Abstract 16809: Deep-Learning-Based Assessment of Left Atrial Volume in Coronary Calcium CT: Association With NT-proBNP and Clinical Outcomes

Abstract

Introduction: Artificial Intelligence (AI) promises to extract imaging biomarkers for cardio-cerebrovascular (CV) risk prediction, though validation is still lacking. Recognizing the importance of left atrial pathology on CV events, we developed an AI algorithm to measure left atrial volume (LAvol) from CAC-CT. Its correlation with MRI, biomarkers, and CV incidents was then tested in the Dallas Heart Study 2 (DHS). Hypothesis: LAvol will be associated with elevations in baseline NT-proBNP levels and incident CV events. Methods: We trained a 3D U-Net model for cardiac chamber segmentation on CAC-CT, assessing congruity with manual segmentation via the Dice score. Normalized left atrial volume (LAvol/BSA) from 3D segmentations was compared to MRI using ICC, and its associations with baseline NT-proBNP and incident Afib, TIA, and stroke were evaluated with logistic regression and Cox models. Results: Cardiac segmentation showed an excellent Dice score of 0.93 ± 0.01. Moderate correlation was observed between CAC-CT estimates of LAvol/BSA and MRI (ICC 0.57, 95% CI 0.52-0.62). Our study, excluding those with prior events, comprised 1852 participants (mean age 50, 41% male, 46% black, 15% Hispanic). Upon multivariable adjustment (detailed in the table), LAvol/BSA was linked with elevated NT-proBNP (≥ 100 pg/mL) (OR 1.9, 95% CI 1.6-2.2 per 1SD LAvol/BSA). Over a 12.5-year follow-up, CAC-CT-derived LAvol/BSA showed association with a composite of Afib, TIA, and stroke (55 events) (HR 1.4, 95% CI 1.1 - 1.8), and Afib (HR 1.7, 95% CI 1.2 - 2.3), post-adjustment. No significant association was found with TIA (HR 1.2, 95% CI 0.6 - 2.1) or stroke (HR 1.3, 95% CI 0.9 - 1.8). Among 749 subjects, MRI-derived LAvol/BSA correlated with NT-proBNP (OR 1.7, 95% CI 1.44 - 2.10) but not with other clinical outcomes. Conclusions: Given associations with NT-proBNP levels and incident CV events, AI-measured LAvol from CAC-CT promises to improve risk prediction.