{ "abstract": "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.", "abstract_shown": true, "affiliations": [ "Cardio-Oncology Research Center, Rajaie Cardiovascular Institute, Tehran 1995614331, Iran", "Neuroscience Research Center, Isfahan University of Medical Sciences, Isfahan 81746-73461, Iran", "School of Medicine and Dentistry, Griffith University, Queensland 4101, Australia", "Cardiovascular Research Center, Rajaie Cardiovascular Institute, Tehran 1996114151, Iran", "Heart Failure Research Center, Cardiovascular Research Institute, Isfahan University of Medical Sciences, Isfahan 81589-87944, Iran", "Gastrointestinal and Liver Diseases Research Center, Guilan University of Medical Sciences, Rasht 41625, Iran", "Cardiovascular Research Center, Hormozgan University of Medical Sciences, Bandar Abbas 7916193145, Iran", "Clinical Research Development Center, Najafabad Branch, Islamic Azad University, Najafabad 85135, Iran" ], "article_type": "review article", "arxiv": null, "author_total": 15, "authors": [ { "affs": [ 0 ], "name": "Azin Alizadehasl" }, { "affs": [ 1 ], "name": "Elahe Abdi Bastami" }, { "affs": [ 0 ], "name": "Seyedeh Fatemeh Hosseini Jebelli" }, { "affs": [ 2 ], "name": "Delaram Narimani Davani" }, { "affs": [ 0 ], "name": "Alia Bahramnejad" }, { "affs": [ 0 ], "name": "Azam Yalameh Aliabadi" }, { "affs": [ 0 ], "name": "Seyyedeh Maryam Moussavi" }, { "affs": [ 3 ], "name": "Azin Ghaffari" }, { "affs": [ 4 ], "name": "Reza Amani-Beni" }, { "affs": [ 4 ], "name": "Bahar Darouei" }, { "affs": [ 5 ], "name": "Ehsan Amini-Salehi" }, { "affs": [ 6 ], "name": "Seyyed Mohammad Hashemi" }, { "affs": [ 7 ], "name": "Samira Golkar" }, { "affs": [ 0 ], "name": "Hoda Hakimian" }, { "affs": [ 2 ], "name": "Soroush Najdaghi", "orcid": "0009-0001-4555-5718" } ], "bibtex": "https://research.draconitic.com/paper/as8awvmajne4m.bib", "cited_by": 0, "doi": "10.3390/jcm15197692", "fulltext_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13666408/?tool=EBI", "id": "as8awvmajne4m", "issns": [ "2077-0383" ], "landing_url": "https://europepmc.org/article/PMC/PMC13666408", "language": "eng", "licence": "CC-BY", "licence_label": "CC BY", "licence_source": "article", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "metadata_licence": null, "native_subjects": [ [ "openalex", "2705|Cardiac Valve Diseases and Treatments" ] ], "openalex": "W7220359763", "pdf_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13666408/pdf/?tool=EBI", "pmcid": "PMC13666408", "pmid": null, "published": "2026-10-01", "publisher": "MDPI AG", "ris": "https://research.draconitic.com/paper/as8awvmajne4m.ris", "sources": [ { "first_seen": "2026-10-30T12:17:31Z", "native_id": "PMC:PMC13666408", "source": "europepmc", "url": "https://europepmc.org/article/PMC/PMC13666408" }, { "first_seen": "2026-10-30T12:20:00Z", "native_id": "10.3390/jcm15197692", "source": "crossref", "url": "https://www.mdpi.com/2077-0383/15/19/7692" } ], "subjects": [ { "field": "medicine", "origin": "openalex:2705|Cardiac Valve Diseases and Treatments", "subfield": "cardiovascular" } ], "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", "title_text": "Machine Learning for Clinical Outcome Prediction After Transcatheter Aortic Valve Replacement: A Systematic Review and Meta-Analysis of Predictive Performance, Validation, and Clinical Readiness", "type": "peer-reviewed", "updated_at": "2026-10-30T12:20:00Z", "url": "https://research.draconitic.com/paper/as8awvmajne4m", "venue": "Journal of clinical medicine", "versions": [] }