AI-DERIVED AUTOMATED QUANTIFICATION OF CARDIAC CHAMBERS AND MYOCARDIUM FROM NON-CONTRAST CT: PREDICTION OF ADVERSE CARDIOVASCULAR EVENTS IN ASYMPTOMATIC SUBJECTS

Abstract

Therapeutic Area: ASCVD/CVD Risk Assessment Background: The significance of myocardial mass and chamber volumes from non-contrast computed tomography (CT) for predicting major adverse cardiovascular events (MACE) has not been studied. Our objective was to evaluate the role of artificial intelligence-enabled multi-chamber cardiac volumetry from non-contrast CT for long-term risk stratification in asymptomatic subjects without known coronary artery disease. Methods: Our study included 2022 asymptomatic individuals (55.6±9.0 years; 59.2% male) from the EISNER (Early Identification of Subclinical Atherosclerosis by Noninvasive Imaging Research) trial. The multi-chamber cardiac volumetry was performed using deep-learning algorithms from routine non-contrast CT scans for coronary artery calcium scoring. MACE was defined as myocardial infarction, late (>180 days) revascularization, and cardiac death. Results: A total of 215 individuals (11%) suffered MACE at a mean follow-up of 13.9±3 years. Individuals with MACE, as compared to those without MACE, had higher left ventricle (LV) myocardial mass (118.1 g vs 106.9 g, p 118.1 g) and chamber (> 105.0 cm3) volume, as divided into tertiles, presented a steep increase in the risk of MACE (log rank p<0.001). Conclusions: LV volume and myocardial mass quantified automatically by AI from routine non-contrast CT independently predicted long-term MACE risk in asymptomatic patients without known coronary artery disease. AI-derived LV measurements from routine non-contrast cardiac CT without physician interaction may improve the risk stratification of MACE.