基于贝叶斯网络的肾综合征出血热发病率预测模型研究

李皓晨, 齐滢滢, 张翀, 韩文菊, 沈铁峰, 李德强, 关鹏, 黄德生

doi:10.11853/j.issn.1003.8280.2021.04.019

中国媒介生物学及控制杂志 >

2021 , Vol. 32 >Issue 4: 475 - 480

DOI: https://doi.org/10.11853/j.issn.1003.8280.2021.04.019

技术与方法

基于贝叶斯网络的肾综合征出血热发病率预测模型研究

展开

1. 中国医科大学公共卫生学院流行病学教研室, 辽宁沈阳 110122;
2. 葫芦岛市疾病预防控制中心, 辽宁葫芦岛 125000;
3. 中国医科大学公共基础学院数学教研室, 辽宁沈阳 110122

李皓晨,女,在读硕士,主要从事传染病流行病学研究,E-mail:hcli@cmu.edu.cn

收稿日期: 2020-10-28

网络出版日期: 2021-08-20

基金资助

国家自然科学基金（71974199）；中国医科大学新冠肺炎疫情防控相关科研攻关基金资助项目（医大科发〔2020〕12号）

收起

A Bayesian network-based prediction model for the incidence of hemorrhagic fever with renal syndrome

Expand

1. Departnnent of Epidemidogy, School of Public Health, China Medical University, Shenyang, Liaoning 110122, China;
2. Huludao Center for Disease Control and Prevention, Huludao, Liaoning 125000, China;
3. School of Fundamental Sciences, China Medical University, Shenyang, Liaoning 110122, China

Received date: 2020-10-28

Online published: 2021-08-20

Supported by

Supported by the National Natural Science Foundation of China (No. 71974199) and China Medical University Special Grant for COVID-19 Prevention and Control (No. CMU-K-2020-12)

Fold

摘要

目的利用贝叶斯网络研究辽宁省葫芦岛市肾综合征出血热（HFRS）的影响因素并构建发病率预测模型。方法收集葫芦岛市2008年1－10月HFRS监测点的发病数据、宿主疫情数据及气象数据，采用禁忌搜索算法对贝叶斯网络进行结构学习，采用最大似然估计对贝叶斯网络进行参数学习。结果葫芦岛市HFRS发病与鼠密度、当月的平均风速和日照时数、滞后1个月的平均最高气温、相对湿度和归一化植被指数、滞后2个月的平均气温、平均最低气温、平均气压和降水量在0.01水平上相关，相关系数分别为0.691、0.689、0.345、-0.635、-0.631、-0.674、-0.714、-0.746、0.650和-0.643。利用气象和宿主资料对HFRS发病率进行预测时，贝叶斯网络模型的预测准确率为85.00%（17/20），精确率为83.33%（10/12），受试者工作特征曲线下面积为0.919。结论基于贝叶斯网络构建的发病率预测模型对葫芦岛市HFRS的预测准确率较高，对HFRS的防控有一定的参考价值。

关键词： 贝叶斯网络; 肾综合征出血热; 发病率; 预测

本文引用格式

李皓晨, 齐滢滢, 张翀, 韩文菊, 沈铁峰, 李德强, 关鹏, 黄德生 . 基于贝叶斯网络的肾综合征出血热发病率预测模型研究[J]. 中国媒介生物学及控制杂志, 2021 , 32(4) : 475 -480 . DOI: 10.11853/j.issn.1003.8280.2021.04.019

Abstract

Objective To study the influencing factors for hemorrhagic fever with renal syndrome (HFRS) in Huludao, Liaoning province, China and to construct an incidence prediction model using a Bayesian network. Methods Data about incidence, host, and meteorological conditions of HFRS were collected at surveillance sites in Huludao from January 2008 to October 2018. The tabu search algorithm was used to learn the structure of the Bayesian network, and maximum likelihood estimation was applied to estimate Bayesian network parameters. Results At the 0.01 level, factors associated with the incidence of HFRS in Huludao included: rodent density; the average wind speed and sunshine hours in the contemporaneous month; the average maximum temperature, relative humidity, and normalized difference vegetation index with a one-month lag; and the average temperature, average minimum temperature, average atmospheric pressure, and precipitation with a two-months lag. The correlation coefficients were 0.691, 0.689, 0.345, -0.635, -0.631, -0.674, -0.714, -0.746, 0.650, and -0.643, respectively. When using meteorological and host data to predict the incidence of HFRS, the accuracy of the Bayesian network model was 85.00% (17/20), the precision was 83.33% (10/12), and the area under the receiver operating characteristic curve was 0.919. Conclusion The Bayesian network-based incidence prediction model shows a relatively high prediction accuracy for HFRS in Huludao, providing a certain reference for HFRS prevention and control.

Key words： Bayesian network; Hemorrhagic fever with renal syndrome; Incidence; Prediction

参考文献

[1] 张永振, 肖东楼, 王玉, 等. 中国肾综合征出血热流行趋势及其防制对策[J]. 中华流行病学杂志, 2004, 25(6):466-469. DOI:10.3760/j.issn:0254-6450.2004.06.002.Zhang YZ, Xiao DL, Wang Y, et al. The epidemic characteristics and preventive measures of hemorrhagic fever with syndromes in China[J]. Chin J Epidemiol, 2004, 25(6):466-469. DOI:10.3760/j.issn:0254-6450.2004.06.002.
[2] Kariwa H, Yoshimatsu K, Arikawa J. Hantavirus infection in East Asia[J]. Comp Immunol Microbiol Infect Dis, 2007, 30(5/6):341-356. DOI:10.1016/j.cimid.2007.05.011.
[3] Sun L, Zou LX. Spatiotemporal analysis and forecasting model of hemorrhagic fever with renal syndrome in mainland China[J]. Epidemiol Infect, 2018, 146(13):1680-1688. DOI:10.1017/S0950268818002030.
[4] 孙英伟, 韩仰欢, 李鑫, 等. 辽宁省2007－2011年肾综合征出血热疫情监测分析[J]. 中国公共卫生, 2012, 28(6):838-840. DOI:10.11847/zgggws-2012-28-06-46.Sun YW, Han YH, Li X, et al. Prevalence of hemorrhagic fever with renal syndrome in Liaoning province, 2007-2011[J]. Chin J Public Health, 2012, 28(6):838-840. DOI:10.11847/zgggws-2012-28-06-46.
[5] 王磊, 刘起勇. 应用贝叶斯网络推理研究中国肾病综合征出血热的传播机制[J]. 国外医学医学地理分册, 2010, 31(4):216-220. DOI:10.3969/j.issn.1001-8883.2010.04.003.Wang L, Liu QY. Bayesian network inference based research on transmission mechanism of hemorrhagic fever with renal syndrome in China[J]. Foreign Med Sci Sect Medgeography, 2010, 31(4):216-220. DOI:10.3969/j.issn.1001-8883.2010.04.003.
[6] 沈铁峰, 黄德生, 吴伟, 等. Bayes判别分析在肾综合征出血热发病预测研究中的应用[J]. 中国媒介生物学及控制杂志, 2009, 20(2):147-150.Shen TF, Huang DS, Wu W, et al. Application of Bayesian discriminant analysis in forecasting hemorrhagic fever with renal syndrome[J]. Chin J Vector Biol Control, 2009, 20(2):147-150.
[7] 吴伟, 郭军巧, 关鹏, 等. 辽宁省2005－2007年肾综合征出血热流行特征及环境危险因素分析[J]. 中国媒介生物学及控制杂志, 2014, 25(1):39-42. DOI:10.11853/j.issn.1003.4692.2014.01.011.Wu W, Guo JQ, Guan P, et al. Analysis of epidemiological features of hemorrhagic fever with renal syndrome and associated environmental risk factors in Liaoning province, China during 2005-2007[J]. Chin J Vector Biol Control, 2014, 25(1):39-42. DOI:10.11853/j.issn.1003.4692.2014.01.011.
[8] 许勤勤, 李润滋, 罗成, 等. 潍坊市气象因素对肾综合征出血热发病影响研究[J]. 环境与健康杂志, 2018, 35(2):149-153. DOI:10.16241/j.cnki.1001-5914.2018.02.013.Xu QQ, Li RZ, Luo C, et al. Relationship between meteorological factors and hemorrhagic fever with renal syndrome in Weifang[J]. J Environ Health, 2018, 35(2):149-153. DOI:10.16241/j.cnki.1001-5914.2018.02.013.
[9] 王智宇, 刘如春, 陈田木. 气候因素对长沙市肾综合征出血热发病影响研究[J]. 中国热带医学, 2015, 15(8):955-957, 965. DOI:10.13604/j.cnki.46-1064/r.2015.08.13.Wang ZY, Liu RC, Chen TM. Influence of climatic factors on hemorrhagic fever with renal syndrome in Changsha[J]. China Trop Med, 2015, 15(8):955-957, 965. DOI:10.13604/j.cnki. 46-1064/r.2015.08.13.
[10] He JY, Wang Y, Mu D, et al. The impacts of climatic factors and vegetation on hemorrhagic fever with renal syndrome transmission in China:a study of 109 counties[J]. Int J Environ Res Public Health, 2019, 16(18):3434. DOI:10.3390/ijerph16183434.
[11] Wei YH, Wang Y, Li XN, et al. Meteorological factors and risk of hemorrhagic fever with renal syndrome in Guangzhou, southern China, 2006-2015[J]. PLoS Negl Trop Dis, 2018, 12(6):e0006604. DOI:10.1371/journal.pntd.0006604.
[12] 张清敏, 禹长兰, 于世成, 等. 气象因素对山东省安丘市肾综合征出血热发病的影响[J]. 中国媒介生物学及控制杂志, 2017, 28(1):85-86, 89. DOI:10.11853/j.issn.1003.8280.2017.01.025.Zhang QM, Yu CL, Yu SC, et al. Influence of meteorological factors on hemorrhagic fever with renal syndrome in Anqiu city, Shandong province[J]. Chin J Vector Biol Control, 2017, 28(1):85-86, 89. DOI:10.11853/j.issn.1003.8280.2017.01.025.
[13] He JY, Christakos G, Wu JP, et al. Spatiotemporal variation of the association between climate dynamics and HFRS outbreaks in Eastern China during 2005-2016 and its geographic determinants[J]. PLoS Negl Trop Dis, 2018, 12(6):e0006554. DOI:10.1371/journal.pntd.0006554.
[14] Li SJ, Ren HY, Hu WS, et al. Spatiotemporal heterogeneity analysis of hemorrhagic fever with renal syndrome in China using geographically weighted regression models[J]. Int J Environ Res Public Health, 2014, 11(12):12129-12147. DOI:10.3390/ijerph111212129.
[15] Xiao H, Tong X, Gao LD, et al. Spatial heterogeneity of hemorrhagic fever with renal syndrome is driven by environmental factors and rodent community composition[J]. PLoS Negl Trop Dis, 2018, 12(10):e0006881. DOI:10.1371/journal.pntd.0006881.
[16] 胡春玲. 贝叶斯网络研究综述[J]. 合肥学院学报(自然科学版), 2013, 23(1):33-40.Hu CL. Research overview on Bayesian network[J]. J Hefei Univ(Nat Sci), 2013, 23(1):33-40.
[17] 黄影平. 贝叶斯网络发展及其应用综述[J]. 北京理工大学学报, 2013, 33(12):1211-1219. DOI:10.3969/j.issn.1001-0645.2013.12.001.Huang YP. Survey on Bayesian network development and application[J]. J Beijing Inst Technol, 2013, 33(12):1211-1219. DOI:10.3969/j.issn.1001-0645.2013.12.001.
[18] Lau CL, Smith CS. Bayesian networks in infectious disease eco-epidemiology[J]. Rev Environ Health, 2016, 31(1):173-177. DOI:10.1515/reveh-2015-0052.
[19] Badawi A, Di Giuseppe G, Gupta A, et al. Bayesian network modelling study to identify factors influencing the risk of cardiovascular disease in Canadian adults with hepatitis C virus infection[J]. BMJ Open, 2020, 10(5):e035867. DOI:10.1136/bmjopen-2019-035867.
[20] 李硕豪, 张军. 贝叶斯网络结构学习综述[J]. 计算机应用研究, 2015, 32(3):641-646. DOI:10.3969/j.issn.1001-3695.2015.03.001.Li SH, Zhang J. Review of Bayesian networks structure learning[J]. Appl Res Comput, 2015, 32(3):641-646. DOI:10.3969/j.issn.1001-3695.2015.03.001.
[21] 何德琳, 程勇. 贝叶斯网络评分准则对MMHC算法学习效果的影响[J]. 西南科技大学学报, 2008, 23(2):56-61. DOI:10.3969/j.issn.1671-8755.2008.02.013.He DL, Cheng Y. Research of the effect of Bayesian score metric on MMHC learning algorithm[J]. J Southwest Univ Sci Technol, 2008, 23(2):56-61. DOI:10.3969/j.issn.1671-8755.2008.02.013.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献