摘要
基于大量实测数据 ,将数据挖掘C4.5算法引入 2型糖尿病的数据处理之中 ,建立了多条有效规则 ,通过测试其患病与未患病的平均正确识别率达 97%。重要的是建立的这些规则同医学上的认识基本一致 ,可以说这些规则的建立为解释糖尿病发病因素之间的相互关系以及影响程度提供了一种新的方法 ,为建立
A kind of data mining algorithm C4.5 has been used in the processing of the type 2 diabetes concrete data,and some rules are established.From the testing results,the average rate of the correct recognition of the healthy person and the diabetic patient is 97%.In particular,these rules are corresponded with the knowledge of the physic.A new method has been provided in this paper to explain the relationship and the influences of the type 2 diabetes disease factors.It is one of the research elements of the type 2 diabetes.
出处
《计算机应用研究》
CSCD
北大核心
2004年第7期174-176,179,共4页
Application Research of Computers
基金
国家"十五"攻关项目资助 (2 0 0 1BA70 2B0 1)
