 灰色模型在我国伤寒副伤寒发病率预测中的应用[J]. 数理医药学杂志, 2010, 23(5): 506-508. DOI:10.3969/j.issn.1004-4337.20 10.05.002. Li JX, Wang PC, Qiu RX, et al. Application of grey model in predicting the incidence of typhoid and paratyphoid in my country[J]. Journal of Mathematical Medicine, 2010, 23(5): 506-508. DOI:10.3969/j.issn.1004-4337.20 10.05.002.
[12]	彭志行, 鲍昌俊, 赵杨, 等. 加权马尔可夫链在伤寒副伤寒发病情况预测分析中的应用[J]. 中国卫生统计, 2008, 25(3): 226-229. DOI:CNKI:SUN:ZGWT.0.2008-03-002. Peng ZX, Bao CJ, Zhao Y, et al. Application of Weighted Markov Chain in Prediction and Analysis of Typhoid and Paratyphoid[J]. Chinese Journal of Health Statistics, 2008, 25(3): 226-229. DOI:CNKI:SUN:ZGWT.0.2008-03-002.
[13]	Wang Y, Shen Z, Jiang Y. Comparison of autoregressive integrated moving average model and generalised regression neural network model for prediction of haemorrhagic fever with renal syndrome in China: a time-series study[J]. BMJ open, 2019, 9(6): e025773. DOI: 10.1136/bmjopen-2018-025773.