Machine Learning for Clinical Outcome Prediction After Transcatheter Aortic Valve Replacement: A Systematic Review and Meta-Analysis of Predictive Performance, Validation, and Clinical Readiness

@article{alizadehasl2026machine,
  title = {{Machine Learning for Clinical Outcome Prediction After Transcatheter Aortic Valve Replacement: A Systematic Review and Meta-Analysis of Predictive Performance, Validation, and Clinical Readiness}},
  author = {Azin Alizadehasl and Elahe Abdi Bastami and Seyedeh Fatemeh Hosseini Jebelli and Delaram Narimani Davani and Alia Bahramnejad and Azam Yalameh Aliabadi and Seyyedeh Maryam Moussavi and Azin Ghaffari and Reza Amani-Beni and Bahar Darouei and Ehsan Amini-Salehi and Seyyed Mohammad Hashemi and Samira Golkar and Hoda Hakimian and Soroush Najdaghi},
  journal = {Journal of clinical medicine},
  year = {2026},
  month = oct,
  doi = {10.3390/jcm15197692},
  url = {https://europepmc.org/article/PMC/PMC13666408},
  note = {CC BY},
}

TY  - JOUR
TI  - Machine Learning for Clinical Outcome Prediction After Transcatheter Aortic Valve Replacement: A Systematic Review and Meta-Analysis of Predictive Performance, Validation, and Clinical Readiness
AU  - Azin Alizadehasl
AU  - Elahe Abdi Bastami
AU  - Seyedeh Fatemeh Hosseini Jebelli
AU  - Delaram Narimani Davani
AU  - Alia Bahramnejad
AU  - Azam Yalameh Aliabadi
AU  - Seyyedeh Maryam Moussavi
AU  - Azin Ghaffari
AU  - Reza Amani-Beni
AU  - Bahar Darouei
AU  - Ehsan Amini-Salehi
AU  - Seyyed Mohammad Hashemi
AU  - Samira Golkar
AU  - Hoda Hakimian
AU  - Soroush Najdaghi
PY  - 2026
DA  - 2026/10/01
JO  - Journal of clinical medicine
DO  - 10.3390/jcm15197692
UR  - https://europepmc.org/article/PMC/PMC13666408
AB  - Background: Machine learning (ML) models are increasingly used to predict adverse outcomes after transcatheter aortic valve replacement (TAVR), but their generalizability and clinical readiness remain uncertain. We evaluated predictive performance across post-TAVR outcomes, emphasizing validation quality, transportability, methodological bias, and clinical utility. Methods: PubMed/MEDLINE, Embase, Scopus, and Web of Science were searched from inception through 6 August 2026 for supervised ML studies reporting out-of-sample performance for clinically relevant post-TAVR outcomes. Overlapping source populations were audited before synthesis. Areas under the receiver operating characteristic curve (AUCs) were pooled on the logit scale using restricted maximum likelihood (REML) random-effects models with modified Hartung–Knapp inference and prediction intervals. Prespecified analyses examined validation maturity, predictor timing, prediction horizon, data architecture, and risk of bias. Within-study dependence was addressed using multilevel meta-regression with bias-reduced cluster-robust variance estimation (CR2); Bayesian analyses complemented the primary synthesis. Results: Sixty-seven full-text reports were included. Twenty independent source/report families contributed to mortality meta-analysis, yielding a pooled AUC of 0.791 (95% confidence interval [CI], 0.732–0.840; I2 = 91.5%; prediction interval, 0.480–0.940). The high heterogeneity and wide prediction interval indicate that this pooled AUC is an average across heterogeneous settings rather than a transportable performance guarantee. Stronger external, temporal, geographic, or inter-centre evaluation showed lower discrimination than internal/resampled evaluation (0.754 vs. 0.814; p = 0.299), while preprocedural models yielded 0.767 versus 0.866 for peri-/postprocedural or mixed models (p = 0.083). High-risk studies showed higher apparent mortality discrimination than low/unclear-risk studies (0.895 vs. 0.747; p for interaction = 0.0009); this observational comparison involved only five high-risk mortality studies and should not be interpreted causally. The Bayesian-adjusted difference was +0.118 AUC units (95% credible interval [CrI], +0.037 to +0.179). Pooled AUCs were 0.760 for permanent pacemaker implantation (PPMI), 0.778 for broader conduction abnormalities, and 0.747 for paravalvular leak (PVL). No algorithm family showed reproducible superiority (p = 0.775). Stronger independent evaluation, calibration/Brier assessment, and decision-curve analysis were reported in only 18/67, 23/67, and 10/67 reports, respectively. Conclusions: ML shows promising post-TAVR discrimination, particularly for mortality, but substantial heterogeneity, limited independent validation, and sparse calibration and decision utility assessment constrain clinical translation. A high AUC alone should not be interpreted as evidence of transportability or clinical usefulness.
SN  - 2077-0383
ER  -