Dynamic Network Connectivity Analysis for Understanding Attention Deficit Hyperactivity Disorder

This research examines the dynamics of brain resting-state functional connectivity (rs-FC) using functional magnetic resonance imaging (fMRI) data for attention-deficit/hyperactivity disorder (ADHD). Machine learning is a high potential approach for brain disorder diagnosis based on the constructed rs-FC brain network. The dynamics of brain connectivity directly impact the choice of algorithm design and model performance evaluation. In this study, we applied a sliding window to fMRI time series data from ADHD-200 dataset for constructing a time-varying network, and we experimented three window sizes (30, 40, and 60 seconds). Then, 10 different network metrics are calculated for each network, and being compared between the ADHD vs. Control groups. We considered the brain rs-FC network as temporal graphs and provided a comprehensive statistical analysis to understand how the network metrics can help differentiate ADHD vs. Control groups. The experimental results show that the graph dynamics have a significant influence on the selection of the key network metrics. However, average shortest path and betweenness centrality show high potential to be used to diagnose ADHD in the Control groups. This study is expected to provide a preliminary study of using temporal network approaches for computer-aided ADHD diagnosis.