EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Residual risk prediction in anticoagulated patients with atrial fibrillation using machine learning: A report from the GLORIA‐AF registry phase II/III

Yang Liu, Yang Chen iD, Ivan Olier iD, Sandra Ortega-Martorell iD, Bi Huang, Hironori Ishiguchi, Ho Man Lam iD, Kui Hong, Menno V Huisman, Gregory Y H Lip, GLORIA‐AF Investigators

European Journal of Clinical Investigation · 2025

DOI: 10.1111/eci.14371 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Journal of Clinical Investigation, 2025. Verfasst von Yang Liu und 10 weiteren Autor:innen. Beteiligte Einrichtung: Liverpool Centre for Cardiovascular Science at University of Liverpool, Liverpool John Moores University, and Liverpool Heart & Chest Hospital, Liver…. Hauptthemen laut MEDLINE: Atrial Fibrillation, Machine Learning, Anticoagulants, Thromboembolism. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Nanchang University Abroad Scholarship for Dr Yang Liu, Boehringer Ingelheim GmbH support for the GLORIA-AF registry.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Although oral anticoagulation decreases the risk of thromboembolism in patients with atrial fibrillation (AF), a residual risk of thrombotic events still exists. This study aimed to construct machine learning (ML) models to predict the residual risk in these patients.

Methods

Patients with newly diagnosed non‐valvular AF were collected from the Global Registry on Long‐Term Oral Anti‐Thrombotic Treatment in Patients with Atrial Fibrillation (GLORIA‐AF) registry. To predict the residual risk of the composite outcome of thrombotic events (defined as ischemic stroke, systemic embolism, transient ischemic attack and myocardial infarction), we constructed four prediction models using the logistic regression (LR), random forest, light gradient boosting machine and extreme gradient boosting machine ML algorithms. Performance was mainly evaluated by area under the receiver‐operating characteristic curve (AUC), g‐means and F1 scores. Feature importance was evaluated by SHapley Additive exPlanations.

Results

15,829 AF patients (70.33 ± 9.94 years old, 55% male) taking oral anticoagulation were included in our study, and 641 (4.0%) had residual risk, sustaining thrombotic events. In the test set, LR had the best performance with higher AUC trend of 0.712. RF has highest g‐means of 0.295 and F1 score of 0.249. This was superior when compared with the CHA 2 DS 2 ‐VA score (AUC 0.698) and 2MACE score (AUC 0.696). Age, history of TE or MI, OAC discontinuation, eGFR and sex were identified as the top five factors associated with residual risk.

Conclusion

ML algorithms can improve the prediction of residual risk of anticoagulated AF patients compared to clinical risk factor‐based scores.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Atrial FibrillationMachine LearningAnticoagulantsThromboembolismThrombosisHumansMaleFemaleAgedRegistriesRisk AssessmentMiddle AgedIschemic Attack, TransientMyocardial InfarctionLogistic ModelsROC CurveIschemic StrokeAged, 80 and overRisk FactorsAdministration, OralStrokeAlgorithmsArea Under Curve

Stichwörter der Autor:innen

atrial fibrillationmachine learningoral anticoagulantresidual risk

Substanzen

Anticoagulants

Autor:innen und Institutionen

  • Liverpool Centre for Cardiovascular Science at University of Liverpool, Liverpool John Moores University, and Liverpool Heart & Chest Hospital, Liverpool, UK.
  • Department of Cardiovascular Medicine, the Second Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, Jiangxi, China.
  • Data Science Research Centre, Liverpool John Moores University, Liverpool, UK.
  • Department of Cardiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China.
  • Division of Cardiology, Department of Medicine and Clinical Science, Yamaguchi University Graduate School of Medicine, Ube, Japan.
  • Department of Genetic Medicine, the Second Affiliated Hospital of Nanchang University, Nanchang, Jiangxi, China.

ORCID-Profile: Yang Chen, Ivan Olier, Sandra Ortega-Martorell, Ho Man Lam

Förderung

  • Nanchang University Abroad Scholarship for Dr Yang Liu
  • Boehringer Ingelheim GmbH support for the GLORIA-AF registry

Zitieren

APA

Liu, Y., Chen, Y., Olier, I., Ortega-Martorell, S., Huang, B., Ishiguchi, H., Lam, H. M., Hong, K., Huisman, M. V., Lip, G. Y. H., & GLORIA‐AF Investigators (2025). Residual risk prediction in anticoagulated patients with atrial fibrillation using machine learning: A report from the GLORIA‐AF registry phase II/III. European Journal of Clinical Investigation. https://doi.org/10.1111/eci.14371

Vancouver

Liu Y, Chen Y, Olier I, Ortega-Martorell S, Huang B, Ishiguchi H, et al. Residual risk prediction in anticoagulated patients with atrial fibrillation using machine learning: A report from the GLORIA‐AF registry phase II/III. European Journal of Clinical Investigation. 2025. doi:10.1111/eci.14371

BibTeX
@article{Liu2025,
  author = {Liu, Yang and Chen, Yang and Olier, Ivan and Ortega-Martorell, Sandra and Huang, Bi and Ishiguchi, Hironori and Lam, Ho Man and Hong, Kui and Huisman, Menno V and Lip, Gregory Y H and GLORIA‐AF Investigators, GLORIA‐AF Investigators},
  title = {Residual risk prediction in anticoagulated patients with atrial fibrillation using machine learning: A report from the GLORIA‐AF registry phase II/III},
  journal = {European Journal of Clinical Investigation},
  year = {2025},
  doi = {10.1111/eci.14371}
}
Kostenlos starten →