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 Videos

Automatic migraine classification via feature selection committee and machine learning techniques over imaging and

Yolanda Garcia-Chimeno1,2, Begonya Garcia-Zapirain3,4, Marian Gomez-Beldarrain5

  • 1DeustoTech - Fundacion Deusto, Avda. Universidades, 24, Bilbao, 48007, Spain. yolanda.garcia@deusto.es.

BMC Medical Informatics and Decision Making
|April 15, 2017
PubMed
Summary

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

Enhancing the detection of LTP through lyophilized protein samples and NIR spectroscopy with explainable deep learning.

Scientific reports·2026
Same author

Beneficial Effects of Olive Oil and the Mediterranean Diet on Alzheimer's Disease and Vascular Dementia: A Review.

Medicina (Kaunas, Lithuania)·2026
Same author

PSA-1DCNN: Multimodal Biomarker and Text Integration for Lung Cancer Diagnosis.

IEEE journal of biomedical and health informatics·2026
Same author

Analysis of Training Behavior in Users of a Fitness App: Cross-Sectional Study.

JMIR mHealth and uHealth·2026
Same author

Teaching NeuroImage: Acquired Midbrain Cleft in a Professional Boxer.

Neurology·2025
Same author

Clinical Reasoning: A 59-Year-Old Man With Acute-Onset Encephalopathy and Aphasia.

Neurology·2025

A new committee-based feature selection method significantly improved migraine diagnosis accuracy using diffusion tensor images (DTIs) and clinical data. This approach achieved over 90% accuracy, aiding specialists in classifying migraines.

Area of Science:

  • Neuroimaging
  • Machine Learning
  • Medical Diagnostics

Background:

  • Feature selection is crucial for classification model development, but its performance in diffusion tensor imaging (DTI) is understudied.
  • Migraine diagnosis can be automated by integrating DTI data with emotional and cognitive factors influencing pain perception.

Purpose of the Study:

  • To evaluate feature selection and machine learning methods for automated migraine diagnosis.
  • To investigate the utility of diffusion tensor imaging (DTI) and questionnaire data in classifying migraine subtypes.

Main Methods:

  • 52 adult subjects (15 control, 19 sporadic migraine, 18 chronic migraine) underwent DTI scans.
  • Feature selection algorithms (Gradient Tree Boosting, L1-based, Random Forest, Univariate) and classification algorithms (SVM, Adaboost, Naive Bayes) were applied.
Keywords:
Boosting(adaboost)ClassificationCommitteeDTIFeature selectionMigraineNaive bayesSVM

Related Experiment Videos

  • A committee method was developed to enhance classification accuracy based on feature selection.

    • Main Results:

    • The committee-based feature selection method significantly improved classification accuracy across all classifiers.
    • Accuracy increased from 67% to 93% (Naive Bayes), 90% to 95% (SVM), and 93% to 94% (Boosting).
    • Key features identified included those related to pain, analgesics, and the left uncinate fasciculus.

    Conclusions:

    • The proposed feature selection committee method enhances migraine diagnosis classifier performance.
    • The robust system achieved over 90% accuracy, supporting specialists in migraine classification.
    • This approach aids in classifying migraines in patients undergoing magnetic resonance imaging.