CT-derived functional imaging biomarkers combined with FEV1 for predicting 10-year all-cause mortality in COPDGene cohort.

Abstract

This study evaluates the predictive power of CT-derived functional imaging (CTFI) combined with forced expiratory volume in 1 second (FEV1) for 10-year all-cause mortality in COPD patients. We analyzed 8583 participants from the COPDGene® cohort, focusing on 3550 participants with spirometric obstruction. CTFI metrics, including ventilation (CT-V) and perfusion (PBM), were computed from non-contrast CT scans at lobar resolution. Our findings show that regional and global CTFI scores decline with advancing GOLD stages. A Random Survival Forest model, adjusted for age, BMI, and scanner type, demonstrated significant improvement in mortality prediction when combining FEV1 with CTFI, compared to FEV1 alone, with an AUC increase from 0.71 to 0.76 over 10 years. The Net Reclassification Index further confirmed the added predictive value of CTFI. These results suggest that integrating CTFI with traditional lung function measures enhances mortality prediction in COPD, offering a promising tool for clinical risk assessment.