摘要
目的:探讨睡眠障碍病人发生心力衰竭的危险因素,建立并评估心力衰竭的列线图模型。方法:从国家健康和营养检查调查中检索2008—2020年的睡眠障碍病人,并以3∶1的比例分为训练集和验证集。利用LASSO回归筛选建立模型的显著变量。模型通过一致性指数(C指数)、校准图、受试者工作特征(ROC)曲线和决策曲线分析(DCA)评估准确度和区分度。结果:共纳入1062例睡眠障碍病人。根据筛选出的危险因素(冠心病、高血压史及血糖、总胆固醇、尿酸和肌酐等生化指标)构建心力衰竭的列线图。训练集的C指数为0.830,95%CI[0.799,0.873],外部验证的C指数为0.746,95%CI[0.709,0.854]。校准图的结果显示模型有较好的准确度,绝对误差约为0.05。决策曲线分析显示,该模型对心力衰竭病人有诊断意义。结论:预测模型可识别患有睡眠障碍的心力衰竭病人。
Objective:To explore the risk factors of heart failure in patients with sleep disorders,establishing and evaluating a Nomogram model of heart failure.Methods:Patients with sleep disorders from 2008-2020 were retrieved through the National Health and Nutrition Examination Survey,and they were divided into to training set and validation set at a ratio of 3∶1.The significant variables for establishing the model were screened using LASSO regression.The model evaluation accuracy and discrimination were assessed using consistency index(C-index),calibration plot,receiver operating characteristic(ROC)curve and decision curve analysis(DCA).Results:A total of 1062 patients with sleep disorders were included.A Nomogram of heart failure was constructed based on the screened risk factors(coronary heart disease,history of hypertension,and biochemical indicators such as blood glucose,total cholesterol,uric acid and creatinine).The C-index of the training set was 0.830,95%CI 0.799-0.873,and the C-index of external validation was 0.746,95%CI 0.709-0.854.The results of calibration plot suggested that the model showed good accuracy,with an absolute error of approximately 0.05.Decision curve analysis indicated that this model held diagnostic value for patients with heart failure.Conclusion:The predictive Nomogram model could identify heart failure patients with sleep disorders.
作者
温伟
赤艺
谢蓓莉
李浩浩
刘明旺
赵福海
WEN Wei;CHI Yi;XIE Beili;LI Haohao;LIU Mingwang;ZHAO Fuhai(Xiyuan Hospital,China Academy of Chinese Medical Sciences,Beijing 100091,China;Heilongjiang University of Chinese Medicine)
出处
《中西医结合心脑血管病杂志》
2025年第22期3390-3396,共7页
Chinese Journal of Integrative Medicine on Cardio-Cerebrovascular Disease
基金
中国中医科学院科技创新工程项目(No.C12021A00901)。
关键词
心力衰竭
睡眠障碍
危险因素
预测模型
决策曲线分析
heart failure
sleep disorders
risk factors
predictive model
decision curve analysis
