Related Experiment Video
Updated: Apr 27, 2026
07:56
Resting-State Connectivity and Neuroimaging of Prefrontal Cortex Activity During a Block-Design Yoga Asana Practice Using fNIRS
Published on: June 24, 2025
982
Machine learning classification of resting state functional connectivity predicts smoking status
Vani Pariyadath1, Elliot A Stein1, Thomas J Ross1
1Neuroimaging Research Branch, Intramural Research Program, National Institute on Drug Abuse, National Institutes of Health Baltimore, MD, USA.
Frontiers in Human Neuroscience
|July 2, 2014
Summary
Machine learning accurately predicts nicotine dependence using brain connectivity data. Within-network connections, especially in executive control and frontoparietal networks, are key indicators of smoking status.
Area of Science:
- Neuroscience
- Computational Psychiatry
- Addiction Research
Background:
- Machine learning (ML) advances multivariate analysis of functional magnetic resonance imaging (fMRI) data.
- Identifying neurobiological markers for nicotine dependence is crucial for understanding addiction.
Purpose of the Study:
- To apply ML classification to resting-state functional connectivity (rsFC) data.
- To identify brain-based features that predict nicotine dependence in smokers versus controls.
Main Methods:
- Support vector machine (SVM) classification applied to rsFC data.
- Network-centered analysis focusing on within-network and between-network connectivity.
- Evaluation of node representativeness within parent networks.
Main Results:
- Within-network functional connectivity measures were most informative for predicting smoking status.
- Connectivity within the executive control and frontoparietal networks showed high predictive value.
- Between-network connectivity and node representativeness were less predictive.
Conclusions:
- ML classification of rsFC data is a powerful tool for addiction research.
- Specific within-network connectivity patterns are associated with nicotine dependence.
- This approach offers insights into large-scale neurobiological differences in addiction.
