Construction and evaluation of a predictive model for post-stroke cognitive impairment
10.3969/j.issn.1671-8348.2025.05.027
- VernacularTitle:缺血性卒中后认知功能障碍预测模型的构建与评价
- Author:
Yuhui ZHAO
1
;
Tingting YIN
;
Guanglei FU
Author Information
1. 暨南大学护理学院,广州 510632;成都文理学院体育与大健康学院,成都 610499
- Keywords:
post stroke cognitive impairment;
ischemic stroke;
risk factors;
column chart;
predictive model
- From:
Chongqing Medicine
2025;54(5):1194-1200
- CountryChina
- Language:Chinese
-
Abstract:
Objective To construct and validate a predictive model of post-stroke cognitive impairment(PSCI)in ischemic stroke patients.Methods A total of 517 ischemic stroke patients admitted to the Depart-ment of Neurology of the hospital from January to December 2021 were selected by convenience sampling method,and were randomly divided into 359 cases of the modeling group and 158 cases of the validation group according to a 7∶3 ratio.In the modeling group,logistic regression analysis was used to screen risk factors for PSCI in the modeling group,and a column chart model was constructed.The performance of the column chart model was evaluated using receiver operating characteristic(ROC)curve and area under the curve(AUC),goodness of fit test Hosmer Lemeshow(H-L test),calibration curve,and clinical decision curve(DCA)in the validation group.Results The incidence of cognitive impairment after ischemic stroke in the modeling group was 63.8％(229/359).The AUC value in the column chart model was 0.836,and the H-L test result was x2=7.254,P=0.510.The calibration curve was close to the ideal curve at 45°.DCA was higher than the reference line,and homocysteine,age,NIHSS score,and educational level were the main predictive factors.Conclusion Con-structing a predictive model for post-stroke cognitive impairment in patients with ischemic stroke has good predictive value.
