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

Multi-task learning for sparsity pattern heterogeneity: statistical and computational perspectives.

Journal of the Royal Statistical Society. Series B, Statistical methodology·2026
Same author

Experimenter-free pain assessment in mice using a thermal gradient ring and functional linear models.

Pain reports·2026
Same author

Characterizing Universal Object Representations Across Vision Models.

ArXiv·2026
Same author

Fast penalized generalized estimating equations for large longitudinal functional datasets.

Biometrics·2026
Same author

In-scanner thoughts contribute to resting-state functional connectivity.

Nature communications·2026
Same author

Brain age prediction in generalized anxiety disorder using a convolutional neural network.

Translational psychiatry·2026

Related Experiment Video

Updated: Jun 26, 2025

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

15.6K

Reliability and predictability of phenotype information from functional connectivity in large imaging datasets.

Jessica Dafflon1,2, Dustin Moraczewski1, Eric Earl1

  • 1Data Science & Sharing Team, National Institute of Mental Health, Bethesda, MD, USA.

Arxiv
|May 15, 2024
PubMed
Summary

Predicting human traits from brain connectivity is challenging. This study shows that using key components of functional connectivity (latent phenotypes) improves prediction accuracy, especially the first few components.

More Related Videos

Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

1.0K
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

Related Experiment Videos

Last Updated: Jun 26, 2025

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

15.6K
Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

1.0K
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

Area of Science:

  • Neuroimaging
  • Computational Neuroscience
  • Behavioral Genetics

Background:

  • Predictive modeling of behavior from brain functional connectivity is a key goal in neuroimaging.
  • Previous models show limited success in predicting behavioral traits from functional connectivity patterns.

Approach:

  • Developed models to predict observable traits (phenotypes) and their latent representations from resting-state functional connectivity.
  • Utilized data from the Human Connectome Project (HCP) and Philadelphia Neurodevelopmental Cohort (PNC).
  • Emphasized the importance of confounding variable regression for accurate phenotype prediction.

Key Points:

  • Both phenotypes and their latent phenotypes showed similar predictive performance.
  • Only the first five latent phenotypes were reliably identified.
  • Using only the top five latent phenotypes for prediction yielded performance comparable to using all latent phenotypes.

Conclusions:

  • Predictable phenotypic information is concentrated in the leading latent phenotypes.
  • Filtering out less reliable latent phenotypes does not harm predictive performance.
  • Findings enhance understanding of functional connectivity's role in phenotypic predictability and reliability for neuroimaging research.