EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Prediction of cardiovascular risk using machine-learning methods. Sex-specific differences

Sara Castel-Feced, Isabel Aguilar-Palacio, Sara Malo, Juan González-García, Lina Maldonado, María José Rabanaque-Hernández

Frontiers in Cardiovascular Medicine · 19.06.2025 · 12

DOI: 10.3389/fcvm.2025.1579947 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Cardiovascular Medicine, online erschienen am 19.06.2025. Verfasst von Sara Castel-Feced und 5 weiteren Autor:innen. Beteiligte Einrichtung: Fundación Instituto de Investigación Sanitaria Aragón (IIS Aragón), Zaragoza, Spain. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Machine learning (ML) algorithms offer some advantages over traditional scoring systems to assess the influence of cardiovascular risk factors (CVRFs) on the risk of major cardiovascular event (MACE), and could be useful in clinical practice. These algorithms can also be trained using a growing body of real world data (RWD). The aim of the study was to evaluate the MACE risk applying the XGBoost and Random Forest ML algorithms to RWD, stratifying the study population by sex, comparing the outcomes of these two algorithms.

Methods

The follow-up period of the study was from 2018 to 2020. For each algorithm, 3 models were generated, including age and different combinations of three groups of variables: blood test and blood pressure measurements; CVRFs; and medication adherence.

Results

In this study, 52,393 subjects were included, of whom 581 suffered a MACE. The incidence of MACE was 1% in women and 1.3% in men. The most prevalent CVRF was hypertension, followed by hypercholesterolaemia in both sexes. Adherence to treatment was highest for antihypertensives and lowest for antidiabetics. In all models age was the greatest relative contributor to the risk of MACE, followed by adherence to antidiabetics. Adherence to treatment proved to be an important variable in the risk of having a MACE. Moreover, similar performance was found for RF and XGBoost algorithms.

Conclusion

These findings support the use of ML to assess cardiovascular risk and guide personalized prevention strategies in primary care settings.

Schlagwörter

Stichwörter der Autor:innen

XGBoostadherence to treatmentcardiovascular diseasemachine learningrandom forest

Autor:innen und Institutionen

  • Fundación Instituto de Investigación Sanitaria Aragón (IIS Aragón), Zaragoza, Spain.
  • Department of Employment, Science and Universities of the Government of Aragón (Spain), GRISSA Research Group, Zaragoza, Spain.
  • Department of Employment, Science and Universities of the Government of Aragón (Spain), Institute for Health Research Aragón (IIS Aragón), Zaragoza, Spain.
  • Network for Research on Chronicity, Primary Care, Health Promotion (RICAPPS), ISCIII, Madrid, Spain.
  • Department of Microbiology, Pediatrics, Radiology, and Public Health, University of Zaragoza, Zaragoza, Spain.
  • Biocomputing Unit, Data Science for Health Services and Policy Research Aragon Health Sciences Institute (IACS), Zaragoza, Spain.

Zitieren

APA

Castel-Feced, S., Aguilar-Palacio, I., Malo, S., González-García, J., Maldonado, L., & Rabanaque-Hernández, M. J. (2025). Prediction of cardiovascular risk using machine-learning methods. Sex-specific differences. Frontiers in Cardiovascular Medicine, 12. https://doi.org/10.3389/fcvm.2025.1579947

Vancouver

Castel-Feced S, Aguilar-Palacio I, Malo S, González-García J, Maldonado L, Rabanaque-Hernández MJ. Prediction of cardiovascular risk using machine-learning methods. Sex-specific differences. Frontiers in Cardiovascular Medicine. 2025;12. doi:10.3389/fcvm.2025.1579947

BibTeX
@article{CastelFeced2025,
  author = {Castel-Feced, Sara and Aguilar-Palacio, Isabel and Malo, Sara and González-García, Juan and Maldonado, Lina and Rabanaque-Hernández, María José},
  title = {Prediction of cardiovascular risk using machine-learning methods. Sex-specific differences},
  journal = {Frontiers in Cardiovascular Medicine},
  year = {2025},
  volume = {12},
  doi = {10.3389/fcvm.2025.1579947}
}
Kostenlos starten →