Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Oct 14, 2025

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

RA-GCN: Graph convolutional network for disease prediction problems with imbalanced data.

Mahsa Ghorbani¹, Anees Kazi², Mahdieh Soleymani Baghshah³

¹Department of Computer Engineering, Sharif University of Technology, Tehran, Iran; Computer Aided Medical Procedures, Department of Informatics, Technical University of Munich, Germany.

Medical Image Analysis

|November 3, 2021

Summary

Related Concept Videos

Classification of Illness

Classification of Illness

The meaning of illness is individualized to each person who experiences an alteration in health. In contrast, disease is a medical term indicating a pathological change in the structure and function of the body or mind. It is a condition that has specific symptoms and boundaries.
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...

You might also read

Related Articles

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

Sort by

Same author

Explainable artificial intelligence models in predicting major cardiovascular events: insights from the PolyIran and PolyPars prospective studies.

Scientific reports·2026

Same author

Development and clinical usability assessment of a web-based AI platform for automated echocardiography analysis.

Computer methods and programs in biomedicine·2026

Same author

Structural connectome analysis using a graph-based deep model for prediction of non-imaging variables.

Frontiers in neuroscience·2026

Same author

Planar optical chemical sensing and imaging of heterogeneous pH and oxygen fronts during reactive transport in porous media: Applications to acid mine drainage neutralization and zero-valent iron permeable reactive barrier treatment.

Journal of contaminant hydrology·2026

Same author

Osteogenic Potential of a Three-Phase Strontium- and Silicon-Doped Tricalcium Silicate Cement on Dental Pulp Stem Cells: An In Vitro Study.

Clinical and experimental dental research·2026

Same author

Prosthetic Management of a Maxillofacial Defect Post-Mucormycosis: A Case Report.

Case reports in dentistry·2026

This study introduces a novel Re-weighted Adversarial Graph Convolutional Network (RA-GCN) to address class imbalance in disease prediction. RA-GCN improves diagnostic accuracy by preventing bias towards majority classes, crucial for identifying rare positive cases.

Area of Science:

Medical Informatics
Machine Learning
Graph Neural Networks

Background:

Disease prediction is a critical classification task in healthcare.
Graph Convolutional Networks (GCNs) model patient relationships but struggle with imbalanced medical data.
Class imbalance leads to biased GCNs, neglecting rare but vital positive cases.

Purpose of the Study:

To develop a robust method for disease prediction that overcomes class imbalance issues.
To enhance the accuracy of identifying rare positive cases in skewed medical datasets.
To propose a novel Re-weighted Adversarial Graph Convolutional Network (RA-GCN) for improved classification.

Main Methods:

Modeling disease prediction as a graph node classification task where each node represents a patient.

Keywords:

Disease prediction Graph convolutional networks Graphs Imbalanced classification Node classification

Related Experiment Videos

Last Updated: Oct 14, 2025

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Introducing RA-GCN, which utilizes class-specific graph-based neural networks for sample re-weighting.

Employing an adversarial training approach to optimize both the classifier and weighting networks.

Main Results:

RA-GCN effectively prevents classifiers from being biased towards majority classes.
The proposed method demonstrates superior performance in identifying patient status across synthetic and three real-world medical datasets.
Experiments confirm RA-GCN's advantage over existing methods in handling imbalanced disease prediction tasks.

Conclusions:

RA-GCN offers a significant advancement in disease prediction by effectively mitigating class imbalance.
The adversarial re-weighting strategy enhances the classifier's attention to crucial, underrepresented samples.
This approach holds promise for improving diagnostic accuracy in various medical applications with imbalanced data.