Computer-Aided Pulmonary Fibrosis Detection Leveraging an Advanced Artificial Intelligence Triage and Notification Software.

Background: Improvement in recognition and referral of pulmonary fibrosis (PF) is vital to improving patient outcomes within interstitial lung disease. We determined the performance metrics and process-ing time of an artificial intelligence triage and notification software, ScreenDx-LungFibrosis (TM), developed to improve detection of PF.Methods: ScreenDx-LungFibrosis (TM) was applied to chest computed tomography (CT) scans from multisource data. Device output (+/-PF) was compared to clinical diagnosis (+/-PF), and diagnostic per-formance was evaluated. Primary endpoints included device sensitiv-ity and specificity > 80% and processing time < 4.5 min.Results: Of 3,018 patients included, PF was present in 22.9%. ScreenDx-LungFibrosis(TM )detected PF with a sensitivity and specificity of 91.3% (95% confidence interval (CI): 89.0-93.3%) and 95.1% (95% CI: 94.2-96.0%), respectively. Mean processing time was 27.6 s (95% CI: 26.0 -29.1 s).Conclusions: ScreenDx-LungFibrosis (TM) accurately and reliably identified PF with a rapid per-case processing time, underscoring its potential for transformative improvement in PF outcomes when routinely applied to chest CTs.