中青年脑卒中病人社交回避风险预测模型的构建与验证

打开文本图片集

Construction and verification of social avoidance risk prediction model in young and middle⁃aged stroke patients

ZHAO Hangchi， ZHANG Lei*， SUN Feiyang， REN Shengnan， ZHANG Yuwei

School of Nursing， Jinzhou Medical University， Liaoning 121000  China

*Corresponding Author  ZHANG Lei， E⁃mail： zhangl1@jzmu.edu.cn

Abstract  Objective：To construct and verify the social avoidance risk prediction model of young and middle⁃aged stroke patients， so as to provide reference for reducing the social avoidance of patients.Methods：A total of 392 young and middle⁃aged stroke patients from 2 tertiary grade A hospitals in Jinzhou were selected.Neurological function， sleep， ability of activities of daily living， mental toughness， perceived social support，perceived social support and social avoidance were measured.Through univariate analysis and multivariate LASSO regression analysis， the risk factors of patients' social avoidance were discussed， and the risk prediction model was established.The calibration plot and the area under the receiver operating characteristic （ROC） curve were used to evaluate the prediction efficiency of the model.Results：The detection rate of social avoidance in young and middle⁃aged stroke patients in modeling group was 40.56%.LASSO regression results showed that stroke location，neurological impairment，sleep，activities of daily living，psychological resilience and perceived social support were the influencing factors of social avoidance.The Nomogram prediction model based on the above 6 independent influencing factors had good discrimination and reliability.The area under the receiver operating characteristic （ROC） curve was 0.839 in internal verification and 0.829 in external verification.Conclusion：The incidence of social avoidance in young and middle⁃aged stroke patients is high， and the constructed prediction model is helpful to effectively predict the risk of early social avoidance in patients.

Keywords    stroke； young and middle⁃aged； social avoidance； influencing factors； prediction model

摘要  目的：构建和验证中青年脑卒中病人社交回避风险预测模型，为减少病人社交回避提供参考。（剩余12542字）