The Journal of thoracic and cardiovascular surgery
-
J. Thorac. Cardiovasc. Surg. · May 2024
Restricted Cusp Motion in Newly Implanted Tricuspid Bioprostheses: Incidence, Predictors, and Impact on Survival.
To investigate the occurrence of restricted cusp motion (RCM) at the time of bioprosthetic tricuspid valve replacement (TVR) and analyze associated risk factors and outcomes. ⋯ This study revealed a high incidence of RCM in bioprosthetic valves in the tricuspid position detected shortly postimplantation, which was associated with increased late mortality. To reduce the probability of RCM, it is important to select the appropriate prosthesis model and size, particularly in small patients.
-
J. Thorac. Cardiovasc. Surg. · May 2024
Validation of the HeartMate 3 survival risk score in a large left ventricular assist device center.
The HeartMate 3 survival risk score was recently validated in the Multicenter study Of MagLev Technology in Patients Undergoing Mechanical Circulatory Support Therapy with HeartMate 3 to predict patient-specific survival in HeartMate 3 left ventricular assist device candidates. The HeartMate 3 survival risk score stratifies individuals into tertiles according to survival probability. ⋯ The unadjusted HeartMate 3 survival risk score was associated with postimplant survival in patients outside of the Multicenter study Of MagLev Technology in Patients Undergoing Mechanical Circulatory Support Therapy with HeartMate 3 but did not remain an independent predictor after adjusting for ischemic etiology and severe diabetes. The HeartMate 3 survival risk score was able to identify patients at high survival using a binary cutoff, but we were unable to demonstrate its discriminatory ability among the previously published risk tertiles.
-
J. Thorac. Cardiovasc. Surg. · May 2024
Machine-Learning Approaches for Risk Prediction in Transcatheter Aortic Valve Implantation: Systematic Review and Meta-Analysis.
With the expanding integration of artificial intelligence (AI) and machine learning (ML) into the structural heart domain, numerous ML models have emerged for the prediction of adverse outcomes after transcatheter aortic valve implantation (TAVI). We aim to identify, describe, and critically appraise ML prediction models for adverse outcomes after TAVI. Key objectives consisted in summarizing model performance, evaluating adherence to reporting guidelines, and transparency. ⋯ ML models for TAVI outcomes exhibit adequate-to-excellent performance, suggesting potential clinical utility. We identified concerns in methodology and transparency, emphasizing the need for improved scientific reporting standards.