摘要
以高血压患者的患病因素为例进行解析,提出代谢综合症相关问题的解决方法.研究年龄、BMI、家族史、吸烟、饮酒、文化程度、职业等18个影响高血压疾病的因素.研究的主要目的是将这些因素对高血压患病影响的重要性程度进行排序,并建立相应患病概率的预测模型.这不仅对人们日常生活疾病的预防、监控有一定的指导意义,也给医疗保险中保单的核保提供了风险度量的判别依据.首先用相关性分析剔除与高血压患病相关性较小的因素,继而用主成分分析方法消除因素间的共线性,最后用Logistic回归拟合患病概率模型并根据系数进行排序和预测.结果显示,无论性别,对高血压疾病影响最大的首先是家族史,其次为年龄.
This paper analyses the cause of hypertension as an example,and then puts forward solutions to these problems of metabolic syndrome.Many factors lead to hypertension.This paper focuses on totally eighteen of them,namely age,BMI, family heredity,smoking,drinking,education,profession and etc.The primary objective of this paper is to rank these factors by the individual degree of their influence on hypertension and to establish the forecasting model of sick probability accordingly.Not only does it indicates the precaution and surveillance of diseases in human daily life,but also provides the criteria of the risk measurement for medical insurance.In this method,correlation analysis is used to kick off the factors of less importance,thus by the means of main composition analysis,linearity connection among factors is removed,and finally this paper imitates the sick probability model by logistic regression and ranks the factors by the coefficients.The conclusion is that,in both male and female cases,the family heredity is the most significant factor of hypertension,while age is of the second importance.
出处
《应用数学与计算数学学报》
2011年第1期90-98,共9页
Communication on Applied Mathematics and Computation
基金
上海市重点学科建设资助项目(S30106)
