Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Dynamic Prediction of 3-Month Recurrence After First-Ever Ischemic Stroke Using a Two-Stream Attention-LSTM Model -

Qianyu Zhou1, Mingyang Zhao1, Tong Wanyan1

  • 1Department of Epidemiology, School of Public Health, Zhengzhou University, Zhengzhou City, Henan Province, China.

China CDC Weekly
|July 11, 2026
PubMed
Summary

Related Concept Videos

Transient Ischemic Attack l: Introduction01:26

Transient Ischemic Attack l: Introduction

A transient ischemic attack (TIA) is a brief episode of neurological dysfunction caused by a temporary, focal reduction in cerebral blood flow. Although symptoms resemble those of an ischemic stroke, the interruption in perfusion is short-lived and does not cause permanent infarction. TIAs are clinically important because they often serve as early warning events for future stroke.Mechanisms of Transient Cerebral IschemiaTransient cerebral ischemia may arise through several mechanisms. One...
Hemorrhagic Stroke l: Introduction01:17

Hemorrhagic Stroke l: Introduction

A hemorrhagic stroke is an acute neurological event that occurs when a weakened cerebral blood vessel ruptures, allowing blood to accumulate within or around the brain. The sudden release of blood forms a focal hematoma that increases intracranial pressure, displaces neural tissue, and can obstruct cerebrospinal fluid pathways. These effects may be compounded by intraventricular extension of the hemorrhage, cerebral edema, or compression of adjacent structures, all of which contribute to...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Effectiveness of a multidisciplinary "crisis checklist" on nursing performance during intraoperative cardiac arrest: A simulation-based study.

Scientific reports·2026
Same author

LivingAvatars: Robust Head Reconstruction With Gaussian Lifecycle Management and Neural Detail Synthesis.

IEEE transactions on visualization and computer graphics·2026
Same author

Development and external validation of an interpretable machine learning model for early prediction of stroke-associated pneumonia: a multicenter study.

International journal of medical informatics·2026
Same author

Impact of PDCA cycle optimization on door-to-wire time in patients with acute st-segment elevation myocardial infarction: a single-center retrospective before-and-after QI study.

Heart & lung : the journal of critical care·2026
Same author

Activatable Immunotheranostic Nanovesicles for Coordinated Phagocytic Reprogramming and Real-Time Immune Monitoring.

Journal of the American Chemical Society·2026
Same author

Nitrate boosts arsenic accumulation in hyperaccumulator Pteris vittata by coupling nitrogen assimilation with arsenic detoxification.

Journal of hazardous materials·2026

A new dynamic model using multimodal data accurately predicts 3-month ischemic stroke recurrence. This advanced prediction tool aids in early risk stratification for patients post-discharge.

Area of Science:

  • Neurology
  • Medical Informatics
  • Biostatistics

Background:

  • First-ever ischemic stroke recurrence poses a significant health risk.
  • Accurate prediction models are crucial for timely intervention and patient management.

Purpose of the Study:

  • To develop and validate a dynamic predictive model for 3-month recurrence after a first-ever ischemic stroke.
  • To leverage multimodal longitudinal data, including imaging phenotypes, for enhanced prediction accuracy.

Main Methods:

  • Utilized longitudinal data from 625 first-ever ischemic stroke patients, including baseline, discharge, and 1-month follow-up variables.
  • Derived imaging phenotypes from DWI and FLAIR using automated segmentation and clustering.
  • Trained and evaluated seven models, including logistic regression and deep learning approaches like two-stream attention-LSTM, with external validation at three hospitals.
Keywords:
Ischemic StrokeMultimodal DataPrediction ModelRecurrence Risk

Related Experiment Videos

Main Results:

  • The two-stream attention-LSTM model achieved the highest predictive performance with an AUC of 0.857 in the validation set.
  • Key predictors identified included dynamic changes in C-reactive protein, systolic blood pressure, and imaging phenotypes.
  • External validation confirmed stable discrimination (pooled AUC=0.83) and good calibration.

Conclusions:

  • The two-stream attention-LSTM model significantly improves the prediction of 3-month recurrence after first-ever ischemic stroke.
  • This model offers a valuable tool for early post-discharge risk stratification, potentially improving patient outcomes.