EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitSystematische ÜbersichtOpen Access · CC BY 4.0

Machine Learning for Warfarin Therapy: A Systematic Review

Pavol Fülöp, Štefan Tóth, Tibor Porubän iD, Zuzana Fülöpová, Anna Borovská, Mariana Dvorožňáková

Pharmaceuticals · 14.10.2025 · 18 (10) · 1544

DOI: 10.3390/ph18101544 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Pharmaceuticals, online erschienen am 14.10.2025. Verfasst von Pavol Fülöp und 5 weiteren Autor:innen. Beteiligte Einrichtung: 2nd Department of Cardiology, East Slovak Institute of Cardiovascular Diseases, Faculty of Medicine, Pavol Jozef Šafárik University in Košice, Ondavs…. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: VEGA.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Despite the availability of direct oral anticoagulants, warfarin remains essential for mechanical valves, renal impairment, and resource-limited settings. Traditional dosing achieves therapeutic range in only 55–65% of patients, increasing bleeding and thrombotic complications. This systematic review evaluates the literature on machine learning (ML) approaches for warfarin dose prediction (2022–2025).

Methods

We analysed 14 studies encompassing 122,400 patients across nine countries following PRISMA guidelines. Studies utilizing ML algorithms for warfarin dosing with quantifiable performance metrics were included. Risk of bias was assessed using PROBAST.

Results

Reinforcement learning demonstrated superior performance, achieving an 80.8% excellent responder ratio versus 41.6% for standard practice and 99.5% safety responder ratio versus 83.1%. Support vector machines achieved R2 up to 0.98 in homogeneous populations. Mean absolute error ranged from 0.11 to 1.8 mg/day, consistently outperforming traditional methods. Seven studies included external validation, whilst 78.6% were retrospective designs. Limited implementation studies showed therapeutic INR rates improving from 47.5% to 61.1%. Critically, only three studies (21.4%) reported any safety outcomes, with none adequately powered to detect differences in major bleeding events.

Conclusions

While ML algorithms demonstrate improved dosing accuracy in retrospective analyses, the near-complete absence of adequately powered safety outcome data represents the primary barrier to clinical implementation. Without robust evidence on bleeding, thromboembolism, and mortality, the risk–benefit profile remains unknown. Implementation requires addressing: the predominance of retrospective studies (78.6%), limited prospective validation, restricted geographic diversity (43% from China), absence of African and South American studies, and no new Hispanic population data. Multicentre prospective trials with safety endpoints, population-specific validation, and interpretable models are essential before widespread clinical adoption can be recommended.

Schlagwörter

Stichwörter der Autor:innen

anticoagulationartificial intelligencedose predictionmachine learningsystematic reviewwarfarin

Autor:innen und Institutionen

  • 2nd Department of Cardiology, East Slovak Institute of Cardiovascular Diseases, Faculty of Medicine, Pavol Jozef Šafárik University in Košice, Ondavská 8, 040 11 Košice, Slovakia.
  • Department of Gerontology and Geriatrics, University Hospital of St. Michael, Faculty of Medicine, Pavol Jozef Šafárik University in Košice, Murgašova 1, 040 86 Košice, Slovakia.
  • 1st Department of Cardiology, East Slovak Institute of Cardiovascular Diseases, Faculty of Medicine, Pavol Jozef Šafárik University in Košice, Ondavská 8, 040 11 Košice, Slovakia.
  • First Department of Internal Medicine, Louis Pasteur University Hospital, Faculty of Medicine, Pavol Jozef Šafárik University in Košice, Trieda SNP 1, 040 11 Košice, Slovakia.

ORCID-Profile: Tibor Porubän

Förderung

  • VEGA

Zitieren

APA

Fülöp, P., Tóth, Š., Porubän, T., Fülöpová, Z., Borovská, A., & Dvorožňáková, M. (2025). Machine Learning for Warfarin Therapy: A Systematic Review. Pharmaceuticals, 18(10), 1544. https://doi.org/10.3390/ph18101544

Vancouver

Fülöp P, Tóth Š, Porubän T, Fülöpová Z, Borovská A, Dvorožňáková M. Machine Learning for Warfarin Therapy: A Systematic Review. Pharmaceuticals. 2025;18(10):1544. doi:10.3390/ph18101544

BibTeX
@article{Flp2025,
  author = {Fülöp, Pavol and Tóth, Štefan and Porubän, Tibor and Fülöpová, Zuzana and Borovská, Anna and Dvorožňáková, Mariana},
  title = {Machine Learning for Warfarin Therapy: A Systematic Review},
  journal = {Pharmaceuticals},
  year = {2025},
  volume = {18},
  number = {10},
  pages = {1544},
  doi = {10.3390/ph18101544}
}
Kostenlos starten →