A Noninvasive Multianalytical Approach for Lung Cancer Diagnosis of Patients with Pulmonary Nodules

Abstract

Addressing thehigh false‐positive rate of conventional low‐dose computed tomography (LDCT)for lung cancer diagnosis, the efficacy of incorporating blood‐basednoninvasive testing for assisting practicing clinician's decision making indiagnosis of pulmonary nodules (PNs) is investigated. In this prospectiveobservative study, next generation sequencing‐ (NGS‐) based cell‐free DNA(cfDNA) mutation profiling, NGS‐based cfDNA methylation profiling, andblood‐based protein cancer biomarker testing are performed for patients withPNs, who are diagnosed as high‐risk patients through LDCT and subsequentlyundergo surgical resections, with tissue sections pathologically examined andclassified. Using pathological classification as the gold standard, statisticaland machine learning methods are used to select molecular markers associatedwith tissue's malignant classification based on a 98‐patient discovery cohort(28 benign and 70 malignant), and to construct an integrative multianalyticalmodel for tissue malignancy prediction. Predictive models based on individualtesting platforms have shown varying levels of performance, while their finalintegrative model produces an area under the receiver operating characteristiccurve (AUC) of 0.85. The model's performance is further confirmed on a29‐patient independent validation cohort (14 benign and 15 malignant, withpower > 0.90), reproducing AUC of 0.86, which translates to anoverall sensitivity of 80% and specificity of 85.7%.

Keywords

cfDNA methylation, cfDNA mutations, circulating tumor DNA, lung cancer diagnosis, machine learning, protein cancer biomarkers, pulmonary nodules

For article detail information, pls visit https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8261512/

MagPure FFPE DNA Kit

For more product information, pls visit http://www.magen-tec.com/products/info.aspx?lcid=34&itemid=87