Lung tumor discrimination by deep neural network model CanDo via DNA methylation in bronchial lavage

Abstract

Summary: Bronchoscopic-assisted discrimination of lung tumors presents challenges, especially in cases with contraindications or inaccessible lesions. Through meta-analysis and validation using the HumanMethylation450 database, this study identified methylation markers for molecular discrimination in lung tumors and designed a sequencing panel. DNA samples from 118 bronchial washing fluid (BWF) specimens underwent enrichment via multiplex PCR before targeted methylation sequencing. The Recursive Feature Elimination Cross-Validation and deep neural network algorithm established the CanDo classification model, which incorporated 11 methylation features (including 8 specific to the TBR1 gene), demonstrating a sensitivity of 98.6% and specificity of 97.8%. In contrast, bronchoscopic rapid on-site evaluation (bronchoscopic-ROSE) had lower sensitivity (87.7%) and specificity (80%). Further validation in 33 individuals confirmed CanDo’s discriminatory potential, particularly in challenging cases for bronchoscopic-ROSE due to pathological complexity. CanDo serves as a valuable complement to bronchoscopy for the discriminatory diagnosis and stratified management of lung tumors utilizing BWF specimens.

Keywords

• Disease
• Cell
• Computing methodology