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

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

The Deep Learning Revolution in Neuroimaging: Insights from a Bibliometric Analysis (2014-2024).

Neuroinformatics·2026

Same author

Neptune: a toolbox for spinal cord functional MRI data processing and quality assurance.

bioRxiv : the preprint server for biology·2026

Same author

Non-invasive Electrophysiological Characterization of Distinctive Meditative States in a Yogi during <i>Samaadhi</i>.

International journal of yoga·2026

Same author

Augmenting an Allograft for Anterior Cruciate Ligament Reconstruction With a Collagen Matrix and Bone Marrow Aspirate Concentrate Injection Appears Safe and Produces Favorable Clinical Outcomes at 2-Year Follow-Up.

Arthroscopy, sports medicine, and rehabilitation·2026

Same author

Topology Assisted Clustering of Temporal fMRI Brain Networks With Use-Case in Mitigating Non-Neural Multi-Site Variability.

IEEE access : practical innovations, open solutions·2026

Same author

Effects of seasonal factors on brain function: Systematic review and future perspectives.

iScience·2025

Search research articles

Related Experiment Video

Updated: Jan 4, 2026

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

Supervised machine learning for diagnostic classification from large-scale neuroimaging datasets.

Pradyumna Lanka^1,2, D Rangaprakash^1,3, Michael N Dretsch^4,5,6

¹AU MRI Research Center, Department of Electrical and Computer Engineering, Auburn University, 560 Devall Dr., Suite 266D, Auburn, AL, 36849, USA.

Brain Imaging and Behavior

|November 7, 2019

Summary

This summary is machine-generated.

Machine learning classifiers in neuroimaging often overfit heterogeneous data. A consensus classifier improved generalizability across diverse patient populations for Autism Spectrum Disorder, ADHD, PTSD, and Alzheimer's disease.

Keywords:

ADHD Alzheimer’s disease Autism Diagnostic classification Functional connectivity PTSD Resting-state functional MRI Supervised machine learning

More Related Videos

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Related Experiment Videos

Last Updated: Jan 4, 2026

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

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Area of Science:

Neuroimaging
Machine Learning
Computational Psychiatry

Background:

Generalizability of machine learning classifiers in neuroimaging is a significant concern.
Evaluating classifier performance across diverse populations and varying data acquisition parameters is crucial.

Purpose of the Study:

To assess the generalizability of 18 machine learning classifiers across heterogeneous neuroimaging datasets for four neurological disorders.
To investigate the impact of age range and acquisition site differences on classifier performance.
To propose and evaluate a consensus-classifier approach to improve generalizability.

Main Methods:

Applied 18 diverse machine learning classifiers to datasets from Autism Spectrum Disorder (N=988), ADHD (N=930), PTSD (N=87), and Alzheimer's disease (N=132).
Training, validation, and testing data were matched by diagnosis but varied in age or acquisition site.
A consensus-classifier was developed by combining predictions from all individual classifiers.

Main Results:

Overfitting was identified as a major issue in heterogeneous datasets, particularly with smaller sample sizes, leading to overestimated accuracy.
Individual classifiers showed variable performance across different datasets.
The consensus-classifier demonstrated reduced sensitivity to discrepancies between training/validation and hold-out test data.
Identified robust functional connectivity patterns with diagnostic predictive ability, independent of classification algorithm, age, or site.

Conclusions:

The generalizability of neuroimaging classifiers is challenged by data heterogeneity and overfitting.
A consensus-classifier approach enhances robustness and generalizability in clinical neuroimaging applications.
Functional connectivity patterns identified through this method hold significant diagnostic potential across diverse populations.