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

Preoperative tumor and edema volumes as predictors of ischemia and morbidity after intracranial meningioma surgery.

Neuro-oncology advances·2026
Same author

T2 signal ratio enhances the diagnostic performance of apparent diffusion coefficient in differentiating orbital lymphoma from inflammatory mimickers.

Diagnostic and interventional radiology (Ankara, Turkey)·2025
Same author

Comparison of hand structure and function in early and late term dental students.

Irish journal of medical science·2025
Same author

Effects of lumbar stabilization exercises on serum biomarker levels and clinical outcomes in lumbar disc herniation: a subgroup analysis of a randomized controlled trial.

Turkish journal of medical sciences·2025
Same author

Re-irradiation in progressive diffuse infiltrative pontine glioma in children and young adults.

Strahlentherapie und Onkologie : Organ der Deutschen Rontgengesellschaft ... [et al]·2025
Same author

Development, reliability, and validity of the nurses' conscientious objection attitude scale (COAS-N).

BMC medical ethics·2024

Related Experiment Video

Updated: Jun 3, 2025

Author Spotlight: Establishing a Reliable Distal MCA Occlusion Model in Mice for Stroke Research
07:34

Author Spotlight: Establishing a Reliable Distal MCA Occlusion Model in Mice for Stroke Research

Published on: December 15, 2023

1.8K

Diagnostic Models for Differentiating COVID-19-Related Acute Ischemic Stroke Using Machine Learning Methods.

Eylem Gul Ates1,2, Gokcen Coban3, Jale Karakaya2

  • 1Institutional Big Data Management Coordination Office, Middle East Technical University, 06800 Ankara, Türkiye.

Diagnostics (Basel, Switzerland)
|January 8, 2025
PubMed
Summary

This study shows artificial intelligence can analyze brain MRI scans to detect COVID-19 in patients with acute ischemic stroke (AIS). Machine learning models effectively distinguish between COVID-19 positive and negative cases, aiding in diagnosis.

Keywords:
COVID-19acute ischemiaimage processinglong COVID-19machine learningstroke

More Related Videos

Modeling Stroke in Mice: Transient Middle Cerebral Artery Occlusion via the External Carotid Artery
07:26

Modeling Stroke in Mice: Transient Middle Cerebral Artery Occlusion via the External Carotid Artery

Published on: May 24, 2021

7.0K
A Thrombotic Stroke Model Based On Transient Cerebral Hypoxia-ischemia
06:01

A Thrombotic Stroke Model Based On Transient Cerebral Hypoxia-ischemia

Published on: August 18, 2015

14.8K

Related Experiment Videos

Last Updated: Jun 3, 2025

Author Spotlight: Establishing a Reliable Distal MCA Occlusion Model in Mice for Stroke Research
07:34

Author Spotlight: Establishing a Reliable Distal MCA Occlusion Model in Mice for Stroke Research

Published on: December 15, 2023

1.8K
Modeling Stroke in Mice: Transient Middle Cerebral Artery Occlusion via the External Carotid Artery
07:26

Modeling Stroke in Mice: Transient Middle Cerebral Artery Occlusion via the External Carotid Artery

Published on: May 24, 2021

7.0K
A Thrombotic Stroke Model Based On Transient Cerebral Hypoxia-ischemia
06:01

A Thrombotic Stroke Model Based On Transient Cerebral Hypoxia-ischemia

Published on: August 18, 2015

14.8K

Area of Science:

  • Neurology
  • Radiology
  • Artificial Intelligence

Background:

  • COVID-19 is increasingly linked to neurological complications, including acute ischemic stroke (AIS).
  • Distinguishing AIS related to COVID-19 requires advanced diagnostic tools.

Purpose of the Study:

  • To evaluate the efficacy of radiomic features from brain MRI and machine learning in identifying COVID-19 in AIS patients.
  • To develop and assess AI-driven models for diagnosing COVID-19 associated AIS.

Main Methods:

  • Retrospective analysis of brain MRI data from 57 AIS patients (30 COVID-19 positive, 27 negative).
  • Extraction of radiomic features from MRI, followed by feature selection using algorithms like Boruta, LASSO, and RFE.
  • Training and evaluation of machine learning classifiers (ANN, k-NN, RF, SVM) to differentiate between COVID-19 positive and negative groups.

Main Results:

  • The Recursive Feature Elimination (RFE) method with k-NN classifier achieved the highest performance, with an Area Under the Curve (AUC) of 0.882 and accuracy of 79.1%.
  • Artificial Neural Networks (ANN) and k-Nearest Neighbors (k-NN) demonstrated strong discriminative power, with AUCs up to 0.857 and 0.863 respectively, without feature selection or with Boruta selection.
  • The models showed high diagnostic reliability, with specific classifiers exhibiting excellent specificity and positive predictive value (PPV).

Conclusions:

  • Radiomics analysis combined with machine learning provides an effective method for distinguishing COVID-19 associated AIS from non-COVID-19 AIS using brain MRI.
  • AI-powered diagnostic tools show significant potential for early detection of high-risk patients, optimizing treatment, and improving clinical outcomes in neurological complications of COVID-19.