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

Gated edge-node interaction graph convolutional network for ADHD classification.

Ying Chen1, Yilan Li1, Zhixin Li1

  • 1School of Microelectronics and Control Engineering, Changzhou University, Changzhou, People's Republic of China.

Journal of Neural Engineering
|May 11, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Attention-Deficit/Hyperactivity Disorder01:30

Attention-Deficit/Hyperactivity Disorder

Attention-deficit/hyperactivity disorder (ADHD) is a neurodevelopmental disorder characterized by persistent inattention, hyperactivity, and impulsivity. It affects approximately 5-8% of children globally, with around 60-70% of cases persisting into adulthood. ADHD has significant implications for educational attainment, social interactions, and occupational success.
Diagnostic Criteria and Symptoms
To diagnose ADHD, symptoms must manifest before age 12 and be evident across multiple settings.
Seizures: Classification01:13

Seizures: Classification

Epilepsy is primarily characterized by unpredictable seizures, either provoked by an identifiable factor, such as injury or illness, or unprovoked, occurring spontaneously without apparent cause.
Seizures are typically classified into two main categories: focal and generalized seizures.
Focal Seizures
Focal seizures originate from specific regions of the brain. These seizures are further sub-classified into two types:

You might also read

Related Articles

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

Sort by
Same author

Baseline patient-reported symptom networks and early risk stratification for six-month symptom burden in newly diagnosed glioma: a prospective cohort study.

Frontiers in public health·2026
Same author

Controllable Synthesis of Silicalite-1 with Tailored c-Axis Length via KHSO<sub>4</sub> and Seed Co-Additive Strategy.

Materials (Basel, Switzerland)·2026
Same author

Epidemiological characteristics and spatiotemporal analysis of scarlet fever in Guangzhou, China: the surveillance of 20 years.

BMC infectious diseases·2026
Same author

Multi-Omics Analysis Identifies Paxillin as a Biomarker of Doxorubicin Resistance via Cytoskeletal Remodeling and Immune Exhaustion.

Journal of proteome research·2026
Same author

DNA demethylation of ANXA4 is associated with atrial fibrillation risk through myeloid immune mechanisms: evidence from Mendelian randomization and multi-omics analyses.

Clinical epigenetics·2026
Same author

Earth Greening Directly Affects Regional Atmospheric Oxidation Chemistry Evidenced by Tibetan Plateau Aerosol Nitrate Isotopes.

Environmental science & technology·2026

This study introduces a new graph neural network model for diagnosing Attention Deficit Hyperactivity Disorder (ADHD) using brain imaging data. The novel approach significantly improves diagnostic accuracy by better utilizing brain network information.

Area of Science:

  • Neuroscience
  • Artificial Intelligence
  • Medical Diagnostics

Background:

  • Objective diagnosis of Attention Deficit Hyperactivity Disorder (ADHD) is challenging, often relying on subjective clinical assessments.
  • Existing graph neural network (GNN) methods for ADHD identification primarily focus on node features, neglecting crucial edge information, thus limiting diagnostic performance.

Purpose of the Study:

  • To propose a novel Gated Edge-Node Interaction Graph Convolutional Network (GENI-GCN) for enhanced ADHD classification using neurobiological signals.
  • To improve feature extraction from brain graphs by effectively co-embedding node and edge information.

Main Methods:

  • Utilized resting-state fMRI-derived multi-band amplitudes of low-frequency fluctuations (ALFF) and functional connectivity (FC) data across 50 brain regions.
Keywords:
ADHD classificationbiomarker analysisco-embeddingedge-node updategraph convolutional network

Related Experiment Videos

  • Developed the GENI-GCN model with refined self-loop adjacent matrices to guide message passing and an adaptive gated mechanism to prevent graph degeneration.
  • Integrated GENI-GCN within a binary hypothesis testing (BHT) framework for ADHD classification.

    • Main Results:

    • Achieved high diagnostic accuracies of 97.9% on the ADHD-200 dataset and 96.6% on the ABIDE-I dataset, outperforming existing state-of-the-art methods.
    • Gradient-based interpretability analysis identified discriminative brain regions and connectivities consistent with known ADHD neurobiological findings.
    • The GENI-GCN-based BHT scheme demonstrated superior performance in ADHD classification.

    Conclusions:

    • The proposed GENI-GCN framework significantly enhances ADHD classification accuracy by effectively leveraging both node and edge information in brain graphs.
    • The model provides interpretable insights into abnormal brain topology associated with ADHD, supporting its potential for advancing neurobiological diagnostics.
    • This approach offers a promising direction for more objective and accurate ADHD diagnosis.