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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Feasibility of a narrative driven mobile video game cognitive training intervention to enhance executive function in post-stroke cognitive impairment.

Scientific reports·2026
Same author

Deep Learning-Based Automated Detection and Burden Assessment of Paramagnetic Rim Lesions on Quantitative Susceptibility Mapping in Patients With Multiple Sclerosis.

Korean journal of radiology·2026
Same author

Small vessel disease burden and response to induced hypertension therapy in small vessel occlusion stroke with early neurological deterioration.

International journal of stroke : official journal of the International Stroke Society·2026
Same author

Distinct remission immune architectures under rituximab and azathioprine in AQP4-IgG-positive neuromyelitis optica spectrum disorder.

Frontiers in immunology·2026
Same author

Assessment of Cortical Myelination in Patients with MS via T1-Weighted/FLAIR Ratio: A Longitudinal Follow-up Study.

AJNR. American journal of neuroradiology·2026
Same author

Cerebral vasodilation and lesion patterns in stroke-like episodes of MELAS: a quantitative angiographic investigation.

Quantitative imaging in medicine and surgery·2026

Related Experiment Video

Updated: Dec 30, 2025

A Magnetic Resonance Imaging Protocol for Stroke Onset Time Estimation in Permanent Cerebral Ischemia
09:59

A Magnetic Resonance Imaging Protocol for Stroke Onset Time Estimation in Permanent Cerebral Ischemia

Published on: September 16, 2017

14.5K

Machine Learning Approach to Identify Stroke Within 4.5 Hours.

Hyunna Lee1, Eun-Jae Lee2, Sungwon Ham3

  • 1From the Health Innovation Big Data Center, Asan Institute for Life Science, Asan Medical Center, University of Ulsan College of Medicine, Seoul, South Korea. (H.L.).

Stroke
|January 29, 2020
PubMed
Summary
This summary is machine-generated.

Machine learning models analyzing MRI scans are more sensitive than human readings for identifying acute ischemic stroke patients eligible for thrombolysis. These AI tools can accurately detect patients within the critical 4.5-hour treatment window.

Keywords:
artificial intelligencehumansmachine learningmagnetic resonance imagingstroke

More Related Videos

Setting Up a Stroke Team Algorithm and Conducting Simulation-based Training in the Emergency Department - A Practical Guide
09:52

Setting Up a Stroke Team Algorithm and Conducting Simulation-based Training in the Emergency Department - A Practical Guide

Published on: January 15, 2017

17.6K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

49.2K

Related Experiment Videos

Last Updated: Dec 30, 2025

A Magnetic Resonance Imaging Protocol for Stroke Onset Time Estimation in Permanent Cerebral Ischemia
09:59

A Magnetic Resonance Imaging Protocol for Stroke Onset Time Estimation in Permanent Cerebral Ischemia

Published on: September 16, 2017

14.5K
Setting Up a Stroke Team Algorithm and Conducting Simulation-based Training in the Emergency Department - A Practical Guide
09:52

Setting Up a Stroke Team Algorithm and Conducting Simulation-based Training in the Emergency Department - A Practical Guide

Published on: January 15, 2017

17.6K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

49.2K

Area of Science:

  • Neurology
  • Radiology
  • Artificial Intelligence

Background:

  • Acute ischemic stroke requires timely thrombolysis for effective treatment.
  • Identifying patients within the narrow therapeutic window is crucial but challenging.

Purpose of the Study:

  • To evaluate the efficacy of machine learning (ML) models in analyzing diffusion-weighted imaging (DWI) and fluid-attenuated inversion recovery (FLAIR) MRI scans.
  • To determine if ML can accurately identify acute ischemic stroke patients within the 4.5-hour thrombolysis window.

Main Methods:

  • Collected DWI and FLAIR MRI data from 355 acute ischemic stroke patients within 24 hours of symptom onset.
  • Applied automatic image processing for infarct segmentation, registration, and feature extraction (89 features per sequence).
  • Developed and compared three ML models (logistic regression, support vector machine, random forest) against human readings of DWI-FLAIR mismatch.

Main Results:

  • Human readings of DWI-FLAIR mismatch showed 48.5% sensitivity and 91.3% specificity for the 4.5-hour window.
  • ML algorithms demonstrated significantly higher sensitivity (72.7%-75.8%) compared to human readers (P<0.05).
  • ML models achieved comparable specificity (82.6%) to human readings.

Conclusions:

  • Machine learning models analyzing multimodal MRI data are feasible for acute ischemic stroke assessment.
  • ML algorithms show superior sensitivity in identifying patients within the thrombolysis time window compared to human interpretation.
  • This suggests ML can enhance clinical decision-making for acute stroke treatment.