Abstract 14453: Deep Learning Enabled Measurement of Cardiac Sphericity Predicts Disease Risk Among Subjects With Normal Left Ventricular Size and Function

Abstract

Introduction: Cardiac imaging primarily focuses on measurements of chamber size and function. Quantitative assessment of morphology may provide additional prognostic information. Left ventricle (LV) sphericity has been proposed as one metric but has not been studied in large populations and is poorly characterized in patients with normal LVs. We aimed to assess the clinical relevance and genetic drivers of sphericity among individuals with normal LV size and systolic function using deep learning enabled phenotyping of cardiac MRIs. Methods: The study cohort consisted of UK Biobank participants with normal LV ejection fraction, LV end-systolic, and end-diastolic volumes by MRI. A fully convolutional neural network was used to perform image segmentation of cardiac chambers. The main exposure was the LV sphericity index, defined as the ratio of short-axis to long-axis lengths of the smallest rectangle encompassing the LV in a 4-chamber view. Risk for incident outcomes were measured using Cox analysis. Genome-wide association study (GWAS) was performed using HAIL software with standard quality-control. Genetic correlations were measured using linkage-disequilibrium score regression. Causal inference was performed using two-sample Mendelian randomization (MR). Results: We identified 38,897 subjects with normal LV volumes and ejection fraction. Mean age was 55 ± 8, and 54% were female. After adjusting for age, sex, BMI, hypertension, and pulse-rate, a 1 standard deviation increase in sphericity index was associated with increased risk of atrial fibrillation (HR 1.31, 95% CI 1.23-1.38, P <2x10 -16 ) and cardiomyopathy (HR 1.62, 95% CI 1.29-2.02, P 2.4x10 -5 ). GWAS of sphericity index identified 4 loci at genome-wide significance, with 3 candidate genes previously implicated in cardiac development and conduction. Sphericity index showed a genetic correlation with cardiomyopathy ( rg 0.42, P 0.01) but not with atrial fibrillation ( rg 0.04, P 0.5). Bidirectional MR analyses supported cardiomyopathy as being causal for sphericity but not the reverse. Conclusion LV sphericity in subjects with normal size and function is genetically mediated and may reflect subclinical manifestations of cardiomyopathic risk prior to LV remodeling by standard measures.