Valvular & structural heart diseaseCohort study
Decoding the complexity of tricuspid regurgitation prognostic drivers using explainable artificial intelligence
- large prospective registry
- supervised explainable artificial intelligence (EAI) models
- proportional hazards models
Authors' conclusion
EAI ranked mortality predictors in TR, highlighting patient factors, haemodynamics, TR-specific measures, and left-ventricular function. Among TR-specific measures, EROA and TRIScore were most prognostic. Recognizing their impact can refine risk stratification, guide intervention timing, and inform long-term management.
Study context
- Population
- Patients with native tricuspid regurgitation (TR) across the full severity spectrum, with detailed clinical evaluation and quantitative Doppler-echocardiographypatients, 2676 deaths during 3.8 ± 4.6 years of follow-up
- Participants
- 9,761 patients
Main finding
As reported in the abstract
Long-term all-cause mortality · 3.8 ± 4.6 years of follow-up
Deaths
2676
Observational data: associations, not effects.
Further findings
Ranked prognostic determinants of survival (EAI)
- Prognostic determinants identified and ranked
- 20
- Haemodynamic measures, led by elevated pulmonary-artery systolic and right-atrial pressures, were strongest, followed by age and comorbidity
- TR-related variables ranked next, led by right ventricular dysfunction and effective regurgitant orifice area (EROA), which outperformed integrative TR grade and TRIScore
- Left-ventricular parameters were less influential
Non-linear effects and interactions
- Higher EROA-related risk with elevated pulmonary pressures or lower TRIScore
- P < 0.03
- Non-linear effects, including those involving ejection fraction
- both P < 0.03
EROA as TR severity marker (proportional hazards models)
- EROA strongest TR severity marker
- P < 0.0001
- Excess mortality beginning at
- 40 mm²
- Increasing further at
- 60 mm²
Baseline characteristics
- Mean age
- 73 ± 15 years
- Women
- 56.9%
- EROA
- 40 (30-56) mm²
- Regurgitant volume
- 39 (29-53) mL/beat
- Severe TR
- 42%
Original publication
Decoding the complexity of tricuspid regurgitation prognostic drivers using explainable artificial intelligence. Eur Heart J Cardiovasc Imaging. Published 27 June 2026. doi:10.1093/ehjci/jeag168
Summarised from the published abstract; every number is checked against it