Predicting Outcomes in Patients With Tricuspid Regurgitation Undergoing Transcatheter Edge-to-Edge Repair Using an...

Area of Science:

• Cardiovascular Medicine
• Medical Artificial Intelligence
• Interventional Cardiology

Background:

• Accurate risk stratification is crucial for selecting patients for tricuspid valve transcatheter edge-to-edge repair (T-TEER).
• Severe tricuspid regurgitation necessitates careful patient selection for T-TEER.

Purpose of the Study:

• To develop and validate an artificial intelligence (AI)-driven risk score, the EuroTR score.
• To predict 1-year mortality in patients undergoing T-TEER.

Main Methods:

• Utilized data from the EuroTR registry (1,225 derivation, 601 validation cohorts).
• Trained an extreme gradient boosting algorithm on 18 clinical, laboratory, echocardiographic, and hemodynamic parameters.
• Independently validated the AI score against established risk models.

Main Results:

• The EuroTR score effectively stratified patients by 1-year mortality risk after T-TEER.
• Outperformed existing scores like EuroScore and TRI-SCORE in validation.
• Demonstrated strong predictive performance for mortality and a combined endpoint of adverse outcomes (C-index = 0.741).

Conclusions:

• The EuroTR score is an easy-to-use, validated tool for T-TEER risk stratification.
• Facilitates personalized treatment, clinical trial design, and shared decision-making.
• Optimizes patient selection for T-TEER procedures.