Comparison of the effects of Cox regression analysis model and decision tree model in identifying risk factors for the occurrence of hypertension in the elderly
10.3969/j.issn.1006-2483.2024.04.006
- VernacularTitle:Cox回归分析模型与决策树模型识别中老年高血压发病危险因素的效果比较
- Author:
Yaru LI
1
;
Nan WANG
1
;
Zhiwen GE
1
;
Zhengli SHI
1
;
Zhongxin HONG
1
Author Information
1. Beijing Friendship Hospital , Capital Medical University , Beijing 100050 , China
- Publication Type:Journal Article
- Keywords:
Hypertension;
Cox regression analysis model;
Decision tree model
- From:
Journal of Public Health and Preventive Medicine
2024;35(4):24-27
- CountryChina
- Language:Chinese
-
Abstract:
Objective To explore the risk factors for the occurrence of hypertension in middle-aged and elderly residents in China using the Cox regression analysis model and decision tree model, and compare the differences between the two methods. Methods The 2011-2015 China Health and Retirement Longitudinal Study data were used. The study investigated the risk factors for hypertension using both a multivariate Cox regression model and a decision tree model. Results The results showed that the incidence rate of hypertension between 2011-2015 was 22.79%. Both the Cox regression model and decision tree model identified age, education level, body mass index, and diabetes as risk factors for hypertension. The Cox regression model also identified drinking status as a risk factor, while the decision tree model identified gender and marital status as additional risk factors. The area under the curve (AUC) suggested that the Cox regression model and decision tree model had comparable ability to predict hypertension. Conclusions The risk factors for hypertension include gender, age, education level, marital status, alcohol consumption, body mass index, and history of diabetes. The effectiveness of the hypertension prediction model established based on Cox regression model and decision tree model results is not different.
