Yang Qingjie, Sun Xiaoyan, Lv Shenghua, Li Qingtian, Lan Linhui, Liu Ningquan, Wang Mingyang, Han Kaibao, Feng Xinhai
Department of Thoracic Surgery, Xiamen Humanity Hospital, Fujian Medical University, Xiamen, China.
J Thorac Dis. 2025 Mar 31;17(3):1349-1363. doi: 10.21037/jtd-24-1763. Epub 2025 Mar 23.
Accurately identifying whether pulmonary nodules are microinvasive adenocarcinoma or invasive carcinoma (MIA or IC) is clinically significant. This study aims to construct a predictive model for this.
Clinical, computed tomography (CT) image, and peripheral blood methylation data of 294 patients were collected. Based on postoperative pathology, they were divided into invasive (MIA or IC) and non-invasive groups. A quarter of the data was randomly selected as the validation set, and the rest was the training set. Screened significant indicators in training set and divided into three groups: clinical and image features, methylation features, and comprehensive features combining both. Logistic regression analyses were conducted respectively to construct models, and the model effect was verified in the validation set.
There were six indicators in the comprehensive model (proportion of solid components, maximum CT value, SH3BP5_338_ CpG 4, PNPLA2_329_CpG 1, PNPLA2_329_CpG 4, and ARHGAP35 476_CpG_5). The area under the curve (AUC) of the training set and the validation set were 0.90 and 0.87, respectively. Prediction accuracies were 82% and 82%, sensitivities were 82% and 80%, specificities were 82% and 84%. The predictive effect of comprehensive model was better than that of the clinical and image feature model and the methylation feature model.
The invasiveness predictive model for pulmonary nodules constructed by combining clinical, CT image, and methylation features in this study has a relatively satisfactory effect and is worthy of further exploration and improvement.
准确鉴别肺结节是微浸润腺癌还是浸润性癌（MIA或IC）具有重要临床意义。本研究旨在构建对此的预测模型。
收集294例患者的临床、计算机断层扫描（CT）图像及外周血甲基化数据。根据术后病理将其分为浸润性（MIA或IC）和非浸润性组。随机抽取四分之一的数据作为验证集，其余作为训练集。在训练集中筛选出显著指标并分为三组：临床和影像特征、甲基化特征以及两者结合的综合特征。分别进行逻辑回归分析构建模型，并在验证集中验证模型效果。
综合模型中有六个指标（实性成分比例、最大CT值、SH3BP5_338_CpG 4、PNPLA2_329_CpG 1、PNPLA2_329_CpG 4和ARHGAP35 476_CpG_5）。训练集和验证集的曲线下面积（AUC）分别为0.90和0.87。预测准确率分别为82%和82%，敏感性分别为82%和80%，特异性分别为82%和84%。综合模型的预测效果优于临床和影像特征模型以及甲基化特征模型。
本研究通过结合临床、CT图像和甲基化特征构建的肺结节浸润性预测模型效果较为满意，值得进一步探索和完善。
