非IA期非小细胞肺癌EGFR罕见突变诊断模型构建

Construction of a Diagnostic Model for Non-IA Stage NSCLC with Rare EGFR Mutations

摘要: 目的：结合血清肿瘤标志物(STMs)和其他临床特征构建预测模型，旨在预测表皮生长因子受体(EGFR)罕见突变的发生。方法：回顾性收集766例接受EGFR基因检测的非IA期非小细胞肺癌(NSCLC)患者，以评估几种临床特征和STMs对EGFR罕见突变的潜在预测价值。结果：构建了包含癌胚抗原(CEA)、细胞角蛋白-19片段(CYFRA21-1)、鳞状细胞癌抗原(SCC-Ag)、病理学和性别的Nomogram模型，用于预测EGFR罕见突变。曲线下面积(AUC = 0.793)表明模型具有良好的预测性能。结论：CEA、CYFRA21-1和SCC-Ag是预测非IA期NSCLC患者EGFR罕见突变的关键因素。将STMs与其他临床因素相结合的Nomogram模型可以有效预测EGFR罕见突变。

Abstract: Objective: To develop a predictive model for the occurrence of rare mutations in the epidermal growth factor receptor (EGFR) by integrating serum tumor markers (STMs) and other clinical features. Methods: A retrospective analysis was conducted on 766 non-IA stage non-small cell lung cancer (NSCLC) patients who underwent EGFR gene testing to assess the potential predictive value of various clinical features and STMs for rare EGFR mutations. Results: A Nomogram model incorporating carcinoembryonic antigen (CEA), cytokeratin-19 fragment (CYFRA21-1), squamous cell carcinoma antigen (SCC-Ag), pathology, and gender was constructed to predict rare EGFR mutations in non-IA stage NSCLC. The area under the curve (AUC = 0.793) indicated good predictive performance of the model. Conclusion: CEA, CYFRA21-1, and SCC-Ag emerged as crucial factors for predicting rare EGFR mutations in non-IA stage NSCLC patients. The Nomogram model, integrating STMs with other clinical factors, proved effective in predicting rare EGFR mutations.