Key result
Machine learning models outperform traditional risk tools in predicting mortality after TAVR.
Why the study?
Early identification of mortality risk after TAVR is challenging, and no systematic review had evaluated the effectiveness of various prediction models in predicting mortality risk.
Do machine learning models improve the prediction of mortality risk after TAVR compared to traditional scoring systems?
Meta-Analysis (n=272,390)
Do machine learning models improve the prediction of mortality risk after TAVR compared to traditional scoring systems?
Machine learning models demonstrate superior predictive performance for mortality after TAVR compared to traditional risk assessment tools like the STS and ACC TVT models.
Answers are grounded in this paper and cite their sources.
EuroSCORE shows limited discrimination for post-TAVR mortality; challenges routine clinical use and extends need for TAVR-specific models.
Background Transcatheter aortic valve replacement (TAVR) is increasingly used due to the rising incidence of aortic stenosis (AS). Early identification of mortality risk after TAVR is challenging. Although various prediction models have been developed, no systematic review has evaluated their effectiveness in predicting mortality risk. Therefore, this study aimed to systematically evaluate the performance of models for early prediction of mortality risk after TAVR, so as to provide evidence-based support for the future development or updating of risk assessment tools. Methods Databases (PubMed, Web of Science, Embase, and Cochrane Library) were systematically searched for studies on tools for predicting the risk of mortality after TAVR, up to June 2024. PROBAST was used to assess the risk of bias in the included studies. A subgroup analysis was conducted based on different time points. Results This systematic review included 36 studies with 272,390 patients receiving TAVR and 6 major scoring tools encompassing 23 new machine learning models. The meta-analysis showed that the concordance index (C-index) was 0.610 (95% CI: 0.588–0.632) for European System for Cardiac Operative Risk Evaluation I (EuroSCORE I), 0.615 (95% CI: 0.588–0.643) for EuroSCORE II, 0.578 (95% CI: 0.531–0.625) for French Aortic National CoreValve and Edwards II (France II), 0.594 (95% CI: 0.554–0.633) for the OBSERVANT score, 0.648 (95% CI: 0.622–0.674) for the Society of Thoracic Surgeons (STS) risk model, 0.632 (95% CI: 0.616–0.648) for the American College of Cardiology Transcatheter Valve Therapy (ACC TVT) risk model, and 0.705 (95% CI: 0.677–0.733) for summarized machine learning models. Conclusion Determining the predictive performance of current established risk assessment tools for predicting the risk of modality after TAVR is challenging. Machine learning models seem to be more effective. Therefore, future research should include more subjects to develop more accurate models. Systematic Review Registration https://www.crd.york.ac.uk/PROSPERO/ , identifier CRD42023485237.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2026) conducted a meta-analysis in Aortic stenosis requiring transcatheter aortic valve replacement (TAVR) (n=272,390). Machine learning prediction models vs. Traditional scoring systems (e.g., STS risk model, EuroSCORE) was evaluated on Concordance index (C-index) for predicting mortality (C-index 0.705, 95% CI 0.677-0.733). Machine learning models demonstrated better predictive performance for mortality after transcatheter aortic valve replacement compared to traditional established risk assessment tools.
Synapse has enriched 10 related papers. Consider them for comparative context: