Early predictive value of prediction models for mortality after transcatheter aortic valve replacement: a systematic review and meta-analysis - Summary - MDSpire
Advertisement
Early predictive value of prediction models for mortality after transcatheter aortic valve replacement: a systematic review and meta-analysis
To systematically evaluate the performance of models for early prediction of mortality risk after TAVR.
Approach:
Search Strategy: PubMed, Web of Science, Embase, and Cochrane Library were systematically searched for studies on predicting mortality risk after TAVR, up to June 2024.
Key Findings:
36 studies with 272,390 patients were included. Concordance indices (C-index) for various models ranged from 0.578 (95% CI: 0.531–0.625) to 0.705 (95% CI: 0.677–0.733). Machine learning models showed higher predictive performance compared to traditional scoring tools.
Interpretation:
Determining the predictive performance of current established risk assessment tools for predicting mortality risk after TAVR is complex.
Limitations:
The review did not include non-English studies.
Exclusion of meta-analyses, reviews, and studies that did not develop complete models.
Conclusion:
Machine learning models appear to be more effective for predicting mortality risk after TAVR, suggesting a need for future research with larger sample sizes.
