基于HITON-PC算法的医院病案首页数据挖掘  

Data Mining in Hospital Medical Record Data Based on the HITON-PC Algorithm

作　　者：易三莉[1] 杨静[1] 姚旭升 谢颖夫[2] 贺建峰[1] YI San-li;YANG Jing;YAO Xu-sheng;XIE Ying-fu;HE Jian-feng(School of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,China;The First People’s Hospital of Yunnan Province,Kunming 650032,China)

机构地区：[1]昆明理工大学信息工程与自动化学院,昆明650500 [2]云南省第一人民医院,昆明650032

出　　处：《软件导刊》2018年第4期188-190,共3页Software Guide

基　　金：国家自然科学基金项目(11265007)

摘　　要：使用HITON-PC算法分析某甲级医院2015年住院首案中记录的非胰岛素依赖型糖尿病及其它协同疾病之间是否存在因果性。HITON-PC算法是一种运用条件独立性检验处理高维数据的因果分析算法,将其应用于医学数据挖掘中,能高效得出变量之间的因果关系。非胰岛素依赖型糖尿病与冠状动脉粥样硬化、高血脂、高血压、高血压II期和高血压III期之间有着因果关系。通过因果关系分析,可以很好地从大量临床数据中发现疾病间的潜在因果性,为相关疾病的临床诊断提供辅助,具有很强的实用性。HITON-PC is an algorithm of causal analysis,and it is used to analyze the causal relationship between non-insulin dependent diabetes mellitus(NIDDM)and its cooperative diseases in the medical record data;it is also an algorithm of causal analysis which conducts high-dimensional data employed conditional independence test.HITON-PC is applied in medical data mining and it can effectively determine the causality between variables in medical data mining.There are a lot of causal relationships among NIDDM,hyperlipidemia and hypertension.Causality analysis is a good way to detect the potential causality between diseases from a large amount of clinical data.It can provide an auxiliary method for the clinical diagnosis of related diseases and plays a practical role in medical data mining.

关 键 词：数据挖掘 HITON-PC 因果关系 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]