论文部分内容阅读
目的应用分类树模型与Logistic回归模型分析郑州市儿童青少年血压的影响因素,为青少年高血压早期干预提供依据。方法对2010年郑州市7~17岁学生4 400人体质调研数据进行分析,运用分类树模型及Logistic回归对儿童高血压影响因素进行探讨,建立预测模型并运用ROC曲线比较2种模型优劣。结果郑州市儿童高血压患病率较低,为6.5%,男女血压偏高发生率分别为12.4%,15.9%,差异无统计学意义(χ2=0.74,P>0.05);肥胖与超重儿童高血压发生率大于正常儿童,差异有统计学意义(χ2=16.14,P<0.05);Logistic回归显示超重肥胖与血压关系密切,超重青少年患高血压风险是正常体重的2.118倍(OR=2.118,95%CI=1.492~3.007),肥胖青少年患高血压的风险为正常体重的6.933倍(OR=6.933,95%CI=5.183~9.273);分类树模型和Logistic回归均显示超重、肥胖是儿童高血压主要影响因素。结论分类树模型对儿童高血压预测效果较好,可作为Logistic回归模型的补充。
Objective To analyze the influencing factors of blood pressure among children and adolescents in Zhengzhou city by using the classification tree model and Logistic regression model to provide the basis for early intervention of hypertension in adolescents. Methods The data of physical fitness of 4 400 people from 7 to 17 years old in Zhengzhou in 2010 were analyzed. Classification tree model and Logistic regression were used to investigate the influencing factors of hypertension in children. The prediction model was established and the ROC curves were used to compare the advantages and disadvantages of the two models. Results The prevalence of hypertension was 6.5% in Zhengzhou. The prevalence of hypertension in both sexes was 12.4% and 15.9% respectively, with no significant difference (χ2 = 0.74, P> 0.05). The obesity and overweight children Logistic regression showed that the risk of overweight and obesity was closely related to blood pressure. The risk of hypertension in overweight teenagers was 2.118 times of that of normal children (OR = 2.118, 95%, P <0.05) % CI = 1.492-3.007). The risk of hypertension in obese adolescents was 6.933 times of normal body weight (OR = 6.933, 95% CI = 5.183-9.273). Both classification tree model and Logistic regression showed that overweight and obesity were the risk factors of hypertension the main factor of influence. Conclusion Classification tree model has good predictive value for hypertension in children and can be used as a supplement to Logistic regression model.