冠心病患者经皮冠状动脉介入术后抑郁预测模型的建立及效能分析

Establishment of a predictive model of post-percutaneous coronary intervention depression in patients with coronary heart disease and its effect analysis

目的筛选冠心病患者经皮冠状动脉介入术(PCI)后并发抑郁症的危险因素,构建冠心病患者PCI术后并发抑郁症的预测模型并分析其诊断效能.方法选取2015年4月至2019年1月在本院就诊并接受治疗的3048例冠心病患者作为研究对象.967例接受PCI治疗后并发抑郁症的患者为抑郁症组,按1∶1比例随机选择967例接受PCI治疗后未并发抑郁症的冠心病患者为冠心病组.采用单因素及多因素Logistic回归分析影响冠心病患者PCI术后并发抑郁症的危险因素,并构建冠心病患者PCI术后并发抑郁症的预测模型.采用ROC曲线分析冠心病患者PCI术后并发抑郁症的预测模型的诊断效能.结果3048例冠心病患者中有967例占31.73%的患者PCI术后并发抑郁症.2组患者在年龄、性别、D型性格、吸烟史、NYHA分级、支架植入数量、独居、急诊PCI、Gensini评分核受教育程度方面比较,差异有统计学意义(P<0.05).Logistic回归分析结果显示,冠心病患者年龄、D型性格、NYHA分级、独居核受教育程度是其PCI术后并发抑郁症的危险因素.冠心病患者PCI术后并发抑郁症模型的ROC曲线下面积为0.961(95%CI:0.910~0.987),敏感性核特异性分别为96.00%核90.82%.结论本研究构建的模型可以预测冠心病患者PCI术后并发抑郁症的风险,且效能较高.

Objective To screen the risk factors of depression in patients with coronary heart disease(CHD)after percutaneous coronary intervention(PCI),and to construct a predictive model of depression in patients with CHD after PCI and to analyze its diagnostic efficacy.Methods A total of 3048 patients with CHD who were treated in our hospital from April 2015 to January 2019 were selected as the study subjects.967 patients with depression after PCI were selected as depression group.967 patients without depression after PCI were randomly selected as CHD group according to 1:1 ratio.Univariate and multivariate logistic regression analysis were used to analyze the risk factors of depression in patients with CHD after PCI,and to construct a predictive model of depression in patients with CHD after PCI.The ROC curve was used to analyze the diagnostic efficacy of a predictive model of depression in patients with CHD after PCI.Results Of 3048 patients with CHD,967(31.73%)suffered from depression after PCI.There were significant differences in age,sex,type D personality,smoking history,NYHA classification,number of stents implanted,solitary living,emergency PCI,Gensini score and education level between the two groups(P<0.05).Logistic regression analysis showed that age,type D personality,NYHA grade,solitude and education were risk factors for depression after PCI.The area under ROC curve of depression model after PCI in CHD patients was 0.961(95%CI:0.910-0.987),the sensitivity and specificity were 96.00%and 90.82%respectively.Conclusion The model constructed in this study can predict the risk of depression in patients with CHD after PCI and is more effective.