Key result
An AI echocardiography system predicted post-operative right ventricular failure with an AUC of 0.860, significantly outperforming contemporary clinical risk scores and manual echocardiographic metrics.
Why the study?
Post-operative RV failure is the largest contributor to short-term mortality in LVAD patients, but pre-operative risk prediction has remained beyond the abilities of experts.
Does an AI-based echocardiography analysis pipeline improve the prediction of post-operative RV failure compared to clinical risk scores and manual echo metrics in heart failure patients receiving LVADs?
Observational (n=290)
No
Does an AI-based echocardiography analysis pipeline improve the prediction of post-operative RV failure compared to clinical risk scores and manual echo metrics in heart failure patients receiving LVADs?
An AI-based echocardiography pipeline using pre-operative imaging significantly outperforms contemporary clinical risk scores and manual echocardiographic metrics in predicting post-operative right ventricular failure in LVAD recipients.
In this study, we describe a novel ‘radiomics’ approach to an echocardiography artificial intelligence system that enables the extraction of hundreds of thousands of motion parameters per echocardiography video. We apply this AI system to the clinical problem of predicting post-operative right ventricular failure (RV failure) in heart failure patients receiving implantable circulatory life support systems. Post-operative RV failure is the single largest contributor to short-term mortality in patients with left ventricular assist devices (LVAD); yet predicting which patient is at risk of developing this complication in the pre-operative setting, has remained beyond the abilities of experts in the field. We report results on testing datasets using a standard 10-fold cross validation. The AUC for the AI system trained using the Stanford LVAD dataset was 0.860 (95% CI 0.815-0.905; n = 290 patients) using pre-operative echocardiograms alone. We further show that our system outperforms board certified clinicians equipped with both contemporary risk scores (AUC 0.502 - 0.584) and independently measured echocardiographic metrics (0.519 – 0.598).
No takes yet. Share an insight, caveat, or question.
Shad et al. (2020) conducted an observational in Heart failure requiring left ventricular assist device (LVAD) (n=290). AI echocardiography system (radiomics approach) vs. Clinical risk scores (CRITT and Penn) and manual echocardiographic metrics was evaluated on Prediction of post-operative right ventricular failure (AUC 0.860, 95% CI 0.815-0.905, p=<0.0001). An AI echocardiography system predicted post-operative right ventricular failure with an AUC of 0.860, significantly outperforming contemporary clinical risk scores and manual echocardiographic metrics.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: