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

Branched chain amino acid metabolism and microbiome in adolescents with obesity during weight loss therapy.

The Journal of clinical investigation·2026
Same author

[Organoids and organ-on-a-chip: novel strategies for TCM against respiratory virus-induced cranial nerve injury].

Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica·2026
Same author

Neuroimmune Correlates of HIV and Marijuana Use: Peripheral Biomarkers and Cognitive Function.

Journal of neuroimmune pharmacology : the official journal of the Society on NeuroImmune Pharmacology·2026
Same author

A Tree Perspective on Stick-Breaking Models in Covariate-Dependent Mixtures (with Discussion).

Bayesian analysis·2026
Same author

Coarsened Mixtures of Hierarchical Skew Normal Kernels for Flow and Mass Cytometry Analyses.

Bayesian analysis·2026
Same author

Membrane-modified mesoporous silica nanoparticles guided by tumor immunomodulatory regulation for anti-tumor strategies.

Frontiers in immunology·2026

Related Experiment Video

Updated: Jul 9, 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

15.7K

Cocaine Use Prediction With Tensor-Based Machine Learning on Multimodal MRI Connectome Data.

Anru R Zhang1, Ryan P Bell2, Chen An3

  • 1Department of Biostatistics and Bioinformatics and Department of Computer Science, Duke University, Durham, NC 27710, U.S.A. anru.zhang@duke.edu.

Neural Computation
|December 5, 2023
PubMed
Summary

Machine learning accurately predicts cocaine use from brain imaging (MRI) connectomic data. Tensor-based algorithms identify at-risk individuals, offering a promising tool for substance abuse research.

More Related Videos

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
Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time
07:12

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time

Published on: July 1, 2014

12.3K

Related Experiment Videos

Last Updated: Jul 9, 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

15.7K
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
Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time
07:12

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time

Published on: July 1, 2014

12.3K

Area of Science:

  • Neuroimaging
  • Machine Learning
  • Addiction Science

Background:

  • Substance use disorders pose significant public health challenges.
  • Predictive models for cocaine use are crucial for early intervention.
  • Connectomic data from magnetic resonance imaging (MRI) offers insights into brain function.

Purpose of the Study:

  • To develop and evaluate a machine learning model for predicting cocaine use.
  • To leverage tensor-based analysis of functional MRI (fMRI) and diffusion MRI (dMRI) data.
  • To integrate demographic factors with neuroimaging data for enhanced prediction accuracy.

Main Methods:

  • Utilized fMRI and dMRI data from 275 individuals, parcellated into 246 regions of interest (ROIs) using the Brainnetome atlas.
  • Applied a tensor-based unsupervised machine learning algorithm (high-order Lloyd algorithm) to reduce data dimensionality by clustering ROIs.
  • Trained a Catboost model with subsampling and nested cross-validation, incorporating extracted tensor features and demographic data.

Main Results:

  • Achieved a prediction accuracy of 0.857 for identifying cocaine users.
  • Successfully reduced the data tensor size while preserving relevant features.
  • Demonstrated the predictive power of combined connectomic and demographic features.

Conclusions:

  • Tensor-based machine learning models can effectively predict cocaine use from MRI connectomic data.
  • This approach shows potential for identifying individuals at risk of substance abuse.
  • Highlights the utility of advanced machine learning techniques in addiction research.