细胞形态计量学对胸腹水鉴别诊断的Logistic回归分析

Logistic regression analysis of differential diagnosis of serous effusions by cell morphometry

目的建立细胞形态计量学对胸腹水鉴别诊断的Logistic回归模型。方法回顾性分析60例患者胸腹水的细胞形态参数,包括胞体大小、胞质特征、胞核大小、核质比、核仁/核、细胞核分裂象、细胞分布特点,通过多因素回归分析建立二分类Logistic回归模型,评价回归模型预报良性、恶性胸腹水的效能。结果进入Logistic回归模型的5个参数分别为胞体大小、胞核大小、核质比、核仁/核、细胞分布特点,回归模型预报良性、恶性胸腹水的准确度、敏感度、特异度分别为90.0%、86.7%、93.3%,ROC曲线下面积为0.977。结论胸腹水细胞形态计量学的Logistic回归模型有助于胸腹水的良性、恶性鉴别诊断。

Objective To establish a Logistic regression model for differential diagnosis of serous effusions by cell morphometry. Methods The cytomorphological parameters were analyzed in 60 patients with serous effusions, including the size of cell, cytoplasm characteristics, size of nucleus, nucleo cytoplasmic ratio, nucleolus/nuclear, mitotic figure and cellular distribution characteristics. Logistic regression model with bipartition was established by multivariate Logistic regression analysis, and the efficiency of Logistic regression model was evaluated to predict benign or malignant of these diseases. Results Five cytomorphological parameters, including the size of cell, size of nucleus, nucleo cytoplasmic ratio, nucleolus/nuclear and cellular distribution characteristics were took into the Logistic regression model. The accuracy, sensitivity and specificity of this model were 90.0% , 86.7% and 93.3% for predicting the benign or malignant serous effusions, respectively. Area under ROC curve was 0.977. Conclusion The Logistic regression model can be helpful for classification of benign or malignant serous effusions.