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 Video

Updated: May 16, 2026

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation
11:06

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

Published on: April 12, 2016

Machine learning models for predicting readmission after stroke: A systematic review and meta-analysis.

Yazeed Alajlouni1, Yousef S Zayed1, Yousef Nofal1

  • 1School of Medicine, The University of Jordan, Amman 11942, Jordan.

International Journal of Medical Informatics
|May 14, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Serum Proteomic Analysis Identifies Junction Plakoglobin and Glyceraldehyde-3-Phosphate Dehydrogenase as Potential Novel Circulating Biomarkers for Patients with Multiple Sclerosis.

Journal of proteome research·2026
Same author

Possible Diagnostic Error in Cervical Artery Dissection: Analysis of STOP-CAD Study.

Journal of the American Heart Association·2026
Same author

Virtual Reality Testing in Neurology and Neuro-ophthalmology.

Neurologic clinics·2026
Same author

Treatment Outcomes of Triamcinolone Acetonide Compared with Cryotherapy in Alopecia Areata: Evidence from a Systematic Review and Meta-Analysis.

Dermatology practical & conceptual·2026
Same author

Dissecting Aneurysm in Cervical Artery Dissection: Insights From the STOP-CAD Study.

Stroke·2026
Same author

Does the Ischemic Core Really Matter? An Updated Systematic Review and Meta-Analysis of Large Core Trials After TESLA, TENSION, and LASTE.

Stroke (Hoboken, N.J.)·2026

Machine learning models show moderate success in predicting hospital readmission after stroke. Key predictors include length of stay, age, and stroke severity scores, highlighting areas for improved patient care.

Area of Science:

  • Medical Informatics
  • Health Services Research
  • Artificial Intelligence in Medicine

Background:

  • Hospital readmission after stroke presents a significant healthcare challenge.
  • Machine learning (ML) models offer potential for improved readmission risk prediction compared to traditional methods.
  • Systematic evaluation of ML model performance in stroke readmission prediction is lacking.

Purpose of the Study:

  • To evaluate the predictive performance of ML models for post-stroke hospital readmission.
  • To identify the most significant predictors of stroke readmission.

Main Methods:

  • A systematic literature review and meta-analysis of studies using ML for stroke readmission prediction.
  • Primary outcome: predictive performance measured by Area Under the Receiver Operating Characteristic Curve (AUROC).
Keywords:
AICerebrovascular accidentMachine learningReadmissionStroke

Related Experiment Videos

Last Updated: May 16, 2026

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation
11:06

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

Published on: April 12, 2016

  • Pooled AUROC values calculated using a random-effects model.

    • Main Results:

    • Eleven studies analyzed 380,254 patients; 49 ML models reported, with Logistic Regression and Random Forest most common.
    • Overall pooled AUROC for readmission prediction was 0.74 (95% CI: 0.69 to 0.78).
    • Top predictors identified: Length of Stay (LOS), Age, National Institutes of Health Stroke Score (NIHSS), HbA1c, and Homocysteine blood level.

    Conclusions:

    • ML models demonstrate moderate predictive performance for stroke readmission risk.
    • Future research should focus on validating and refining models.
    • Adopting unified methodological approaches is crucial for more accurate conclusions.