Comparing and Scaling fMRI Features for Brain-Behavior Prediction

2025-07-28

AI Summary

This study systematically evaluates the predictive performance and scalability of nine resting-state fMRI features—including functional connectivity (FC), graph signal processing, graph filtering, and temporal/spatial variability metrics—for behavioral phenotypes (cognition, mental health, age, sex). Leveraging the large-scale Human Connectome Project (HCP) dataset, we employ a unified modeling framework to quantify how prediction accuracy varies with sample size and scan duration. Results show that FC achieves the highest overall predictive accuracy; however, graph density and temporal/spatial variability features exhibit unique robustness—particularly under resource-constrained conditions (e.g., small samples or short scans). To our knowledge, this is the first comprehensive comparative assessment of diverse emerging fMRI feature classes for brain–behavior prediction. Our findings reveal complementary information beyond FC, offering empirical guidance for feature selection, experimental design optimization, and translational neuroimaging applications.

Technology Category

• Machine Learning: Dimensionality Reduction/Feature Selection
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Predicting behavioral variables from neuroimaging modalities such as magnetic resonance imaging (MRI) has the potential to allow the development of neuroimaging biomarkers of mental and neurological disorders. A crucial processing step to this aim is the extraction of suitable features. These can differ in how well they predict the target of interest, and how this prediction scales with sample size and scan time. Here, we compare nine feature subtypes extracted from resting-state functional MRI recordings for behavior prediction, ranging from regional measures of functional activity to functional connectivity (FC) and metrics derived with graph signal processing (GSP), a principled approach for the extraction of structure-informed functional features. We study 979 subjects from the Human Connectome Project Young Adult dataset, predicting summary scores for mental health, cognition, processing speed, and substance use, as well as age and sex. The scaling properties of the features are investigated for different combinations of sample size and scan time. FC comes out as the best feature for predicting cognition, age, and sex. Graph power spectral density is the second best for predicting cognition and age, while for sex, variability-based features show potential as well. When predicting sex, the low-pass graph filtered coupled FC slightly outperforms the simple FC variant. None of the other targets were predicted significantly. The scaling results point to higher performance reserves for the better-performing features. They also indicate that it is important to balance sample size and scan time when acquiring data for prediction studies. The results confirm FC as a robust feature for behavior prediction, but also show the potential of GSP and variability-based measures. We discuss the implications for future prediction studies in terms of strategies for acquisition and sample composition.

Problem

• Comparing fMRI features for brain-behavior prediction
• Evaluating feature performance across sample sizes and scan times
• Identifying optimal features for predicting cognition, age, and sex

Innovation

• Compares nine fMRI feature subtypes
• Uses graph signal processing techniques
• Analyzes scaling with sample size