Date of Award

Spring 5-2023

Author's School

Graduate School of Arts and Sciences

Author's Department


Degree Name

Master of Arts (AM/MA)

Degree Type



Machine learning (ML) models are widely used to investigate the human connectome and to predict and understand behavior, emotion, and cognition. Prior research has organized pediatric connectome data using adult functional network models. However, this assumes that adult functional network models are appropriate and useful for prediction developmental outcomes from pediatric connectome data. We hypothesize that the application of adult brain network models could result in poor model fit, limiting the generalizability of results. Here, we test whether prediction of biological age is improved by concordant brain network models matching underlying functional connectome data. To quantify the difference in age prediction performance, we used resting-state fMRI data from both the Human Connectome Project Young Adult and Baby Connectome Project datasets. In this study, we employed a linear support vector regression model, random sampling, and permutation techniques to predict age and quantify prediction accuracy, reliability, and reproducibility. We quantified network-level reproducibility using network level enrichment analysis applied to whole-connectome data and we quantified network-level prediction accuracy using an individual network-block feature selection approach. Our findings indicate that age-matched network models produced more consistent results across different days or split halves, and the ML model using individual network block features organized by age-matched networks outperformed the one using network block features organized by age-mismatched networks. Taken together, these findings suggest that using age-specific network models is crucial for producing accurate, reliable, and reproducible predictions that are biologically interpretable. These findings are particularly important for functional connectome analysis in pediatric populations.


English (en)

Chair and Committee

Soumendra Lahiri

Committee Members

Muriah D. Wheelock, Likai Chen