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: Jun 29, 2026

Motor Dual-Tasks for Gait Analysis and Evaluation in Post-Stroke Patients
05:23

Motor Dual-Tasks for Gait Analysis and Evaluation in Post-Stroke Patients

Published on: March 11, 2021

Prediction of Early Hospital Admission (≤24 Hours) After Stroke Using Machine Learning and Deep Learning: Multicenter

Qingjia Zeng1,2, Jiachen Cui3, Xinyu Fan4

  • 1Institute of Medical Information/Medical Library, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, Beijing, China.

JMIR Medical Informatics
|June 24, 2026
PubMed

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

Microglial CR3-mediated synaptic pruning in the dmPFC promotes the generation and maintenance of chronic muscle pain via glutamatergic dysfunction.

Experimental & molecular medicine·2026
Same author

Effectiveness of Virtual Reality on Hand Function for Patients with Hemiplegia After Stroke: A Meta-Analysis of Randomized Controlled Trials.

NeuroRehabilitation·2026
Same author

The HALP Index as a Bridge Between Nutrition, Inflammation, and Coagulation in Predicting DVT Risk in Stroke Patients.

Biological research for nursing·2025
Same author

Mental Health Literacy, Anxiety, and Insomnia in Chinese Chronically Ill Older Adult-Caregiver Dyads: Actor-Partner Interdependence Moderation Model.

Family process·2025
Same author

Repetitive transcranial magnetic stimulation for musculoskeletal pain: A systematic review and meta-analysis.

British journal of pain·2025
Same author

Correlation Between Swallowing and Cognitive Brain Networks in Older Adults via Functional MRI.

Journal of oral rehabilitation·2024
Summary

A multilayer perceptron (MLP) model effectively predicts early hospital admission (≤24h) for acute stroke patients. This machine learning approach demonstrates strong temporal performance, aiding in timely stroke management and public health interventions.

Area of Science:

  • Neurology
  • Artificial Intelligence in Medicine
  • Health Informatics

Background:

  • Effective acute stroke management requires timely hospital admission within the therapeutic window.
  • Many patients miss the optimal treatment window due to delayed medical facility arrival.
  • Existing stroke prediction models lack temporal robustness and clinical interpretability.

Purpose of the Study:

  • To develop and temporally validate machine learning (ML) and deep learning (DL) models for predicting early hospital admission (≤24 hours) after acute stroke.
  • To assess model performance using multicenter clinical data, focusing on temporal validation.
  • To enhance clinical utility through improved temporal robustness and interpretability.

Main Methods:

  • Retrospective analysis of electronic medical record data from 1327 patients across 6 Chinese hospitals.
Keywords:
early hospital admissionmulticenter studymultilayer perceptronprehospital delaystroketemporal validation

More Related Videos

Dual-Task Stroop Paradigm for Detecting Cognitive Deficits in High-Functioning Stroke Patients
07:42

Dual-Task Stroop Paradigm for Detecting Cognitive Deficits in High-Functioning Stroke Patients

Published on: December 16, 2022

Related Experiment Videos

Last Updated: Jun 29, 2026

Motor Dual-Tasks for Gait Analysis and Evaluation in Post-Stroke Patients
05:23

Motor Dual-Tasks for Gait Analysis and Evaluation in Post-Stroke Patients

Published on: March 11, 2021

Dual-Task Stroop Paradigm for Detecting Cognitive Deficits in High-Functioning Stroke Patients
07:42

Dual-Task Stroop Paradigm for Detecting Cognitive Deficits in High-Functioning Stroke Patients

Published on: December 16, 2022

  • Development and comparison of six predictive models: logistic regression, support vector machine, random forest, multilayer perceptron (MLP), convolutional neural network (CNN), and long short-term memory (LSTM).
  • Independent temporal validation on a separate testing set (2023-2025) using discrimination metrics, sensitivity, specificity, F1-score, and Shapley additive explanations for interpretability.

    • Main Results:

    • The MLP model demonstrated superior performance in the independent temporal testing set, achieving an Area Under the Receiver Operating Characteristic Curve (AUC) of 0.9020.
    • MLP achieved high sensitivity (91.5%), specificity (75.6%), and F1-score (0.9033), outperforming other models including logistic regression, SVM, random forest, and CNN.
    • MLP showed statistically significant improvements over most models and favorable calibration, indicating robust predictive capability.

    Conclusions:

    • The MLP model exhibits favorable temporal performance for predicting early hospital admission post-stroke in a Chinese cohort.
    • This ML-based prediction tool can potentially support risk stratification and targeted public health interventions for stroke.
    • Further external validation and calibration refinement are recommended before clinical deployment.