Using graph theory as a common language to combine neural structure and function in models of healthy cognitive performance

Abstract

Graph theory has been used in cognitive neuroscience to understand how organisational properties of structural and functional brain networks relate to cognitive function. Graph theory may bridge the gap in integration of structural and functional connectivity by introducing common measures of network characteristics. However, the explanatory and predictive value of combined structural and functional graph theory have not been investigated in modelling of cognitive performance of healthy adults. In this work, a Principal Component Regression approach with embedded Step‐Wise Regression was used to fit multiple regression models of Executive Function, Self‐regulation, Language, Encoding and Sequence Processing with a collection of 20 different graph theoretic measures of structural and functional network organisation used as regressors. The predictive ability of graph theory‐based models was compared to that of connectivity‐based models. The present work shows that using combinations of graph theory metrics to predict cognition in healthy populations does not produce a consistent benefit relative to making predictions based on structural and functional connectivity values directly.

Task-guided Generative Adversarial Networks for Synthesizing and Augmenting Structural Connectivity Matrices for Connectivity-Based Prediction

“…Garai et al highlighted that network patterns or topological features in structural connectivity possess predictive power for human cognitive traits [36]. While Litwińczuk observed no consistent advantage in utilizing graph theory measures over connectivity values for explaining and predicting cognitive functions in healthy and typical domains, they noted instances where nodal graph theory metrics of the structural network outperformed raw connectivity models in predictive ability [37]. These prior studies support that the enhanced prediction accuracy observed with matrices synthesized by TG GAN II can be attributed to their graph theoretical features, which are more akin to those of the acquired matrices.…”

From brain to education through machine learning: Predicting literacy and numeracy skills from neuroimaging data

“…Among the studies included in the current review, LOOCV was the most widely adopted (21 studies), while most other studies used 10-fold CV (10 studies). Although a recent study suggested that repetitive cross-validation is more reliable than the leave-one-out method (Valente et al, 2021), this technique was only adopted in three studies (Litwińczuk et al, 2023;Nemmi et al, 2023;Torres-Ramos et al, 2020). Overall, there is wide variability in the machine-learning techniques used in neuroimaging studies, both in terms of algorithm selection and CV method.…”

Functional Brain Connectivity Differences between Aphasic and Neurotypical Brains

“…Graph theory, utilizing fMRI, quantifies brain connectivity, identifying regions contributing to cognitive functions like language processing with potential applications in neurological treatments, including aphasia [20]. Graph theory integrates neural structure and function for precise cognitive models, validated using fMRI in language tasks, predicting individual differences and identifying crucial brain regions for cognitive performance [21]. The study emphasizes vital QC procedures using the CONN toolbox for accurate fcMRI results, demonstrating effectiveness in artifact removal and improving connectivity accuracy in healthy participants.…”