老年房颤患者认知衰弱预测模型的构建与验证  

Construction and Validation of Prediction Model for Cognitive Frailty in Elderly Patients with Atrial Fibrillation

作　　者：邢雨涵 张月[2] 姚志萍[3] 许方蕾[2] XING Yuhan;ZHANG Yue;YAO Zhiping;XU Fanglei(Medical College of Tongji University,Shanghai 200331,China;Department of Nursing,Tongji Hospital Affiliated to Tongji University,Shanghai 200065,China;Department of Cardiology,Tongji Hospital Affiliated to Tongji University)

机构地区：[1]同济大学医学院,上海200331 [2]同济大学附属同济医院护理部,上海200065 [3]同济大学附属同济医院心内科

出　　处：《军事护理》2024年第7期38-42,共5页MILITARY NURSING

基　　金：上海市卫生健康委员会研究课题(202240365);上海市残疾人联合会康复项政策研究专项(2022ZC1017)。

摘　　要：目的 构建老年心房颤动患者认知衰弱预测模型并验证该模型预测性能,以期为护理人员提供风险筛查工具。方法 采用便利抽样法选取2022年10月至2023年4月就诊于上海市某三级甲等医院的老年房颤患者为研究对象,将数据按7∶3随机划分为训练集(293例)和验证集(126例),采用Logistic回归法分析老年房颤患者认知衰弱的影响因素,构建风险预测模型并根据受试者工作特征曲线(receiver operating characteristic, ROC)下面积(area under curve, AUC)及校准曲线检验模型预测效果。结果 Logistic回归分析显示,年龄、文化程度、饮酒情况、多重用药、跌倒史以及健康素养水平是老年房颤患者发生认知衰弱的影响因素(均P<0.05)。训练集AUC为0.848,灵敏度0.848,特异度0.727。验证集AUC为0.793,灵敏度0.774,特异度0.747。结论 本研究构建的风险预测模型区分度和准确度良好,能够有效预测老年房颤患者认知衰弱的发生风险,为临床尽早识别认知衰弱患者提供理论依据。Objective To establish a predictive model of cognitive frailty in elderly patients with atrial fibrillation and validate the predictive performance of the model,aiming to provide a risk screening tool for nursing staff.Methods The convenience sampling method was used to select elderly patients with atrial fibrillation who visited a tertiary A Hospital in Shanghai from October 2022 to April 2023 as the study subjects.The data were randomly divided into a training set(293 cases)and a validation set(126 cases)at the ratio of 7:3.Logistic regression method was used to analyze the influencing factors of cognitive frailty in elderly patients with atrial fibrillation to establish a risk prediction model.The prediction performance of the model was tested by the area under the curve of the receiver operating and calibration curve.Results Logistic regression analysis showed that age,education level,drinking status,polypharmacy,history of falls,and health literacy level were associated with cognitive frailty in elderly patients with atrial fibrillation(all P<0.05).The area under the ROC curve for the training set was 0.848,with a sensitivity of 0.848,a specificity of 0.727.The area under the ROC curve for the validation set was 0.793,with a sensitivity of 0.774,a specificity of 0.747.Conclusions The risk prediction model constructed in this study has good discrimination and accuracy,and can effectively predict the risk of cognitive frailty in patients with atrial fibrillation,providing a theoretical basis for early clinical identification of patients with cognitive frailty.

关 键 词：心房颤动 认知衰弱 预测模型 老年 

分 类 号：R473.59[医药卫生—护理学]