Cui Shu-Lei, Qi Lin-Lin, Liu Jia-Ning, Li Feng-Lan, Chen Jia-Qi, Cheng Sai-Nan, Xu Qian, Wang Jian-Wei
Department of Diagnostic Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
Department of Computed Tomography and Magnetic Resonance, The Fourth Hospital of Hebei Medical University, Shijiazhuang, China.
J Thorac Dis. 2024 Jul 30;16(7):4238-4249. doi: 10.21037/jtd-23-1943. Epub 2024 Jul 22.
Distinguishing benign from malignant sub-centimeter solid pulmonary nodules (SSPNs) continues to be challenging in clinical practice. Earlier diagnosis is crucial for improving patient survival and prognosis. This study aimed to investigate the risk factors of malignant SSPNs and establish and validate a prediction model based on computed tomography (CT) characteristics to assist in their early diagnosis.
A total of 261 consecutive participants with 261 SSPNs were retrospectively recruited between January 2012 and July 2023 from National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College (Center 1), including 161 malignant lesions and 100 benign lesions. Patients were randomly assigned to the training set (n=183) and validation set (n=78) according to a 7:3 ratio. Malignant nodules were confirmed by pathology; and benign nodules were confirmed by follow-up or pathology. Clinical data and CT features were collected to estimate the independent predictors of malignancy of SSPN with multivariate logistic analysis. A clinical prediction model was subsequently established by logistic regression. Furthermore, an additional 69 consecutive patients with 69 SSPNs from The Fourth Hospital of Hebei Medical University (Center 2) between January 2022 and December 2022 were retrospectively included as an external cohort to validate the predictive efficacy of the model. The performance of the prediction model was assessed by sensitivity, specificity, and the area under the receiver operating characteristic curve.
There were 113 (61.7%), 48 (61.5%) and 28 (40.6%) malignant SSPNs in the training, internal and external validation sets, respectively. Multivariate logistic analysis revealed four independent predictors of malignant SSPNs: tumor-lung interface (P=0.002), spiculation (P=0.04), air bronchogram (P=0.047), and invisible at the mediastinal window (P=0.003). The area under the curve (AUC) for the prediction model in the training set was 0.875 [95% confidence interval (CI): 0.818, 0.933]; and the sensitivity and specificity were 94.7% and 68.6%, respectively. The AUCs in the internal and external validation set were (0.781; 95% CI: 0.664, 0.897) and (0.873; 95% CI: 0.791, 0.955), respectively; the sensitivity and specificity were 66.7% and 83.3% for the internal validation data, and 100.0% and 61.0% for the external validation data, respectively.
The prediction model based on CT characteristics could be helpful for distinguishing malignant SSPNs from benign ones.
在临床实践中，区分亚厘米实性肺结节（SSPNs）的良恶性仍然具有挑战性。早期诊断对于改善患者生存率和预后至关重要。本研究旨在探讨恶性SSPNs的危险因素，并建立和验证基于计算机断层扫描（CT）特征的预测模型，以辅助其早期诊断。
2012年1月至2023年7月，从中国医学科学院肿瘤医院/国家癌症中心/国家癌症临床研究中心/北京协和医学院（中心1）回顾性招募了261例连续的患有261个SSPNs的参与者，其中包括161个恶性病变和100个良性病变。根据7:3的比例将患者随机分配到训练集（n = 183）和验证集（n = 78）。恶性结节经病理证实；良性结节经随访或病理证实。收集临床数据和CT特征，通过多因素逻辑分析评估SSPNs恶性的独立预测因素。随后通过逻辑回归建立临床预测模型。此外，2022年1月至2022年12月期间，从河北医科大学第四医院（中心2）回顾性纳入另外69例连续的患有69个SSPNs的患者作为外部队列，以验证该模型的预测效能。通过敏感性、特异性和受试者工作特征曲线下面积评估预测模型的性能。
训练集、内部验证集和外部验证集中分别有113个（61.7%）、48个（61.5%）和28个（40.6%）恶性SSPNs。多因素逻辑分析显示，恶性SSPNs的四个独立预测因素为：肿瘤-肺界面（P = 0.002）、毛刺征（P = 0.04）、空气支气管征（P = 0.047）和在纵隔窗不可见（P = 0.003）。预测模型在训练集中的曲线下面积（AUC）为0.875 [95%置信区间（CI）：0.818，0.933]；敏感性和特异性分别为94.7%和68.6%。内部验证集和外部验证集中的AUC分别为（0.781；95% CI：0.664，0.897）和（0.873；95% CI：0.791，0.955）；内部验证数据的敏感性和特异性分别为66.7%和83.3%，外部验证数据的敏感性和特异性分别为100.0%和61.0%。
基于CT特征的预测模型有助于区分恶性SSPNs和良性SSPNs。
