应用Logistic回归模型评价超声在鉴别卵巢肿瘤良恶性中的价值

Evaluation of ultrasonic exam in differentiation diagnosis of ovarian tumors using Logistic regression

目的:探讨Logistic回归模型在鉴别卵巢肿瘤良恶性中的应用价值。方法:选择169例经手术病理证实的卵巢肿瘤患者,术前收集患者的一般资料、肿瘤标记物、二维灰阶超声、彩色多普勒超声各项指标,以病理诊断为金标准建立Logistic回归模型。绘制ROC曲线,评价Logistic回归模型的预报能力。结果:运用前进法二分类Logistic回归分析,筛选出对卵巢肿瘤的良恶性鉴别诊断中有统计学意义的特征变量包括肿瘤标记物水平、内部回声、阻力指数及腹水。Logistic回归模型对卵巢肿瘤良恶性预报的正确率为90.53%,敏感性为91.53%,特异性为90.00%。结论:所建立的Logistic回归模型对鉴别卵巢肿瘤的良恶性有较高的价值。

Objective：To evaluate the diagnostic value of Logistic model in differentiating malignant and benign ovarian tumors.Methods：All 169 patients with ovarian lesions confirmed by surgical pathology underwent ultrasonic exam.A Logistic model was obtained on the basis of ultrasonographic features.Receiver operator characteris （ROC） curve was constructed to assess the performance of the Logistic model.Results：Four ultrasonographic features including tumor makers,internal echo,RI and ascites were finally entered into the Logistic model.The percentage of correct prediction was 90.53％.Conclusion：Ultrasonic plays more important role in the differential diagnosis of ovarian tumors.