Related Experiment Video
Updated: May 5, 2026

Assessment of Right Ventricular Structure and Function in Mouse Model of Pulmonary Artery Constriction by Transthoracic Echocardiography
Published on: February 3, 2014
Deep Learning-Enabled Assessment of Right Ventricular Function Improves Prognostication After Transcatheter
Mark Lachmann1,2, Vera Fortmeier3, Lukas Stolz4
1First Department of Medicine, Klinikum Rechts der Isar, Technical University of Munich, Munich, Germany (M.L., A.H., E.R., J.T., K.-L.L.).
Deep learning accurately predicts right ventricular ejection fraction (RVEF) from echocardiograms, improving prognostication for patients undergoing transcatheter edge-to-edge repair (TEER). This AI-driven RVEF assessment is superior to traditional methods for predicting mortality risk after TEER.
Area of Science:
- Cardiology
- Artificial Intelligence in Medicine
- Echocardiography
Background:
- Right ventricular (RV) function is a critical prognostic indicator in severe mitral regurgitation (MR) patients undergoing transcatheter edge-to-edge repair (TEER).
- Tricuspid annular plane systolic excursion (TAPSE) is the conventional echocardiographic measure for RV function.
- A novel deep learning (DL) model can predict RV ejection fraction (RVEF) from 2D echocardiographic videos with high accuracy.
Purpose of the Study:
- To evaluate the prognostic value of DL-predicted RVEF in patients with severe MR undergoing TEER.
- To compare the predictive performance of DL-RVEF with TAPSE for 1-year mortality.
Main Methods:
- A multicenter registry study analyzed 1154 patients with severe MR undergoing TEER.
- Preprocedural 2D transthoracic echocardiographic videos were processed using a validated DL model to predict RVEF.
- Associations between predicted RVEF and 1-year mortality were assessed.
Main Results:
- DL-predicted RVEF showed modest correlation with TAPSE (R=0.33).
- DL-predicted RVEF was superior to TAPSE in predicting 1-year mortality (AUC 0.687 vs. 0.625, P=0.029).
- Patients with reduced predicted RVEF (<45%) had significantly worse 1-year survival rates (80.3%) compared to those with preserved RVEF (92.1%; HR 2.67, P<0.001).
Conclusions:
- DL-enabled RVEF assessment refines prognostication in severe MR patients undergoing TEER.
- This AI approach can identify patients with RV dysfunction who may benefit from closer monitoring.
- DL-predicted RVEF offers a valuable tool for risk stratification in this patient population.
Related Concept Videos
Mitral Valve Prolapse II: Assessment and Management
Mitral Regurgitation I: Introduction
Mitral Regurgitation II: Clinical Features and Diagnostic Tests
Mitral Regurgitation III: Medical Management
Mitral Regurgitation IV: Nursing Management
Mitral Stenosis II: Clinical features and Diagnostic Tests

