Development and validation of a machine learning model based on multi-source clinical data for predicting the risk of early neurological deterioration in patients with ischemic stroke - Takeaways - MDSpire
Coming Soon: Introducing MDSpire News. Learn more
Conexiant’s news site is now MDSpire News. Learn more

Creation and assessment of a machine learning framework utilizing diverse clinical data to forecast early neurological decline in individuals with ischemic stroke

  • By

  • Yue Li

  • Wei Wang

  • Yilan Wei

  • Jing Han

  • Yuan Shi

  • Quping Ouyang

  • September 15, 2026

Share

  • 1

    The study developed a machine learning model to predict early neurological deterioration (END) in patients with acute ischemic stroke.

  • 2

    A total of 1,151 patients treated for acute ischemic stroke were included in the analysis from January 2021 to December 2024.

  • 3

    Five key predictors for END were identified: ischemic stroke subtype, OCSP classification, age, atrial fibrillation history, and previous stroke history.

  • 4

    The logistic regression model demonstrated AUCs of 0.787 and 0.751 in development and validation cohorts, respectively.

  • 5

    An online tool was created to facilitate early risk stratification for END, supporting personalized clinical management.

Original Source(s)

Related Content