医学信息2025，Vol.38Issue(22)：18-25,8.DOI:10.3969/j.issn.1006-1959.2025.22.003
基于NHANES数据库的卒中后抑郁风险预测模型的构建
Construction of a Risk Prediction Model for Post-stroke Depression Based on the NHANES Database
摘要
Abstract
Objective To conduct a comprehensive analysis of the influencing factors for post-stroke depression(PSD)and construct a PSD risk prediction model and nomogram,taking into account the factor of physical function limitations after stroke.Methods Survey data of 10 years were selected from the National Health and Nutrition Examination Survey(NHANES)database from 2007 to 2016,and were divided into a training set and a testing set at a ratio of 7∶3.A total of 18 influencing factors,including physical function limitations,were included.Multivariate Logistic regression analysis was used to analyze their independent effects on PSD,and a PSD risk prediction model and a nomogram were constructed.Results A total of 360 subjects were included,in which 69 had PSD.Multivariate logistic regression analysis found that gender[OR(95%CI)=2.22(1.05,4.89)],general[OR(95%CI)=0.31(0.11,0.81)]or good[OR(95%CI)=0.27(0.06,0.88)]economic status,smoking[OR(95%CI)=2.87(1.27,6.99)],sleep disorders[OR(95%CI)=3.82(1.84,8.25)],and ADL limitations[OR(95%CI)=3.09(1.49,6.53)]had statistically significant independent associations with PSD.Based on these five factors,a PSD risk prediction model and nomogram were constructed.The ROC curve AUC values on the training set and test set were 0.824(95%CI=0.761-0.886)and 0.706(95%CI=0.602-0.809),respectively.The calibration curve was highly consistent with the ideal curve,and the DCA curve was above the invalid line within the range of 0.1-0.6 on the horizontal axis.Conclusion Female gender,general and good economic status,smoking,sleep disorders,and limited ADL are associated with PSD.The constructed model has good performance and can be used for PSD risk prediction.关键词
NHANES/卒中后抑郁/预测模型/ADLKey words
NHANES/Post-stroke depression/Prediction model/ADL分类
医药卫生引用本文复制引用
陈晓帆,李蓓,刘菲,谢山..基于NHANES数据库的卒中后抑郁风险预测模型的构建[J].医学信息,2025,38(22):18-25,8.基金项目
中南大学研究生创新项目(自主探索类)(编号:512340012) （自主探索类）
