Validation of American Society of Echocardiography Guideline-Recommended Parameters of Right Ventricular Dysfunction Using Artificial Intelligence Compared With Cardiac Magnetic Resonance Imaging

Abstract

Right ventricular function is important in evaluation of cardiac function but its assessment by standard transthoracic echocardiographic (TTE) remains challenging. Cardiac magnetic resonance imaging (CMR) is considered the gold standard. The American Society of Echocardiography recommends surrogate measures of RV function and ejection fraction (RVEF) by TTE including fractional area change (FAC), free wall strain (FWS), and tricuspid annular planar systolic excursion (TAPSE), but they require technical expertise in acquisition and quantification. We sought to evaluate the sensitivity, specificity, and positive and negative predictive values (PPV, NPV) of FAC, FWS, and TAPSE derived by a rapid, novel artificial intelligence (AI) software (LVivoRV®) from a single-plane TTE apical 4-chamber (A4C), RV-focused view without ultrasound-enhancing agents for detecting abnormal RV function compared with CMR-derived RVEF. RV dysfunction was defined as RVEF<50% and <40% on CMR. TTE and CMR were performed within a median of 10 days [IQR: 2-32] of each other in 225 consecutive patients without interval procedural or pharmacological intervention. The sensitivity and NPV to detect CMR-defined RV dysfunction when all three AI-derived parameters (FAC, FWS, and TAPSE) were abnormal were 91% and 96%, while those of expert physician-reads were 91% and 97%. Specificities and PPV were lower (50% and 32%) compared with expert physician-read echocardiograms (82% and 56%). AI-derived measurements of FAC, FWS, and TAPSE had excellent sensitivity and NPV for ruling out significant RV dysfunction (CMR RVEF <40%), comparable to that of expert physician readers, but lower specificity. This AI, using ASE guidelines, may serve as a useful screening tool for rapid bedside assessment to exclude significant RV dysfunction.