• Siwei Wang, Fanchen Meng, Peng Chen, Yang Lv, Min Wu, Haimeng Tang, Hua Bao, Xue Wu, Yang Shao, Jie Wang, Juncheng Dai, Lin Xu, Xiaoxiao Wang, and Rong Yin.
• Department of Thoracic Surgery, Jiangsu Key Laboratory of Molecular and Translational Cancer Research, Nanjing Medical University Affiliated Cancer Hospital & Jiangsu Cancer Hospital & Jiangsu Institute of Cancer Research, Nanjing, China; Clinical Research Institute of Traditional Chinese Medicine, Jiangsu Province Hospital of Chinese Medicine, The Affiliated Hospital of Nanjing University of Chinese Medicine, Nanjing, China.
• J. Thorac. Cardiovasc. Surg. 2024 Apr 24.

ObjectiveAlthough low-dose computed tomography has been proven effective to reduce lung cancer-specific mortality, a considerable proportion of surgically resected high-risk lung nodules were still confirmed pathologically benign. There is an unmet need of a novel method for malignancy classification in lung nodules.MethodsWe recruited 307 patients with high-risk lung nodules who underwent curative surgery, and 247 and 60 cases were pathologically confirmed malignant and benign lung lesions, respectively. Plasma samples from each patient were collected before surgery and performed low-depth (5×) whole-genome sequencing. We extracted cell-free DNA (cfDNA) characteristics and determined radiomic features. We built models to classify the malignancy using our data and further validated models with two independent lung nodule cohorts.ResultsOur models using one type of profile were able to distinguish lung cancer and benign lung nodules (BLNs) at an area under the curve (AUC) metrics of 0.69-0.91 in the study cohort. Integrating all the five base models using cfDNA profiles, the cfDNA-based ensemble model achieved an AUC of 0.95 (95%CI: 0.92-0.97) in the study cohort and 0.98 (95%CI: 0.96-1.00) in the validation cohort. At a specificity of 95.0%, the sensitivity reached 80.0% in the study cohort. With the same threshold, the specificity and sensitivity had similar performances in both validation cohorts. Furthermore, the performance of AUC reached 0.97 both in the study and validation cohorts when considering the radiomic profile.ConclusionsThe cfDNA profiles-based method is an efficient non-invasive tool to distinguish malignancies and high-risk but pathologically BLNs.Copyright © 2024. Published by Elsevier Inc.

5 keywords...

hide…