Logistic回归和ROC曲线综合评价检测四种尿蛋白排泄对早期肾小球疾病的诊断价值

目的：应用LogistIc回归和ROC曲线探讨尿白蛋白、α2-巨球蛋白、IgG、α1-微球蛋白4种蛋白排泄单独或联合检测对早期肾小球疾病的诊断价值。方法：收集肾小球疾病组患者22例,肾小管间质疾病组患者12例,非肾实质性疾病组患者20例,健康对照组35例,检测患者晨尿白蛋白、α2-巨球蛋白、IgG、α1-微球蛋白4种蛋白的排泄量。应用Logistic回归模型,绘制ROC曲线并计算曲线下面积（AUC）来评价各指标的诊断价值。结果：尿白蛋白和IgG的检测与肾小球疾病的诊断呈密切正相关（P〈0.01;P〈0.05）,而α2-巨球蛋白、α1-微球蛋白的相关性不大（P〉0.05）;4种蛋白的联合检测诊断肾小球疾病的AUC为0.94,高于尿白蛋白和IgG的检测的AUC分别为0.861、0.856。结论：尿白蛋白和IgG的检测可作为肾小球疾病的诊断标志物,4种蛋白联合检测有较好的互补作用,可以显著提高诊断肾小球疾病的特异性。

Logistic Regression and ROC Curve Detected Four Kinds of Comprehensive Evaluation of Urinary Protein Excretion in the Early Diagnosis of Glomerular Disaes

Objective：To explore the diagnostic value of urinary protein excretion of Alb,IgG,α2-macroglobulin andα1-microglobulin for Early glomerular disease by a model of logistic regression and ROC curve.Methods：Methods Collected 22 cases of patients with glomerular diseases,tubular interstitial disease patients,12 cases of non-renal parenchymal disease group 20 patients,35 cases of healthy controls,while urinary albumin,α2-macroglobulin,IgG,Four protein α1-microglobulin excretion.Applied Logistic Regression Model,drawing ROC curves and calculate the area under the curve （AUC） to evaluate the diagnostic value of each index.Results：Urinary albumin and IgG in the detection and diagnosis of glomerular disease was positively correlated （P0.01;P0.05）,while the α2-macroglobulin,α1-microglobulin is not associated （P0.05） ;four proteins combined detection and diagnosis of glomerular disease,the area under the ROC curve （AUC） was 0.94,higher than the detection of urinary albumin and IgG in the AUC were 0.861,0.856.Conclusion：Detection of urinary albumin and IgG as a diagnostic marker of glomerular disease,joint detection of four proteins has a good complement,which can significantly improve the diagnostic specificity of glomerular disease.