Establishment and validation of a nomogram prediction model for cognitive impairment in patients with hypertension based on the CHARLS database
10.13406/j.cnki.cyxb.003917
- VernacularTitle:基于CHARLS数据构建高血压患者认知功能障碍风险预测列线图模型及验证
- Author:
Weiye YANG
1
;
Xiaofei GAO
;
Han XIAO
;
Yuqing WANG
Author Information
1. 重庆市中医院神经内科,重庆 400010
- Keywords:
hypertension;
cognitive impairment;
risk prediction model;
nomogram;
China Health and Retirement Longitudinal Study
- From:
Journal of Chongqing Medical University
2025;50(10):1329-1337
- CountryChina
- Language:Chinese
-
Abstract:
Objective:To establish a predictive model for the risk of cognitive impairment in patients with hypertension.Methods:Data were obtained from the China Health and Retirement Longitudinal Study(CHARLS),and 17 indicators were analyzed,including demographic features,behavioral factors,and health status.The study cohort was randomly divided into a training set(n=2 918)and an internal validation set(n=1 249)at a ratio of 7∶3,and 1 457 patients with hypertension who were treated in Chongqing Traditional Chinese Medicine Hospital from January to December 2024 were included as an external validation set.The least absolute shrinkage and selection operator regression analysis was used to identify predictive variables,and 10-fold cross-validation was used to determine the optimal model.A logistic regression model was used to investigate the risk factors for cognitive impairment in patients with hypertension,and then a nomogram prediction model was established.The calibration curve was used to assess the accuracy of the model,and the area under the ROC curve(AUC)and the decision curve analysis were used to assess the predictive performance of the model.Results:A total of 4167 hypertensive patients aged≥45 years were included from the CHARLS database,among whom 668 had cognitive impairment.The multivariate logistic regression analysis showed that age(odds ratio[OR]=1.408,95%CI=1.040-1.056),sex(OR=0.570,95%CI=0.492-0.660),body mass index(OR=0.931,95%CI=0.914-0.948),educational level(OR=0.235,95%CI=0.200-0.277),place of residence(OR=1.674,95%CI=1.447-1.936),physi-cal activity(OR=0.459,95%CI=0.373-0.562),depression(OR=1.386,95%CI=1.198-1.604),and total cholesterol level(OR=0.997,95%CI=0.995-0.999)were predictive variables.The ROC curve analysis showed that the nomogram model had good performance,with an AUC of 0.814(95%CI=0.802-0.826)in the training set,0.817(95%CI=0.788-0.846)in the internal validation set,and 0.725(95%CI=0.699-0.752)in the external validation set.Conclusion:The nomogram model developed in this study can effectively predict the risk of cognitive impairment in Chinese patients with hyperten-sion and has a good application value.
