Predicting Recurrence of Stage IA Lung Adenocarcinoma Using Circulating Tumor Cell–Free DNA Whole-Genome Mutational Signatures

Lung adenocarcinoma (LUAD) remains a leading cause of cancer-related mortality. Although for stage IA, LUAD surgery is often curative, recurrence rates remain significant. Liquid biopsy enables monitoring residual disease and predicts recurrence; however, utility in stage IA LUAD is not well established. Tumor-informed whole-genome sequencing (WGS) represents a highly sensitive liquid biopsy method for the analysis of circulating tumor cell–free DNA (ctDNA) without designing and maintaining patient-specific probes. This study aimed to determine the prognostic value of genome-wide tumor-informed minimal residual disease monitoring in stage IA non–small-cell lung cancer (NSCLC) using WGS of ctDNA. WGS was performed on 42 patients with stage IA NSCLC. Tumor was sequenced at 40× and germline DNA and plasma derived ctDNA at 20×, and patient-specific mutational signatures were developed from the tumor-normal comparison and applied to ctDNA WGS at each time point using an artificial intelligence–supported pattern recognition algorithm. ctDNA results were compared with clinical recurrence. WGS ctDNA was able to predict recurrence with 0.75 sensitivity and 0.83 specificity, with median 16.7 months lead time compared with clinical or imaging recurrence. ctDNA WGS was able to distinguish between a second primary and recurrence in histologically or clinically challenging cases. Whole-genome sequencing of ctDNA can predict recurrence in the earliest clinical stage of NSCLC, identifying patients who will recur, and providing information to help guide radiological follow-up and adjuvant therapy.