Despite progressive improvements over the decades, the rich temporally resolved data in an echocardiogram remain underutilized. Human assessments reduce the complex patterns of cardiac wall motion, to a small list of measurements of heart function. All modern echocardiography artificial intelligence (AI) systems are similarly limited by design – automating measurements of the same reductionist metrics rather than utilizing the embedded wealth of data. This underutilization is most evident where clinical decision making is guided by subjective assessments of disease acuity. Predicting the likelihood of developing post-operative right ventricular failure (RV failure) in the setting of mechanical circulatory support is one such example. Here we describe a video AI system trained to predict post-operative RV failure using the full spatiotemporal density of information in pre-operative echocardiography. We achieve an AUC of 0.729, and show that this ML system significantly outperforms a team of human experts at the same task on independent evaluation.

With recent advances in imaging methods, detection of LVNC is increasingly common. Concomitantly, the prognostic importance of LVNC is less clear. We followed 42 patients (63% male, age 44 ± 15 years) with incident heart failure or suspected cardiomyopathy, in whom cardiovascular magnetic resonance (CMR) yielded a diagnosis of LVNC, for 27 ± 16 months. LVNC was preferentially distributed among posterolateral segments, with apical predominance. Patients with maximum non-compacted-to-compacted thickness ratio (NC:C) < 3 improved by 0.9 ± 0.7 NYHA Class, compared to 0.3 ± 0.8 for patients with NC:C > 3 (p = 0.001). In 29 patients with baseline LVEF < 0.40, there was an inverse correlation between NC:C ratio, and the change in LVEF during follow-up. Tachyarrhythmias were observed in 42% of patients with LGE, and in 0% of patients without LGE (p = 0.02). In multivariate analysis, arrhythmia incidence was significantly higher in patients with LGE, even when adjusted for LVEF and RVEF. CMR assessments of myocardial morphology provide important prognostic information for patients with LVNC who present with incident heart failure or suspected cardiomyopathy.