摘要
目的:探究影响老年脑卒中病人肌少症的因素,构建风险预测模型,并评估其预测准确性。方法:于2022年9月—2023年4月选取辽宁省某三级甲等医院神经内科的489例老年脑卒中病人为研究对象。依据Logistic回归分析结果构建肌少症风险预测模型,绘制列线图和决策树,并根据受试者工作特征曲线下面积(AUC)和混淆矩阵对模型的预测效能进行评价。结果:老年脑卒中病人肌少症发生率为37.6%。Logistic回归分析结果显示,年龄、吸烟、日常生活自理能力(ADL)、跌倒风险、营养状态和运动习惯是老年脑卒中病人肌少症发生的影响因素(P<0.05);决策树模型结果显示,年龄、ADL、吸烟、运动习惯、营养状态是病人发生肌少症的决策因素。Logistic回归模型的AUC为0.959,决策树模型训练集和测试集的AUC分别为0.892和0.826。结论:本研究构建的Logistic回归模型和决策树模型预测效能均良好,有利于临床医护人员对肌少症高危人群进行筛查。
Objective:To explore the factors affecting sarcopenia in senile patients with stroke,construct risk prediction models,and evaluate their accuracy of prediction.Methods:A total of 489 senile patients with stroke from neurology department of a tertiary grade A hospital in Liaoning province were selected as the research subjects from September 2022 to April 2023.The risk prediction models of sarcopenia were constructed according to the results of Logistic regression analysis.The Nomogram and decision tree were painted,and the prediction efficiency of models were evaluated according to area under the curve(AUC)of receiver operator characteristic and confusion matrix.Results:The incidence of sarcopenia in senile patients with stroke was 37.6%.The results of logistic regression analysis show that smoking,age,activity of daily living(ADL),fall risk,nutrition and exercise habits were effect factors for sarcopenia in senile patients with stroke(P<0.05).The results of decision tree model showed that smoking,age,ADL,nutrition and exercise habits were decision-making factors for the sarcopenia in senile patients with stroke.The AUC of Logistic regression model was 0.959,and that of decision tree model training set and test set were 0.892 and 0.826,respectively.Conclusions:The Logistic regression model and decision tree model construct in this study have good predictive performance,which is helpful for clinical medical staff to screen the high-risk group of sarcopenia.
作者
孔令慧
于杰
张会君
陈萍
KONG Linghui;YU Jie;ZHANG Huijun;CHEN Ping(Jinzhou Medical University,Liaoning 121001 China)
出处
《护理研究》
北大核心
2024年第10期1703-1710,共8页
Chinese Nursing Research
基金
2021年度辽宁省社会科学规划基金项目,编号:L21BGL023。
