Predicting post-operative right ventricular failure using video-based deep learning

TL;DR

This paper introduces a novel deep learning system that analyzes pre-operative echocardiography videos to predict post-operative right ventricular failure, outperforming human experts and utilizing full spatiotemporal data.

Contribution

The study presents a new video AI approach that leverages complete echocardiography data for predicting RV failure, surpassing traditional measurement-based methods and human performance.

Findings

Achieved an AUC of 0.729 in prediction accuracy.

Outperformed human experts in clinical evaluation.

Demonstrated generalizability to other cardiac decision support tasks.

Abstract

Non-invasive and cost effective in nature, the echocardiogram allows for a comprehensive assessment of the cardiac musculature and valves. Despite progressive improvements over the decades, the rich temporally resolved data in echocardiography videos remain underutilized. Human reads of echocardiograms reduce the complex patterns of cardiac wall motion, to a small list of measurements of heart function. Furthermore, all modern echocardiography artificial intelligence (AI) systems are similarly limited by design - automating measurements of the same reductionist metrics rather than utilizing the wealth of data embedded within each echo study. This underutilization is most evident in situations where clinical decision making is guided by subjective assessments of disease acuity, and tools that predict disease onset within clinically actionable timeframes are unavailable. Predicting the likelihood of developing post-operative right ventricular failure (RV failure) in the setting of mechanical circulatory support is one such clinical example. To address this, we developed a novel video AI system trained to predict post-operative right ventricular failure (RV failure), using the full spatiotemporal density of information from pre-operative echocardiography scans. We achieve an AUC of 0.729, specificity of 52% at 80% sensitivity and 46% sensitivity at 80% specificity. Furthermore, we show that our ML system significantly outperforms a team of human experts tasked with predicting RV failure on independent clinical evaluation. Finally, the methods we describe are generalizable to any cardiac clinical decision support application where treatment or patient selection is guided by qualitative echocardiography assessments.