Machine learning-based prediction model for cognitive frailty in elderly patients with ischaemic stroke: a prospective cohort study - Takeaways - MDSpire

Machine learning-based prediction model for cognitive frailty in elderly patients with ischaemic stroke: a prospective cohort study

  • By

  • Xuan Chen

  • Linjie Zhou

  • Ying Zhang

  • Tuonan Liu

  • Bo Yan

  • Yang Li

  • Yan Hua

  • June 5, 2026

  • 0 min

Share

  • 1

    Cognitive frailty, characterized by cognitive impairment and physical frailty, is common in older patients after ischaemic stroke.

  • 2

    The study developed a machine learning model to predict cognitive frailty risk at 3 months post-stroke using 26 candidate variables.

  • 3

    Among 402 enrolled patients, 149 (37.1%) developed cognitive frailty within 3 months after ischaemic stroke.

  • 4

    The random forest model showed the best performance with an AUC of 0.889, accuracy of 0.798, and sensitivity of 0.909.

  • 5

    Key predictors of cognitive frailty included stroke severity, age, white matter hyperintensity burden, depression, and social support.

Original Source(s)

Machine learning-based prediction model for cognitive frailty in elderly patients with ischaemic stroke: a prospective cohort study

  • by Xuan Chen, Linjie Zhou, Ying Zhang, Tuonan Liu, Bo Yan, Yang Li, Yan Hua

  • June 5, 2026

Related Content

Impaired pendulum-like mechanics during post-stroke walking: a biomechanical comparison with healthy individuals

Prognostic significance of coagulation factor activity in acute stroke: a retrospective cohort study

Comparing the effects of different electromagnetic stimulation on lower limb motor impairment after stroke: a protocol for systematic review and network meta-analysis