基于支持向量机的浙江省流感样病例预警模型研究

目的:建立浙江省流感样病例预警模型,为流感疫情的早期发现提供科学依据。方法:收集整理2012年1月2日至2013年12月29日期间104周浙江省11家哨点医院门急诊中流感相关疾病病例数、各类气象因素以及流感病原阳性率,与同期流感样病例数作相关分析,寻找出流感样病例发生的相关因素。通过交叉检验选取最优参数,采用支持向量机方法建立流感样病例预警模型,并利用历史数据对模型进行验证。结果:相关性分析显示有8个因素与流感样病例相关。模型的最优参数为:C=3,s=0.009,y=0.4,验证结果显示流感样病例预警模型的同级预报正确率为50.0%,相差一级的预报正确率为96.7%。结论:支持向量机方法适用于...

Full description

Saved in:
Bibliographic Details
Published in浙江大学学报(医学版) Vol. 44; no. 6; pp. 653 - 658
Main Author 卢汉体 李傅冬 林君芬 何凡 沈毅
Format Journal Article
LanguageChinese
Published 浙江大学公共卫生学院流行病与卫生统计学系,浙江杭州,310058%浙江省疾病预防控制中心,浙江杭州,310051 2015
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:目的:建立浙江省流感样病例预警模型,为流感疫情的早期发现提供科学依据。方法:收集整理2012年1月2日至2013年12月29日期间104周浙江省11家哨点医院门急诊中流感相关疾病病例数、各类气象因素以及流感病原阳性率,与同期流感样病例数作相关分析,寻找出流感样病例发生的相关因素。通过交叉检验选取最优参数,采用支持向量机方法建立流感样病例预警模型,并利用历史数据对模型进行验证。结果:相关性分析显示有8个因素与流感样病例相关。模型的最优参数为:C=3,s=0.009,y=0.4,验证结果显示流感样病例预警模型的同级预报正确率为50.0%,相差一级的预报正确率为96.7%。结论:支持向量机方法适用于流感样病例的预警。
Bibliography:LU Han-ti, LI Fu-dong, LIN Jun-fen, HE Fan, SHEN Yi (1. Department of Epidemiology and Biostatistics, Zhejiang University School of Public Health, Hangzhou 310058, China ; 2. The Center for Disease Control and Prevention of Zhejiang Province, Hangzhou 310051, China)
33-1248/R
Influenza, human/epidemiology ; Artificial intelligence ; Models, statistical ; Forecasting/methods
Objective: To construct a forecasting model of influenza-like illness in Zhejiang Province. Methods: The number of influenza-like cases and related pathogens among outpatients and emergency patients were obtained from 11 sentinel hospitals in Zhejiang Province during 2012 to 2013 (total 104 weeks ), and corresponding meteorological factors were also collected. The epidemiological characteristics of influenza during the period were then analyzed. Linear correlation and rank correlation analyses were conducted to explore the association between influenza-like illness and related factors. Optimal parameters were selected by cross validation. Sup
ISSN:1008-9292
DOI:10.3785/j.issn.1008-9292.2015.11.09