EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

A machine learning study of the effect of thrombolysis on outcome at discharge in the UK stroke registry: how does benefit compare with clinical trials?

Kerry Pearn, Michael Allen, Anna Laws, Peter McMeekin iD, Richard Everson, Mark Kelson, Jason Scott iD, Eleanor Kashouris, Joao Delgado iD, Leon Farmer, Lauren Asare, Ajay Bhalla und 1 weitere

European Stroke Journal · 06.07.2026 · 11 (7)

DOI: 10.1093/esj/aakag078 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift European Stroke Journal, online erschienen am 13.07.2026. Verfasst von Kerry Pearn und 12 weiteren Autor:innen. Beteiligte Einrichtung: University of Exeter Medical School, Exeter, United Kingdom. Hauptthemen laut MEDLINE: Machine Learning, Thrombolytic Therapy, Stroke, Ischemic Stroke. Die Arbeit nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Institute for Health and Care Research Applied Research Collaboration South West, National Institute for Health Research Health and Social Care Delivery Research (HSDR) Programme.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Thrombolysis has been shown to reduce disability after acute ischaemic stroke in randomised trials. Our study sought to compare the benefit from thrombolysis observed in a comprehensive national stroke registry with that expected from the clinical trials. Patients and methods Data from a total of 168,347 ischaemic stroke patients who attended one of 118 emergency stroke hospitals in England and Wales from 2016 to 2021 were extracted from the Sentinel Stroke National Audit Programme. We constructed a machine learning model, designed to isolate the effect of thrombolysis, using explainable machine learning (XGBoost with SHapley Additive exPlanations [SHAP]).

Results

Thrombolysis was found to be associated with a statistically significant improvement in the odds of achieving a better outcome (modified Rankin scale [mRS] threshold). Regression analysis predicted a maximum 2.5-fold improvement in odds of achieving mRS 0–1, with a decline to no treatment effect at 5 h 28 min post-onset.

Discussion

Our results confirm a beneficial effect of thrombolysis in a large prospective national stroke registry, and align closely with meta-analyses of clinical trials of thrombolysis both in terms of magnitude of effect and decline over time. This work also demonstrates the potential to apply explainable machine learning to observational data to assist in understanding how clinical trials are implemented in real-world settings.

Conclusions

Thrombolysis, in practice, has the same observed benefit as in the clinical trials.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningThrombolytic TherapyStrokeIschemic StrokeHumansRegistriesFemaleTreatment OutcomeMaleAgedPatient DischargeClinical Trials as TopicMiddle AgedUnited KingdomFibrinolytic AgentsPredictive Learning ModelsAged, 80 and over

Stichwörter der Autor:innen

alteplasehealth service researchischemic strokemachine learningstrokethrombolysis

Substanzen

Fibrinolytic Agents

Autor:innen und Institutionen

  • University of Exeter Medical School, Exeter, United Kingdom.
  • NIHR South West Peninsula Applied Research Collaboration (ARC), Exeter, United Kingdom.
  • University of Northumbria, Newcastle, United Kingdom.
  • University of Exeter, Exeter, United Kingdom.
  • Guy's and St Thomas' NHS Foundation Trust, London, United Kingdom.

ORCID-Profile: Peter McMeekin, Jason Scott, Joao Delgado

Förderung

  • National Institute for Health and Care Research Applied Research Collaboration South West
  • National Institute for Health Research Health and Social Care Delivery Research (HSDR) Programme

Zitieren

APA

Pearn, K., Allen, M., Laws, A., McMeekin, P., Everson, R., Kelson, M., Scott, J., Kashouris, E., Delgado, J., Farmer, L., Asare, L., Bhalla, A., & James, M. (2026). A machine learning study of the effect of thrombolysis on outcome at discharge in the UK stroke registry: how does benefit compare with clinical trials?. European Stroke Journal, 11(7). https://doi.org/10.1093/esj/aakag078

Vancouver

Pearn K, Allen M, Laws A, McMeekin P, Everson R, Kelson M, et al. A machine learning study of the effect of thrombolysis on outcome at discharge in the UK stroke registry: how does benefit compare with clinical trials?. European Stroke Journal. 2026;11(7). doi:10.1093/esj/aakag078

BibTeX
@article{Pearn2026,
  author = {Pearn, Kerry and Allen, Michael and Laws, Anna and McMeekin, Peter and Everson, Richard and Kelson, Mark and Scott, Jason and Kashouris, Eleanor and Delgado, Joao and Farmer, Leon and Asare, Lauren and Bhalla, Ajay and James, Martin},
  title = {A machine learning study of the effect of thrombolysis on outcome at discharge in the UK stroke registry: how does benefit compare with clinical trials?},
  journal = {European Stroke Journal},
  year = {2026},
  volume = {11},
  number = {7},
  doi = {10.1093/esj/aakag078}
}
Kostenlos starten →