Department of Thoracic Surgery and Oncology, The First Affiliated Hospital of Guangzhou Medical University, China National Center for Respiratory Medicine, China State Key Laboratory of Respiratory Disease & National Clinical Research Center for Respiratory Disease, Guangzhou, China.
AnchorDx Medical Co., Guangzhou, China.
J Clin Invest. 2021 May 17;131(10). doi: 10.1172/JCI145973.
BACKGROUNDCurrent clinical management of patients with pulmonary nodules involves either repeated low-dose CT (LDCT)/CT scans or invasive procedures, yet causes significant patient misclassification. An accurate noninvasive test is needed to identify malignant nodules and reduce unnecessary invasive tests.METHODWe developed a diagnostic model based on targeted DNA methylation sequencing of 389 pulmonary nodule patients' plasma samples and then validation in 140 plasma samples independently. We tested the model in different stages and subtypes of pulmonary nodules.RESULTSA 100-feature model was developed and validated for pulmonary nodule diagnosis; the model achieved a receiver operating characteristic curve-AUC (ROC-AUC) of 0.843 on 140 independent validation samples, with an accuracy of 0.800. The performance was well maintained in (a) a 6 to 20 mm size subgroup (n = 100), with a sensitivity of 1.000 and adjusted negative predictive value (NPV) of 1.000 at 10% prevalence; (b) stage I malignancy (n = 90), with a sensitivity of 0.971; (c) different nodule types: solid nodules (n = 78) with a sensitivity of 1.000 and adjusted NPV of 1.000, part-solid nodules (n = 75) with a sensitivity of 0.947 and adjusted NPV of 0.983, and ground-glass nodules (n = 67) with a sensitivity of 0.964 and adjusted NPV of 0.989 at 10% prevalence. This methylation test, called PulmoSeek, outperformed PET-CT and 2 clinical prediction models (Mayo Clinic and Veterans Affairs) in discriminating malignant pulmonary nodules from benign ones.CONCLUSIONThis study suggests that the blood-based DNA methylation model may provide a better test for classifying pulmonary nodules, which could help facilitate the accurate diagnosis of early stage lung cancer from pulmonary nodule patients and guide clinical decisions.FUNDINGThe National Key Research and Development Program of China; Science and Technology Planning Project of Guangdong Province; The National Natural Science Foundation of China National.
目前，肺结节患者的临床管理包括重复进行低剂量 CT（LDCT）/CT 扫描或采用有创性操作，但这会导致大量患者被误诊。因此，需要一种准确的非侵入性检测方法来识别恶性结节并减少不必要的有创性检测。
我们基于 389 例肺结节患者血浆样本的靶向 DNA 甲基化测序开发了一种诊断模型，并在 140 例独立血浆样本中进行了验证。我们在不同阶段和亚型的肺结节中对该模型进行了测试。
我们建立并验证了一个用于肺结节诊断的 100 个特征模型；该模型在 140 例独立验证样本中实现了 0.843 的受试者工作特征曲线下面积（ROC-AUC），其准确性为 0.800。该模型在以下情况中的表现保持良好：（a）大小为 6 至 20 毫米的亚组（n = 100），其灵敏度为 1.000，10%患病率时的调整阴性预测值（NPV）为 1.000；（b）I 期恶性肿瘤（n = 90），灵敏度为 0.971；（c）不同的结节类型：实性结节（n = 78）的灵敏度为 1.000，调整后的 NPV 为 1.000，部分实性结节（n = 75）的灵敏度为 0.947，调整后的 NPV 为 0.983，磨玻璃结节（n = 67）的灵敏度为 0.964，调整后的 NPV 为 0.989，10%患病率时。这种称为 PulmoSeek 的甲基化检测在鉴别良恶性肺结节方面优于 PET-CT 和 2 种临床预测模型（Mayo 诊所和退伍军人事务部）。
该研究表明，基于血液的 DNA 甲基化模型可能为肺结节分类提供更好的检测方法，有助于从肺结节患者中准确诊断早期肺癌，并指导临床决策。
中国国家重点研发计划；广东省科技计划项目；中国国家自然科学基金。
