EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access

Beyond Comparing Machine Learning and Logistic Regression in Clinical Prediction Modelling: Shifting from Model Debate to Data Quality

Yanan Hu iD, Xin Zhang iD, Valerie Slavin iD, Yitayeh Belsti iD, Sofonyas Abebaw Tiruneh iD, Emily Callander iD, Joanne Enticott iD

Journal of Medical Internet Research · 05.11.2025 · 27 · e77721

DOI: 10.2196/77721 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Journal of Medical Internet Research, online erschienen am 05.11.2025. Verfasst von Yanan Hu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Monash Centre for Health Research and Implementation, Faculty of Medicine, Nursing and Health Sciences, Monash University, Melbourne, Australia. Hauptthemen laut MEDLINE: Machine Learning, Data Accuracy. Die Arbeit wurde bisher 64-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid uptake of supervised machine learning (ML) in clinical prediction modelling, particularly for binary outcomes based on tabular data, has sparked debate about its comparative advantage over traditional statistical logistic regression. Although ML has demonstrated superiority in unstructured data domains, its performance gains in structured, tabular clinical datasets remain inconsistent and context dependent. This viewpoint synthesizes recent comparative studies and simulation findings to argue that there is no universal best modelling approach. Model performance depends heavily on dataset characteristics (eg, linearity, sample size, number of candidate predictors, minority class proportion) and data quality (eg, completeness, accuracy). Consequently, we argue that efforts to improve data quality, not model complexity, are more likely to enhance the reliability and real-world utility of clinical prediction models.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningData AccuracyLogistic ModelsHumans

Stichwörter der Autor:innen

binary classficationclinical dataclinical prediction modelsdata qualitylogistic regressionmachine learning

Autor:innen und Institutionen

  • Monash Centre for Health Research and Implementation, Faculty of Medicine, Nursing and Health Sciences, Monash University, Melbourne, Australia.
  • Department of Electrical and Computer Systems Engineering, Monash University, Melbourne, Australia.
  • Gold Coast Hospital and Health Service, Gold Coast Hospital, Gold Coast, Australia.
  • School of Nursing and Midwifery, Griffith University, Gold Coast, Australia.
  • School of Nursing and Midwifery, University of Technology Sydney, Sydney, Australia.
  • School of Nursing, Midwifery and Social Work, The University of Queensland, Brisbane, Australia.

ORCID-Profile: Yanan Hu, Xin Zhang, Valerie Slavin, Yitayeh Belsti, Sofonyas Abebaw Tiruneh, Emily Callander, Joanne Enticott

Zitieren

APA

Hu, Y., Zhang, X., Slavin, V., Belsti, Y., Tiruneh, S. A., Callander, E., & Enticott, J. (2025). Beyond Comparing Machine Learning and Logistic Regression in Clinical Prediction Modelling: Shifting from Model Debate to Data Quality. Journal of Medical Internet Research, 27, e77721. https://doi.org/10.2196/77721

Vancouver

Hu Y, Zhang X, Slavin V, Belsti Y, Tiruneh SA, Callander E, et al. Beyond Comparing Machine Learning and Logistic Regression in Clinical Prediction Modelling: Shifting from Model Debate to Data Quality. Journal of Medical Internet Research. 2025;27:e77721. doi:10.2196/77721

BibTeX
@article{Hu2025,
  author = {Hu, Yanan and Zhang, Xin and Slavin, Valerie and Belsti, Yitayeh and Tiruneh, Sofonyas Abebaw and Callander, Emily and Enticott, Joanne},
  title = {Beyond Comparing Machine Learning and Logistic Regression in Clinical Prediction Modelling: Shifting from Model Debate to Data Quality},
  journal = {Journal of Medical Internet Research},
  year = {2025},
  volume = {27},
  pages = {e77721},
  doi = {10.2196/77721}
}
Kostenlos starten →