Abstract 4144043: Automated Left Ventricular Volumetry using Artificial Intelligence in Coronary Calcium Scans (AI-CAC) Predicts Heart Failure Comparably to Cardiac MRI and Outperforms NT-proBNP: The Multi-Ethnic Study of Atherosclerosis (MESA)

Introduction: Artificial intelligence-powered coronary artery calcium scan (AI-CAC) provides more actionable information than currently reported. We have previously shown in the Multi-Ethnic Study of Atherosclerosis (MESA) that AI-enabled left atrial (LA) volumetry in CAC scans (AI-CAC) enabled prediction of atrial fibrillation (AF) as early as one year. Furthermore, we have shown adding AI-CAC LA volumetry to CHA 2 DS 2 -VASc risk score improved stroke prediction in MESA. We have recently reported that AI-CAC left ventricular (LV) volumetry and mass significantly predicted incident heart failure (HF) and outperformed NT-proBNP. In this study, we compared LV volume measured by AI-CAC versus cardiac magnetic resonance (CMR) imaging and NT-proBNP for predicting HF. Additionally, we compared AI-CAC vs. NT-proBNP for detection of left ventricular hypertrophy (LVH) defined by the 95th percentile of CMR LV mass. Methods: We used 15-year outcomes data for incident HF from 3078 asymptomatic MESA participants (52.3% women, age 62.2±10.3 years) who underwent both CAC scans and CMR at the baseline examination. We applied the AutoChamber TM (HeartLung.AI, Houston, TX) component of AI-CAC to 3078 CAC scans.Data on CMR semi-automated LV volume, NT-proBNP, and Agatston CAC score were obtained from MESA. Discrimination was assessed using the time-dependent area under the curve (AUC) for incident HF. Results: Over 15 years of follow up, 133 cases of HF were diagnosed. The AUC for AI-CAC (0.789) and CMR (0.793) were not significantly different (p=0.67) but were significantly higher than NT-proBNP (0.719) and Agatston score (0.664) (p<.0001) for prediction of incident HF. AI-CAC and CMR significantly improved the continuous Net Reclassification Index of NT-proBNP (0.37) and Agatston score (0.45) for HF prediction (p<0.001 for all). The AUC for AI-CAC vs. NT-proBNP for LVH was 0.871 vs. 0.600 for males and 0.854 vs. 0.600 for females. Conclusion: In this multi-ethnic asymptomatic population, AI-CAC automated LV volumetry and CMR semi-automated LV volumetry similarly predicted incident HF over 15 years and outperformed NT-proBNP. AI-CAC significantly outperformed NT-proBNP for detection of LVH. Both AI-CAC and CMR significantly improved on NT-proBNP and Agatston CAC score for predicting incident HF.