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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Habenula alterations in resting state functional connectivity among autistic individuals.

Biological psychiatry. Cognitive neuroscience and neuroimaging·2026
Same author

Predicting progression of Alzheimer's disease using blood-based multi-omics data.

Bioinformatics advances·2026
Same author

Executive Summary of ASN Kidney Health Guidance on Conservative Management in People with Kidney Failure.

Journal of the American Society of Nephrology : JASN·2026
Same author

ASN Kidney Health Guidance on Conservative Management in People with Kidney Failure.

Journal of the American Society of Nephrology : JASN·2026
Same author

End-to-end deep attention-based multitask pipeline for predicting uncertainty-quantified peptide properties from mass spectrometry data.

Scientific reports·2026
Same author

FiCOPS: Hardware/Software Co-Design of FPGA Computational Framework for Mass Spectrometry-Based Peptide Database Search.

bioRxiv : the preprint server for biology·2026

Related Experiment Video

Updated: Jul 19, 2025

Dynamic Inter-subject Functional Connectivity Reveals Moment-to-Moment Brain Network Configurations Driven by Continuous or Communication Paradigms
08:36

Dynamic Inter-subject Functional Connectivity Reveals Moment-to-Moment Brain Network Configurations Driven by Continuous or Communication Paradigms

Published on: March 21, 2019

7.3K

Confounding Effects on the Performance of Machine Learning Analysis of Static Functional Connectivity Computed from

Oswaldo Artiles1, Zeina Al Masry2, Fahad Saeed3

  • 1Knight Foundation School of Computing and Information Sciences, Florida International University, 11200 SW 8th Street CASE 354, Miami, Florida, 33199, USA.

Neuroinformatics
|August 15, 2023
PubMed
Summary
This summary is machine-generated.

This study addresses variability in multi-site resting-state functional MRI data for brain connectivity analysis. Novel stratification and feature generation methods improved machine learning classification for autism, enhancing diagnostic accuracy.

Keywords:
ABIDEConfounding effectsFunctional connectivityMachine learningrs-fMRI multi-site data

More Related Videos

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

15.7K
Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy
12:09

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Published on: August 5, 2014

18.1K

Related Experiment Videos

Last Updated: Jul 19, 2025

Dynamic Inter-subject Functional Connectivity Reveals Moment-to-Moment Brain Network Configurations Driven by Continuous or Communication Paradigms
08:36

Dynamic Inter-subject Functional Connectivity Reveals Moment-to-Moment Brain Network Configurations Driven by Continuous or Communication Paradigms

Published on: March 21, 2019

7.3K
Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

15.7K
Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy
12:09

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Published on: August 5, 2014

18.1K

Area of Science:

  • Neuroscience
  • Medical Imaging
  • Machine Learning

Background:

  • Resting-state functional MRI (rs-fMRI) is crucial for understanding brain connectivity.
  • Multi-site rs-fMRI data present challenges due to acquisition variability and population heterogeneity.
  • Confounding effects in multi-site data can limit the generalizability of machine learning models.

Purpose of the Study:

  • To identify and control confounding variables in multi-site rs-fMRI data.
  • To enhance machine learning classification performance using the Autism Brain Imaging Data Exchange (ABIDE) dataset.
  • To maximize classification scores by improving data homogeneity and feature representation.

Main Methods:

  • Proposed novel stratification methods to create homogeneous subsamples from 17 ABIDE sites.
  • Generated new features from static functional connectivity using multiple linear regression and ComBat harmonization.
  • Employed normalization techniques to control for confounding phenotypic and imaging variables.

Main Results:

  • Achieved classification accuracy of 76.4%, sensitivity of 82.9%, and specificity of 77.0%.
  • These scores represent significant improvements over baseline: 8.8% accuracy, 20.5% sensitivity, and 7.5% specificity.
  • Demonstrated the effectiveness of proposed methods in mitigating confounding effects.

Conclusions:

  • The developed methods successfully identified and controlled confounding effects in multi-site rs-fMRI data.
  • Enhanced data homogeneity and feature engineering significantly improved machine learning model performance for autism classification.
  • This approach offers a pathway to more reliable and generalizable computational neuroscience findings.