亚实性肺结节良恶性数学预测模型的建立与验证

Establishment and verification of a mathematical prediction model for benignancy and malignancy in subsolid pulmonary nodules

目的探讨亚实性肺结节良恶性病变的独立危险因素,建立恶性概率预测模型。方法回顾性分析江苏省苏北人民医院2014~2018年入院且病理结果明确的443例亚实性肺结节患者的病例资料,包括临床资料、影像学特征及肿瘤标志物。将患者随机分为建模组和验证组,其中建模组296例,男125例、女171例,平均年龄(55.9±11.1)岁;验证组147例,男68例、女79例,平均年龄(56.9±11.6)岁。应用单因素及多因素分析,筛选亚实性肺结节良恶性病变的独立危险因素,建立预测模型;基于验证组数据,对本研究模型与Mayo、VA、Brock及北京大学人民医院(PKUPH)模型进行对比验证。结果单因素及多因素分析显示,性别、肿瘤实性成分直径比值(consolidation/tumor ratio,CTR)、边界、毛刺征、分叶征及癌胚抗原(carcinoembryonic antigen,CEA)是判断亚实性肺结节良恶性病变的独立危险因素。预测模型公式为:恶性概率P=ex/(1+ex)。X=0.018+(1.436×性别)+(2.068×CTR)+(–1.976×边界)+(2.082×毛刺征)+(1.277×分叶征)+(2.296×CEA)。本研究模型受试者工作特征曲线下面积为0.856,灵敏度为81.6%,特异性为75.6%,阳性预测值为95.4%,阴性预测值为39.8%。与传统模型进行模型间对比验证,本研究模型预测价值显著优于Mayo、VA、Brock和PKUPH模型。结论相较于Mayo、VA、Brock和PKUPH模型,本研究建立的亚实性肺结节良恶性预测模型预测价值更为理想,具有较大的临床应用价值,可作为亚实性结节的早期筛查方法。

Objective To explore the independent risk factors for benign and malignant subsolid pulmonary nodules and establish a malignant probability prediction model.Methods A retrospective analysis was performed in 443 patients with subsolid pulmonary nodules admitted to Subei People’s Hospital of Jiangsu Province from 2014 to 2018 with definite pathological findings.The patients were randomly divided into a modeling group and a validation group.There were 296 patients in the modeling group,including 125 males and 171 females,with an average age of 55.9±11.1 years.There were 147 patients in the verification group,including 68 males and 79 females,with an average age of 56.9±11.6 years.Univariate and multivariate analysis was used to screen the independent risk factors for benign and malignant lesions of subsolid pulmonary nodules,and then a prediction model was established.Based on the validation data,the model of this study was compared and validated with Mayo,VA,Brock and PKUPH models.Results Univariate and multivariate analysis showed that gender,consolidation/tumor ratio(CTR),boundary,spiculation,lobulation and carcinoembryonic antigen(CEA)were independent risk factors for the diagnosis of benign and malignant subsolid pulmonary nodules.The prediction model formula for malignant probability was:P=ex/(1+ex).X=0.018+(1.436×gender)+(2.068×CTR)+(-1.976×boundary)+(2.082×spiculation)+(1.277×lobulation)+(2.296×CEA).In this study,the area under the curve was 0.856,the sensitivity was 81.6%,the specificity was 75.6%,the positive predictive value was95.4%,and the negative predictive value was 39.8%.Compared with the traditional model,the predictive value of this model was significantly better than that of Mayo,VA,Brock and PKUPH models.Conclusion Compared with Mayo,VA,Brock and PKUPH models,the predictive value of the model is more ideal and has greater clinical application value,which can be used for early screening of subsolid nodules.