Abstract
Accurate, non-invasive, and cost-effective tools are needed to assist pulmonary nodule diagnosis and management due to increasing detection by low-dose computed tomography (LDCT). We perform genome-wide methylation sequencing on malignant and non-malignant lung tissues and designed a panel of 263 differential DNA methylation regions, which is used for targeted methylation sequencing on blood cell-free DNA (cfDNA) in two prospectively collected and retrospectively analyzed multicenter cohorts. We develop and optimize an integrative model for risk stratification of pulmonary nodules based on 40 cfDNA methylation biomarkers, age, and five simple computed tomography (CT) imaging features using machine learning approaches and validate its good performance in two cohorts. Using the two-threshold strategy can effectively reduce unnecessary invasive surgeries, overtreatment costs, and injury for patients with benign nodules while advising immediate treatment for patients with lung cancer, which can potentially improve the overall diagnosis of lung cancer following LDCT/CT screening.
Keywords:
low-dose computed tomography; methylation model; plasma cell-free DNA; pulmonary nodules; risk stratification.