CT影像学特征联合肺癌自身抗体列线图模型对恶性肺结节的诊断价值

Diagnostic Value of Nomogram Model of CT Imaging Features Combined with Lung Cancer Autoantibody in Malignant Pulmonary Nodules

目的:探讨CT影像学特征联合肺癌自身抗体构建的列线图模型对恶性肺结节的诊断价值。方法:回顾性获取26例良性肺结节和80例恶性肺结节患者的人口学、CT影像和肺癌自身抗体资料数据。采用单因素、最小绝对值选择与收缩算子(LASSO)和多因素Logistic回归分析筛选恶性肺结节的独立危险因素,并据此建立列线图模型;采用受试者工作特征曲线(ROC)及校准曲线验证该模型。结果:CT特征指标结节位于上叶(UP)、CT恶性特征(CTF)和肺癌自身抗体指标p53、G抗原7(GAGE7)、ATP结合RNA解旋酶4-5(GBU4-5)、SRY盒转录因子2(SOX2)等为恶性肺结节的独立危险因素(P<0.05)。列线图模型显示其预测恶性肺结节的概率为89.7%,ROC和校准曲线也验证列线图模型有良好临床预测能力。结论:基于CT影像学特征和肺癌自身抗体构建的列线图对恶性肺结节有良好诊断效能,可作为无创量化模型用于肺结节管理。

Objective:To explore the diagnostic value of nomogram based on CT imaging features and lung cancer autoantibody in malignant pulmonary nodules.Method:Demographic,CT imaging,and lung cancer autoantibody data about 26 patients with benign pulmonary nodules and 80 patients with malignant pulmonary nodules were retrospectively reviewed.Relevant risk factors were screened by univariate analysis,least absolute selection and shrinkage operator(LASSO)regression analysis,and multivariate logistic regression analysis,and a nomogram was established.Receiver operating curve(ROC)and calibration curve were used to validate the nomogram.Results:CT characteristic indicators including located in the upper lobe(UP),CT malignant features(CTF),and lung cancer autoantibody indicators such as P53,G antigen 7(GAGE7),ATP binding RNA helicase 4-5(GBU4-5),SRY box transcription factor 2(SOX2)were independent risk factors for predicting malignant pulmonary nodules(P<0.05).The probability of predicting malignant pulmonary nodules using nomogram was 89.7%.The ROC and calibration curve validation demonstrated that the nomogram was clinically effective in malignant pulmonary nodules.Conclusion:The nomogram based on CT features and lung cancer associated autoantibody is effective in the diagnosis of malignant pulmonary nodules,and can also be performed as a non-invasive quantitative model for the management of pulmonary nodules.