Hybrid machine learning for real-time prediction of edema trajectory in large middle cerebral artery stroke.

Journal: NPJ digital medicine
Published Date: May 17, 2025

Abstract

In treating malignant cerebral edema after a large middle cerebral artery stroke, clinicians need quantitative tools for real-time risk assessment. Existing predictive models typically estimate risk at one, early time point, failing to account for dynamic variables. To address this, we developed Hybrid Ensemble Learning Models for Edema Trajectory (HELMET) to predict midline shift severity, an established indicator of malignant edema, over 8-h and 24-h windows. The HELMET models were trained on retrospective data from 623 patients and validated on 63 patients from a different hospital system, achieving mean areas under the receiver operating characteristic curve of 96.6% and 92.5%, respectively. By integrating transformer-based large language models with supervised ensemble learning, HELMET demonstrates the value of combining clinician expertise with multimodal health records in assessing patient risk. Our approach provides a framework for accurate, real-time estimation of dynamic clinical targets using human-curated and algorithm-derived inputs.

Authors

  • Ethan Phillips
    University of Oxford, Oxford, UK.
  • Odhran O'Donoghue
    University of Oxford, Oxford, UK.
  • Yumeng Zhang
    Minimally Invasive Tumor Therapy Center, Beijing Hospital, Peking Union Medical College, Beijing, China.
  • Panos Tsimpos
    Massachusetts Institute of Technology, Cambridge, MA, USA.
  • Leigh Ann Mallinger
    Boston Medical Center, United States. Electronic address: leigh.mallinger@bmc.org.
  • Stefanos Chatzidakis
    Brigham & Women's Hospital, Department of Neurology, Boston, MA, USA.
  • Jack Pohlmann
    Boston Medical Center, Department of Neurology, Boston, MA, USA.
  • Yili Du
    Boston University School of Public Health, Boston, MA, USA.
  • Ivy Kim
    Boston Medical Center, Department of Neurology, Boston, MA, USA.
  • Jonathan Song
    Boston University Chobanian & Avedisian School of Medicine, Boston, MA, USA.
  • Benjamin Brush
    NYU Langone Hospital, New York, NY, USA.
  • Stelios Smirnakis
    Harvard Medical School, Boston, Massachusetts, United States of America.
  • Charlene J Ong
    Boston Medical Center, United States; Boston University Chobanian and Avedisian School of Medicine, United States. Electronic address: cjong@bu.edu.
  • Agni Orfanoudaki
    Operations Research Center, Massachusetts Institute of Technology, Cambridge, Massachusetts, United States of America.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals