您的位置:山东大学 -> 科技期刊社 -> 《山东大学学报(医学版)》

山东大学学报(医学版) ›› 2016, Vol. 54 ›› Issue (9): 82-86.doi: 10.6040/j.issn.1671-7554.0.2015.1163

• • 上一篇    下一篇

SARIMA模型在流行性腮腺炎发病预测中的应用

李润滋1,章涛1,梁玉民2,罗成1,蒋正1,薛付忠1,刘言训1,刘静1,李秀君1   

  1. 1. 山东大学公共卫生学院生物统计学系, 山东 济南 250012;2. 济宁市疾病预防控制中心, 山东 济宁 272000
  • 收稿日期:2015-11-24 出版日期:2016-09-10 发布日期:2016-09-10
  • 通讯作者: 李秀君. E-mail:xjli@sdu.edu.cn E-mail:xjli@sdu.edu.cn
  • 基金资助:
    山东省科技发展计划(2014GGH218019);病原微生物生物安全国家重点实验室开放课题(SKLPBS1453)

Application of SARIMA model in predicting the incidence of mumps

LI Runzi1, ZHANG Tao1, LIANG Yumin 2, LUO Cheng1, JIANG Zheng1, XUE Fuzhong1, LIU Yanxun1, LIU Jing1, LI Xiujun1   

  1. 1. Department of Biostatistics, School of Public Health, Shandong University, Jinan 250012, Shandong, China;
    2. Center for Disease Control and Prevention of Jining City, Jining 272000, Shandong, China
  • Received:2015-11-24 Online:2016-09-10 Published:2016-09-10

摘要: 目的 利用SARIMA模型预测未来山东省济宁市流行性腮腺炎发病情况,为流行性腮腺炎防控提供决策依据。 方法 收集山东省济宁市2009年1月至2013年7月流行性腮腺炎月发病数据资料,利用时间序列分析方法,构建SARIMA模型,并对2013年8月至12月的发病数资料进行预测。 结果 济宁市2009至2013年共报告流行性腮腺炎病例数8 520例,且发病具有明显的周期性和季节性特征。最终建立的最优模型为SARIMA(0,1,1)(0,1,1)12,赤池信息准则(AIC)为74.45,且通过了统计学检验,模型残差为白噪声。实际月发病数与拟合月发病数进行相关性分析结果显示为显著性相关(r=0.75,P<0.000 1)。对2013年8月至12月发病数进行预测,均在95%置信区间内,且与实际发病数变动的趋势一致,验证了模型合理性。 结论 SARIMA模型能较好地拟合济宁市流行性腮腺炎月发病数动态变化,可用于流行性腮腺炎的短期预测。

关键词: 预测, 时间序列分析, 季节性差分自回归移动平均模型, 流行性腮腺炎

Abstract: Objective To predict the incidence of mumps with autoregressive integrated moving average(SARIMA)model so as to provide scientific guidance for its prevention and control. Methods Time-series data of monthly mumps cases from Jan. 2009 to July 2013 were analyzed using SARIMA model and predictive model was established to predict the incidence from August to December 2013. Results From 2009 to 2013, a total of 8,520 cases of mumps were reported in Jining City. Eventually the optimal model of SARIMA(0,1,1)(0,1,1)12 was established, and the information criterion(AIC)was 74.45. Parameters estimated were statistically significant, and residuals were white noise sequence. Monthly mumps cases from January 2009 to July 2013 were used for model fitting and the monthly mumps cases from Aug. to Dec. 2013 predicted by the optimal model were within the 95% confidence interval, and were consistent with the trend of the actual incidence, which demonstrated the rationality of the model. Correlation between actual case number and fitted case number was statistically significant(r=0.75, P<0.000 1). Conclusion SARIMA model can fit the incidence of dynamic change of mumps, and can be used to make short-term prediction and to provide scientific evidence for the prevention and control of mumps.

Key words: Time series analysis, Seasonal autoregressive integrated moving average model, Prediction, Mumps

中图分类号: 

  • R181.25
[1] Dayan GH, Quinlisk MP, Parker AA, et al. Recent resurgence of mumps in the United States[J]. N Engl J Med, 2008, 358(15):1580-1589.
[2] Galazka AM, Robertson SE, Kraigher A. Mumps and mumps vaccine: a global review[J]. Bull World Health Organ, 1999, 77(1):3-14.
[3] Mumps virus vaccines[J]. Wkly Epidemiol Rec, 2007, 82(7):51-60.
[4] Hviid A, Rubin S, Muhlemann K. Mumps[J]. Lancet, 2008, 371(9616):932-944.
[5] Yang Q, Yang Z, Ding H, et al. The relationship between meteorological factors and mumps incidence in Guangzhou, China, 2005-2012[J]. Hum Vaccin Immunother, 2014, 10(8):2421-2432.
[6] Fu CX, Nie J, Liang JH, et al. Evaluation of live attenuated S79 mumps vaccine effectiveness in mumps outbreaks: a matched case-control study[J]. Chin Med J(Engl), 2009, 122(3):307-310.
[7] 彭志行, 陶红, 贾成梅, 等. 时间序列分析在麻疹疫情预测预警中的应用研究[J]. 中国卫生统计, 2010, 27(5):459-463. PENG Zhihang, TAO Hong, JIA Chengmei, et al. Application of time series analysis in the prediction of measles incidence[J]. Chinese Journal of Health Statistics, 2010, 27(5):459-463.
[8] Moosazadeh M, Nasehi M, Bahrampour A, et al. Forecasting tuberculosis incidence in Iran using box-jenkins models[J]. Iran Red Crescent Med J, 2014, 16(5): e11779. doi:10.5812/ircmj.11779
[9] Martinez EZ, Silva EA. Predicting the number of cases of dengue infection in Ribeirao Preto, Sao Paulo State, Brazil, using a SARIMA model[J]. Cad Saude Publica, 2011, 27(9):1809-1818.
[10] 金如锋, 邱宏, 周霞, 等. ARIMA模型和GM(1,1)模型预测全国3种肠道传染病发病率[J]. 复旦学报(医学版), 2008, 35(5):675-680. JIN Rufeng, QIU Hong, ZHOU Xia, et al. Forecasting incidence of three intestinal infectious diseases in China with ARIMA model and GM(1,1)model[J]. Fudan University Journal of Medical Sciences, 2008, 35(5):675-680.
[11] 马亮亮, 田富鹏. 不同时间序列分析方法在高血压发病率预测中的比较[J]. 中国老年学杂志, 2010, 30(13):1777-1780. MA Liangliang, TIAN Fupeng. Application of time series analysis in the prediction of hypertension incidence[J]. Chinese Journal of Gerontology, 2010, 30(13):1777-1780.
[12] 李秀君, 康殿民, 曹杰, 等. 时间序列模型在肾综合征出血热发病率预测中的应用[J]. 山东大学学报(医学版), 2008, 46(5):547-549. LI Xiujun, KANG Dianmin, CAO Jie, et al. Application of time series analysis in the prediction of hemorrhagic fever of renal syndrome incidence[J]. Journal of Shandong University(Health Science), 2008, 46(5):547-549.
[13] 许阳婷. ARIMA模型在流行性腮腺炎发病率预测中的应用[J]. 华南预防医学, 2015, 41(3):255-259. XU Yangting. Application of time series analysis in the prediction of mumps incidence[J]. South China Journal of Preventive Medicine, 2015, 41(3):255-259.
[14] Liu L, Luan RS, Yin F, et al. Predicting the incidence of hand, foot and mouth disease in Sichuan province, China using the ARIMA model[J]. Epidemiol Infect, 2016, 144(1):144-151.
[15] 赛晓勇, 张治英, 徐德忠, 等. 不同时间序列分析法在洞庭湖区血吸虫病发病预测中的比较[J]. 中华流行病学杂志, 2004, 25(10):40-43. SAI Xiaoyong, ZHANG Zhiying, XU Dezhong, et al. Different time series analysis method on the prediction of schistosomiasis in Dongting Lake regions[J]. Chinese Journal of Epidemiology, 2004, 25(10):40-43.
[16] Kane MJ, Price N, Scotch M, et al. Comparison of ARIMA and Random Forest time series models for prediction of avian influenza H5N1 outbreaks[J]. BMC Bioinformatics, 2014, 15(1):276. doi:10.1186/1471-2105-15-276.
[1] 肖宇飞,冯佳宁,王晓璇,毛倩,石福艳,王素珍. 利用数据库数据采用联合模型动态预测312例肝硬化患者预后的观察分析[J]. 山东大学学报 (医学版), 2020, 1(9): 71-76.
[2] 吴强,何泽鲲,刘琚,崔晓萌,孙双,石伟. 基于机器学习的脑胶质瘤多模态影像分析[J]. 山东大学学报 (医学版), 2020, 1(8): 81-87.
[3] 李吉庆,赵焕宗,宋炳红,张理纯,李向一,陈亚飞,王萍,薛付忠. 基于健康管理队列的心血管事件风险预测模型[J]. 山东大学学报(医学版), 2017, 55(6): 56-60.
[4] 于涛,刘焕乐,冯新,徐付印,陈亚飞,薛付忠,张成琪. 基于健康管理队列的高血压风险预测模型[J]. 山东大学学报(医学版), 2017, 55(6): 61-65.
[5] 王春霞,许艺博,杨宁,夏冰,王萍,薛付忠. 基于健康管理队列的冠心病风险预测模型[J]. 山东大学学报(医学版), 2017, 55(6): 66-71.
[6] 张光,王广银,吴红彦, 张红玉,王停停,李吉庆,李敏,康凤玲,刘言训,薛付忠. 健康管理人群高脂血症风险预测模型[J]. 山东大学学报(医学版), 2017, 55(6): 72-76.
[7] 苏萍,杨亚超,杨洋,季加东,阿力木·达依木,李敏,薛付忠,刘言训. 健康管理人群2型糖尿病发病风险预测模型[J]. 山东大学学报(医学版), 2017, 55(6): 82-86.
[8] 孙苑潆,杨亚超,曲明苓,陈雁敏,李敏,王淑康,薛付忠,刘云霞. 健康管理人群代谢综合征发病风险预测模型[J]. 山东大学学报(医学版), 2017, 55(6): 87-92.
[9] 周苗,夏同耀,孙爱玲,李明,申振伟,卞伟玮,蒋正,康凤玲,柳晓涓,薛付忠,刘静. 健康管理人群慢性肾脏病风险预测模型[J]. 山东大学学报(医学版), 2017, 55(6): 98-103.
[10] 李敏,王春霞,夏冰,朱茜,孙苑潆,王淑康,薛付忠,贾红英. 健康管理人群脑卒中风险预测模型[J]. 山东大学学报(医学版), 2017, 55(6): 93-97.
[11] 于媛媛,王春霞,苏萍,孙苑潆,薛付忠,刘言训. 健康管理队列白内障发病风险预测模型[J]. 山东大学学报(医学版), 2017, 55(6): 104-107.
[12] 张振堂,杨洋,韩福俊,陈向华,季晓康,王永超,王淑康,孙苑潆,李敏,陈亚飞,王丽,薛付忠,刘言训. 基于社区2型糖尿病患者的心脑血管事件5年风险预测模型[J]. 山东大学学报(医学版), 2017, 55(6): 108-113.
[13] 杨洋,张光,张成琪,宋心红,薛付忠,王萍,王丽,刘言训. 基于体检队列的2型糖尿病风险预测模型[J]. 山东大学学报(医学版), 2016, 54(9): 69-72.
[14] 曹洪丽1,刘书盈2. 血清脑钠肽浓度与肺癌的相关性[J]. 山东大学学报(医学版), 2013, 51(8): 62-64.
[15] 王爱光1,崔蕾2,王桂玲2,李建志2,张梅芳2,赵敏2,孙爱华2,单容2. FibroScan检测肝脏硬度影响因素的多元回归分析[J]. 山东大学学报(医学版), 2013, 51(8): 69-73.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!