关联规则及其在细菌性痢疾风险预测中的应用  

ASSOCIATION RULES AND ITS APPLICATION IN RISK PREDICTION OF BACILLARY DYSENTERY

作　　者：关鹏[1] 曲波 何苗[3] 黄德生[4] 周宝森[1] 

机构地区：[1]中国医科大学公共卫生学院流行病学教研室,沈阳110001 [2]中国卫生统计编辑部 [3]中国医科大学附属第一医院计算机室 [4]中国医科大学基础医学院数学教研室

出　　处：《现代预防医学》2007年第11期2007-2008,共2页Modern Preventive Medicine

基　　金：国家自然科学基金资助项目(70503028)

摘　　要：[目的]进行细菌性痢疾疫情风险数据挖掘并形成关联规则。[方法]传染病疫情资料来源于辽宁省朝阳市疾病预防控制中心,收集1981￣1994年的伤寒副伤寒、斑疹伤寒、甲型肝炎、乙型肝炎、细菌性痢疾、流行性脑脊髓膜炎、百日咳、猩红热和流行性乙型脑炎等法定传染病发病率数据。气象资料由该市气象站提供,内容包括各年相应的13项月气象指标。首先将气象指标和传染病数据离散化为计数资料,分为高、中、低3个水平,由此将源数据库映射为挖掘数据库;设置最小支持度为0.15,最小置信度为0.9,利用Apriori算法进行关联规则挖掘。[结果]共形成70个强关联规则,这些强关联规则中蕴含着细菌性痢疾与季节、气温、气压、降水量、蒸发量等影响因素之间的关联关系。[结论]本方法有利于将抽象的数理统计理论转变为实用的关联规则来指导疾病预防控制实践。[Objective] To detect the potential factors which may cause the outbreaks of intectious diseases and estimate their risk and tendency, and thus provide theoretical and technical support for public health administrators. [Methods] Meteo- rological data and infectious disease surveillance data were collected, several pre-processing techniques were explotted, database for mining was constructed by mapping from source data to spreadsheet format file, and then, the method of Apriori algorithm was applied to find all the strong association rules by setting support as 0.15 and confidence as 0.9. [ Results] These associations revealed the relation between risk of Bacillary Dysentery and the influencing factors such as season, air pressure, temperature, precipitation and amount of evaporation. [ Conclusion] The association rules method is proved to be useful in decision-making for infectious disease control.

关 键 词：细菌性痢疾 风险 数据挖掘 关联规则 

分 类 号：R730.1[医药卫生—肿瘤]