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

Correction: What's a migraine day? Towards a consensus definition for clinical care and research - a Delphi panel-based study.

The journal of headache and pain·2026
Same author

Exploring the role of resistin as a biomarker of early renal changes in pediatric type 1 diabetes mellitus.

Acta diabetologica·2026
Same author

Mechanotransduction in the Brain: Soliton Theory, Piezo Receptors and MR Elastography in Headache Pathophysiology.

Brain and behavior·2026
Same author

What's a migraine day? Towards a consensus definition for clinical care and research - a Delphi panel-based study.

The journal of headache and pain·2026
Same author

Functional Magnetic Resonance Imaging for Investigating the Role of the Hippocampus in Migraine with Aura.

Diagnostics (Basel, Switzerland)·2026
Same author

Hallmarks of headache disorders: part 5 - secondary headaches.

The journal of headache and pain·2026

Related Experiment Video

Updated: Jul 23, 2025

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.5K

Migraine with aura detection and subtype classification using machine learning algorithms and morphometric magnetic

Katarina Mitrović1, Igor Petrušić2, Aleksandra Radojičić3,4

  • 1Department of Information Technologies, Faculty of Technical Sciences in Čačak, University of Kragujevac, Čačak, Serbia.

Frontiers in Neurology
|July 13, 2023
PubMed
Summary

Machine learning accurately distinguishes migraine with aura (MwA) patients from healthy individuals using MRI data. This approach also precisely differentiates between simple and complex MwA subtypes, paving the way for improved diagnosis and tailored treatments.

Keywords:
artificial intelligenceclassificationmachine learningmagnetic resonance imagingmigraine with aura

More Related Videos

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

48.1K
Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

8.9K

Related Experiment Videos

Last Updated: Jul 23, 2025

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.5K
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

48.1K
Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

8.9K

Area of Science:

  • Neurology
  • Radiology
  • Machine Learning
  • Medical Diagnostics

Background:

  • Migraine with aura (MwA) is a prevalent neurological condition affecting approximately 5% of the global population.
  • MwA presents with diverse symptoms, necessitating advanced diagnostic and classification techniques for personalized treatment.
  • Current diagnostic methods require enhancement for accurate phenotyping and biomarker validation in MwA.

Purpose of the Study:

  • To develop and evaluate machine learning models for distinguishing MwA patients from healthy controls.
  • To differentiate between simple MwA and complex MwA subtypes using neuroimaging data.
  • To identify key neuroimaging features indicative of MwA and its subtypes.

Main Methods:

  • Utilized post-processed Magnetic Resonance Imaging (MRI) data, including cortical thickness, surface area, volume, Gaussian curvature, and folding index.
  • Collected data from 78 subjects: 46 MwA patients (22 simple, 24 complex) and 32 healthy controls.
  • Trained machine learning algorithms on 340 distinct neuroimaging features.

Main Results:

  • Achieved 97% classification accuracy in distinguishing MwA patients from healthy individuals.
  • Attained 98% accuracy in differentiating between simple and complex MwA subtypes.
  • Identified specific cortical thickness features (left temporal pole, right lingual gyrus, left pars opercularis) as crucial for MwA classification and (left pericalcarine gyrus, left pars opercularis) for subtype differentiation.

Conclusions:

  • Machine learning analysis of post-processed MRI data offers a highly accurate method for MwA diagnosis and subtype classification.
  • The identified neuroimaging features serve as potential biomarkers for MwA and its subtypes.
  • This approach holds significant potential for advancing the diagnosis and treatment strategies for MwA patients.