Traditional statistics versus machine learning in clinical registries: A pragmatic workflow for matching methods to data and clinical questions
SA Heart · 2026 · 26 (2)
DOI: 10.24170/26-2-8319 ↗Kurz gefasst
Fachartikel in der Zeitschrift SA Heart, 2026. Verfasst von A. Wentzel und 2 weiteren Autor:innen.
Abstract (Originalsprache)
This piece discusses the importance of data type, identification, and organisation for machine learning (ML) and neural network (NN) development, and the applicability of ML for statistical analysis in large clinical and physiological datasets, such as the South African Heart Association Registry (SHARE). Core outcomes/key lessons To enable clinicians and researchers to: Systematically assess their clinical dataset (registry data, e.g. SHARE) for variable types, dimensionality, sample size, missingness, and event rates. Understand when traditional statistical methods are sufficient, when regularised regression is preferable, and when more complex ML approaches are justified. Recognise common pitfalls (overfitting, multicollinearity, data leakage, mis-specified outcomes), and how to avoid them in both “classic” and ML settings. Apply a staged workflow to their own data, using the SHARE-transcatheter aortic valve implantation (TAVI) registry as an illustrative case.
Zitieren
APA
Wentzel, A., Schaafsma, E., & Blignaut, B. (2026). Traditional statistics versus machine learning in clinical registries: A pragmatic workflow for matching methods to data and clinical questions. SA Heart, 26(2). https://doi.org/10.24170/26-2-8319
Vancouver
Wentzel A, Schaafsma E, Blignaut B. Traditional statistics versus machine learning in clinical registries: A pragmatic workflow for matching methods to data and clinical questions. SA Heart. 2026;26(2). doi:10.24170/26-2-8319
BibTeX
@article{Wentzel2026,
author = {Wentzel, A. and Schaafsma, E. and Blignaut, B.},
title = {Traditional statistics versus machine learning in clinical registries: A pragmatic workflow for matching methods to data and clinical questions},
journal = {SA Heart},
year = {2026},
volume = {26},
number = {2},
doi = {10.24170/26-2-8319}
}
EUVIMED