Autism Classification Using Brain Functional Connectivity Dynamics and Machine Learning

TL;DR

This study uses brain functional connectivity variability derived from resting-state imaging data and machine learning to classify autism spectrum disorder, achieving 65% accuracy and demonstrating the effectiveness of dynamic connectivity features.

Contribution

It introduces the use of FC variability as features for ASD classification, showing that dynamic measures outperform static ones in predictive accuracy.

Findings

Autism patients show increased FC variability in specific brain regions.

Dynamic FC features outperform or match static FC features in ASD prediction.

Achieved 65% classification accuracy using FC variability features.

Abstract

The goal of the present study is to identify autism using machine learning techniques and resting-state brain imaging data, leveraging the temporal variability of the functional connections (FC) as the only information. We estimated and compared the FC variability across brain regions between typical, healthy subjects and autistic population by analyzing brain imaging data from a world-wide multi-site database known as ABIDE (Autism Brain Imaging Data Exchange). Our analysis revealed that patients diagnosed with autism spectrum disorder (ASD) show increased FC variability in several brain regions that are associated with low FC variability in the typical brain. We then used the enhanced FC variability of brain regions as features for training machine learning models for ASD classification and achieved 65% accuracy in identification of ASD versus control subjects within the dataset. We also used node strength estimated from number of functional connections per node averaged over the whole scan as features for ASD classification.The results reveal that the dynamic FC measures outperform or are comparable with the static FC measures in predicting ASD.