A Manifold Regularized Multi-Task Learning Model for IQ Prediction from Multiple fMRI Paradigms

TL;DR

This paper introduces a manifold regularized multi-task learning model that leverages the geometric structure of multi-modal fMRI data to improve IQ prediction and identify relevant biomarkers.

Contribution

The novel model considers both between-subject and between-modality relationships, integrating manifold regularization with group sparsity for enhanced feature selection.

Findings

Improved IQ prediction accuracy over baseline models

Identification of IQ-relevant brain biomarkers

Effective utilization of multi-modal fMRI data structure

Abstract

Multi-modal brain functional connectivity (FC) data have shown great potential for providing insights into individual variations in behavioral and cognitive traits. The joint learning of multi-modal imaging data can utilize the intrinsic association, and thus can boost the learning performance. Although several multi-task based learning models have already been proposed by viewing the feature learning on each modality as one task, most of them ignore the geometric structure information inherent in the modalities, which may play an important role in extracting discriminative features. In this paper, we propose a new manifold regularized multi-task learning model by simultaneously considering between-subject and between-modality relationships. Besides employing a group-sparsity regularizer to jointly select a few common features across multiple tasks (modalities), we design a novel manifold regularizer to preserve the structure information both within and between modalities in our model. This will make our model more adaptive for realistic data analysis. Our model is then validated on the Philadelphia Neurodevelopmental Cohort dataset, where we regard our modalities as functional MRI (fMRI) data collected under two paradigms. Specifically, we conduct experimental studies on fMRI based FC network data in two task conditions for intelligence quotient (IQ) prediction. The results demonstrate that our proposed model can not only achieve improved prediction performance, but also yield a set of IQ-relevant biomarkers.