Evaluating The Utility of Connectome-Based Predictive Modeling in a Large-Scale Cognitive Task-Based Dataset
Abstract/Contents
- Abstract
- Connectome-based predictive modeling (CBPM) represents an innovative approach in cognitive neuroscience, aiming to predict individual behavior based on functional brain connectivity. This study evaluates the efficacy of CBPM in predicting behavioral outcomes in a large-scale (N=103) dataset of healthy adults performing tasks related to cognitive control. Functional connectivity matrices were derived and correlated with task-specific behavioral measures. CBPM was employed using k-fold cross-validation to predict individual behavioral scores from the connectivity data. The predictive models did not accurately predict the observed values for performance across the tasks. The lack of significant predictive power indicates potential limitations within the instantiation of CBPM in this procedure or the dataset. The findings challenge the robustness of CBPM in cognitive control task-based fMRI data, suggesting that further refinement of predictive models or methodologies are necessary. Future research could explore standardizing CBPM approaches across different datasets or evaluating why this procedure is able to accurately predict brain-behavior relationships in some datasets compared to others.
Description
Type of resource | text |
---|---|
Date created | May 31, 2024 |
Date modified | July 18, 2024 |
Publication date | May 31, 2024 |
Creators/Contributors
Author | Ryan, Alexa |
![]() |
---|---|---|
Advisor | Bissett, Patrick | |
Advisor | Poldrack, Russell |
Subjects
Subject | neuroimaging |
---|---|
Subject | fMRI |
Subject | cognitive control |
Subject | connectome-based predictive modeling |
Genre | Text |
Genre | Thesis |
Bibliographic information
Access conditions
- Use and reproduction
- User agrees that, where applicable, content will not be used to identify or to otherwise infringe the privacy or confidentiality rights of individuals. Content distributed via the Stanford Digital Repository may be subject to additional license and use restrictions applied by the depositor.
- License
- This work is licensed under a Creative Commons Attribution 4.0 International license (CC BY).
Preferred citation
- Preferred citation
- Ryan, A. (2024). Evaluating The Utility of Connectome-Based Predictive Modeling in a Large-Scale Cognitive Task-Based Dataset. Stanford Digital Repository. Available at https://purl.stanford.edu/cs588rn5341. https://doi.org/10.25740/cs588rn5341.
Collection
Undergraduate Honors Thesis - Stanford Department of Psychology
View other items in this collection in SearchWorksContact information
- Contact
- ahryan@stanford.edu
Also listed in
Loading usage metrics...