Deep Learning Phenotyping of Tricuspid Regurgitation for Automated High Throughput Assessment of Transthoracic Echocardiography

Abstract

AbstractBackground and AimsDiagnosis of tricuspid regurgitation (TR) requires careful expert evaluation. This study developed an automated deep learning pipeline for assessing TR from transthoracic echocardiography.MethodsAn automated deep learning workflow was developed using 47,312 studies (2,079,898 videos) from Cedars-Sinai Medical Center (CSMC) between 2011 and 2021. The pipeline was tested on a temporally distinct test set of 2,462 studies (108,138 videos) obtained in 2022 at CSMC and a geographically distinct cohort of 5,549 studies (278,377 videos) from Stanford Healthcare (SHC).ResultsIn the CSMC test dataset, the view classifier demonstrated an AUC of 1.000 (0.999 – 1.000) and identified at least one A4C video with colour Doppler across the tricuspid valve in 2,410 of 2,462 studies with a sensitivity of 0.975 (0.968-0.982) and a specificity of 1.000 (1.00-1.000). In the CSMC test cohort, moderate-or-severe TR was detected with an AUC of 0.928 (0.913 - 0.943) and severe TR was detected with an AUC of 0.956 (0.940 - 0.969). In the SHC cohort, the view classifier correctly identified at least one TR colour Doppler video in 5,268 of the 5,549 studies, resulting in an AUC of 0.999 (0.998 – 0.999), a sensitivity of 0.949 (0.944 - 0.955) and specificity of 0.999 (0.999 – 0.999). The AI model detected moderate-or-severe TR with an AUC of 0.951 (0.938 - 0.962) and severe TR with an AUC of 0.980 (0.966 - 0.988).ConclusionsWe developed an automated pipeline to identify clinically significant TR with excellent performance. This approach carries potential for automated TR detection and stratification for surveillance and screening.Structured Graphical AbstractComputer Vision Based Tricuspid Regurgitation (TR) Detection: An automated deep learning pipeline was trained to stratify tricuspid regurgitation severity using large-scale data in the form of A4C TTE videos with colour Doppler across the tricuspid valve. The pipeline generalized across two geographically distinct test sets from CSMC and SHC, demonstrating the pipeline’s ability to detect clinically significant TR using single-view TTE videos with Doppler information. These results open the door to potential TR point-of-care screening.Key QuestionCan an automated deep learning model assess tricuspid regurgitation severity from echocardiography?Key FindingWe developed and validated an automated tricuspid regurgitation detection algorithm pipeline across two healthcare systems with high volume echocardiography labs. The algorithm correctly identifies apical-4-chamber view videos with colour Doppler across the tricuspid valve and grades clinically significant TR with strong agreement to expert clinical readers.Take Home messageA deep learning pipeline could automate TR screening, facilitating reproducible accurate assessment of TR severity, allowing rapid triage or re-review and expand access in low-resource or primary care settings.