Valvular & structural heart disease
A streamlined, machine learning-derived approach to risk-stratification in heart failure patients with secondary tricuspid regurgitation
Authors' conclusion
This study presents a streamlined, machine learning-derived and internally validated approach to risk-stratification in patients with moderate and severe sTR, that adds important prognostic information to aid clinical-decision-making.
Study context
- Population
- HF patients (preserved, mid-range and reduced EF) with moderate or severe secondary tricuspid regurgitation
- Participants
- 3,359 vs 1,509
- Exposure
- 4 or 5 adverse features vs fewer adverse features
- Moderate secondary tricuspid regurgitation (sTR)n = 3,359
- Severe sTRn = 1,509
- Outcome
- All-cause mortality
Methodological detailsmachine learning (random survival forest), internally validated
- Machine learning (random survival forest)
- Internally validated
Main finding
As reported in the abstract
All-cause mortality, 4 or 5 adverse features
4 or 5 adverse featuresHazard ratio (95% CI)P value
Moderate sTR
4.81(3.56–6.50)
P < 0.001Severe sTR
5.33(3.28–8.66)
P < 0.001Observational data: associations, not effects.
Original publication
A streamlined, machine learning-derived approach to risk-stratification in heart failure patients with secondary tricuspid regurgitation. Eur Heart J Cardiovasc Imaging. Published 10 February 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →