基于数据挖掘的齐市地区脑卒中危险因素分层的研究

Stratified study of risking factors affecting stroke in Qiqihar based on data mining

主要对齐齐哈尔地区脑卒中危险因素进行分层研究。采用的方法是数据挖掘的方法。首先对第一医院门诊就医诊疗的患者进行问卷调查和有关数据的测评,筛查出脑卒中高危人群,并对高危人群进行血脂、血糖、颈动脉彩超等检查。得到初筛信息表等原始数据表。然后对数据进行处理,找到相关研究属性。再通过SQLServer2008数据挖掘工具建立了数据源和数据源视图,选择决策树的挖掘方法,得到数据挖掘模型。通过挖掘模型把脑卒中危险因素按重要程度分层。分为最主要因素,次主要因素和相关因素。再根据录入的测试数据,进行决策患脑卒中的危险分级。通过实验验证了所建立的决策系统可靠性和可行性。决策系统对于实现脑卒中人群预防和个体保健起到重要的作用。

In this paper,the risk factors of stroke in Qiqihar were stratified.The method adopted is data mining.First of all,questionnaire survey and evaluation of relevant data were conducted on the patients in the outpatient department of the first hospital for medical treatment to screen out the high-risk groups of stroke,and blood lipid,blood glucose and carotid artery color doppler ultrasound examination were conducted on the high-risk groups.The original data table was obtained.Then the data were processed to find relevant research properties.Then the data source and data source view are established through the SQL Server 2008 data mining tool,and the mining method of decision tree is selected to obtain the data mining model.Stroke risk factors were stratified according to importance by mining model.It is divided into the most important factors,the secondary major factors and related factors.According to the test data,the risk classification of stroke was determined.The reliability and feasibility of the decision system are verified by experiments.The decision-making system plays an important role in the prevention of stroke and individual health care.