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

Machine-learning identifies Parkinson's disease patients based on resting-state between-network functional

Christian Rubbert1, Christian Mathys1,2, Christiane Jockwitz3,4

  • 11University Dusseldorf, Medical Faculty, Department of Diagnostic and Interventional Radiology, D-40225 Dusseldorf, Germany.

The British Journal of Radiology
|April 18, 2019
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

Brain age gap in multiple sclerosis: associated with disability but independent of serum biomarkers.

Therapeutic advances in neurological disorders·2026
Same author

Varying patterns of association between cortical large-scale networks and subthalamic nucleus activity in Parkinson's disease.

NPJ Parkinson's disease·2026
Same author

The deep brain stimulation response network in Parkinson's disease operates in the high beta band.

Brain : a journal of neurology·2026
Same author

Effect of deep brain stimulation on dysphagia in Parkinson's disease: mechanisms, evidence, and outlook.

Frontiers in aging neuroscience·2026
Same author

Spatial signature of low-frequency network changes accounts for pallidal stimulation outcome in cervical dystonia.

EBioMedicine·2026
Same author

Quantity and quality of care and staff knowledge regarding people with Parkinson's disease in long-term nursing care: "real-life" results from the German Care4PD study.

Frontiers in aging neuroscience·2026

This study used resting-state functional MRI (rs-fMRI) to develop a data-driven model for distinguishing Parkinson's disease (PD) patients from healthy individuals. The approach achieved high accuracy and sensitivity, suggesting potential for screening.

Area of Science:

  • Neuroimaging
  • Computational Neuroscience
  • Biomarker Discovery

Background:

  • Idiopathic Parkinson's disease (PD) diagnosis relies on clinical assessment, highlighting the need for objective biomarkers.
  • Resting-state functional MRI (rs-fMRI) offers a non-invasive method to investigate brain connectivity.
  • Between-network functional connectivity patterns may differentiate neurological conditions.

Purpose of the Study:

  • To evaluate a data-driven, model-based classification approach using whole-brain rs-fMRI connectivity.
  • To discriminate between patients with idiopathic Parkinson's disease (PD) and healthy controls (HC).
  • To assess the diagnostic performance of this novel approach.

Main Methods:

  • Whole-brain rs-fMRI data acquired from 42 PD patients and 47 age/gender-matched HC.

Related Experiment Videos

  • Computation of between-network connectivity using full and L2-regularized partial correlation measures.
  • A Boosted Logistic Regression model trained with nested cross-validation for performance estimation and feature importance analysis.

    • Main Results:

    • The model achieved a mean accuracy of 76.2% (median 77.8%) in discriminating PD patients from HC.
    • Mean sensitivity was 81% (median 80%) and mean specificity was 72.7% (median 75%).
    • The best performance was obtained using the 1000BRAINS 50-network parcellation with full correlations, with sensorimotor and sensory networks identified as key features.

    Conclusions:

    • A data-driven, model-based rs-fMRI approach demonstrates high accuracy and sensitivity for differentiating PD from HC.
    • The high sensitivity suggests potential utility in a screening setting for Parkinson's disease.
    • Rs-fMRI connectivity analysis shows promise as a non-invasive neuroimaging biomarker for neurodegenerative diseases.