系统性红斑狼疮患者糖皮质激素维持治疗抑郁风险预测模型的构建

Construction of risk prediction model for the occurrence of depression in patients with systemic lupus erythematosus during glucocorticoid maintenance therapy

目的探索系统性红斑狼疮(SLE)患者糖皮质激素维持治疗发生抑郁的危险因素,建立并验证抑郁风险的列线图模型。方法选取该院SLE患者288例,应用抑郁自评量表进行评估,将患者分为抑郁组和无抑郁组,通过单因素分析和多因素logistic回归分析确定抑郁发生的独立影响因素,应用R4.0.3软件构建SLE糖皮质激素维持治疗抑郁风险的列线图模型并验证。结果多因素logistic回归分析显示,糖皮质激素日平均剂量、睡眠质量、社会支持度和家庭人均月收入是抑郁发生的独立影响因素。根据上述4项影响因素构建的抑郁风险列线图模型:受试者工作特征(ROC)曲线的曲线下面积(AUC)为0.893,灵敏度为85.7%,特异度为83.0%,校准曲线为斜率接近于1的直线;外部模型验证结果:AUC为0.902,灵敏度为89.71%,特异度为71.24%。结论本研究基于SLE患者糖皮质激素日平均剂量、睡眠质量、社会支持度、家庭人均月收入4项抑郁发生的独立影响因素构建列线图模型,具有良好的区分度与准确度,可为临床个体化预测患者抑郁发生风险提供参考。

Objective To explore the risk factors of depression in patients with systemic lupus erythematosus(SLE)during glucocorticoid maintenance therapy,and to establish and verify the nomogram model for predicting depression risk.Methods A total of 288 patients with SLE in the Second Affiliated Hospital of Nanjing University of Chinese Medicine were selected.Patients were divided into the depression group and the non-depression group by self-rating depression scale.The univariate analysis and multivariate logistic regression analysis were used to determine the independent factors influencing depression.And the nomogram model for predicting depression risk of patients with SLE during glucocorticoid maintenance therapy was constructed and verified via the R4.0.3 software.Results The results of multivariate logistic regression analysis showed that the daily average dose of glucocorticoids,sleep quality,social support and family monthly income per capita were independent influencing factors of depression.The depression risk nomogram model was constructed based on the above four risk factors,the area under the ROC curve(AUC)was 0.893,the sensitivity was 85.7%,and the specificity was 83.0%,and the calibration curve was a straight line with a slope close to 1.The external model verification results showed that the AUC was 0.902,the sensitivity was 89.71%,and the specificity was 71.24%.Conclusion The nomogram model for predicting depression risk in SLE patients during glucocorticoid maintenance therapy has been constructed based on the daily average dose of glucocorticoids,sleep quality,social support and family monthly income per capita,with good discrimination and accuracy,which could provide references for clinically individualized prediction of the risk of depression in SLE patients.