Valvular & structural heart disease
Deep Learning–Enabled Assessment of Right Ventricular Function Improves Prognostication After Transcatheter Edge-to-Edge Repair for Mitral Regurgitation
Authors' conclusion
Deep learning-enabled assessment of RV function using standard 2-dimensional echocardiographic videos can refine the prognostication of patients with severe MR undergoing TEER. Thus, it can be used to screen for patients with RV dysfunction who might benefit from intensified follow-up care.
Study context
- Population
- Patients with severe mitral regurgitation (MR) undergoing transcatheter edge-to-edge repair (TEER) between 2017 and 2023, with good-quality 2-dimensional apical 4-chamber view videos from preprocedural transthoracic echocardiographypatients with good-quality 2-dimensional apical 4-chamber view videos
- Participants
- 1,154 patients
- Exposure
- reduced right ventricular (RV) function vs preserved RV function
- reduced RV functionn = 723
- preserved RV functionn = 431reference
Main finding
As reported in the abstract
Survival · 1 year after TEER
Survival at 1 year after TEER
84.7%
Observational data: associations, not effects.
Further findings
| Outcome | Reduced RV function | Preserved RV function | Hazard ratio (95% CI) | P value | |
|---|---|---|---|---|---|
| 1-year survival (Kaplan-Meier) and 1-year mortality | 1-year survival rate 80.3% (95% CI 77.4%–83.3%) | 1-year survival rate 92.1% (95% CI 89.5%–94.7%) | 2.67 (1.82–3.90) | P < 0.001 | |
| 0.20.5125Hazard ratio (log scale) |
| Outcome | Estimate | P value |
|---|---|---|
| Prediction of 1-year mortality after TEER · predicted RVEF superior | P = 0.029 |
- Prediction of 1-year mortality after TEER: predicted RV ejection fraction (RVEF) area under the curve 0.687
- Prediction of 1-year mortality after TEER: tricuspid annular plane systolic excursion area under the curve 0.625
Range of predicted RVEF values
- Predicted RVEF range
- 26.6% to 64.0%
Correlation of predicted RVEF with tricuspid annular plane systolic excursion
- Pearson R
- 0.33
- P
- P < 0.001
- Correlated only modestly
Original publication
Deep Learning–Enabled Assessment of Right Ventricular Function Improves Prognostication After Transcatheter Edge-to-Edge Repair for Mitral Regurgitation. Circ Cardiovasc Imaging. Published 21 January 2025. doi:10.
Summarised from the published abstract; every number is checked against it