Comparison of Network Analysis Approaches on EEG Connectivity in Beta during Visual Short-Term Memory Binding Tasks

TL;DR

This study compares network analysis methods on EEG beta band signals during visual short-term memory tasks, finding threshold-based methods outperform MSTs in detecting functional network differences and highlighting contralateral activity's role.

Contribution

It demonstrates that threshold-based network analysis methods are more effective than MSTs for detecting differences in EEG connectivity during memory tasks.

Findings

Threshold analyses outperform MSTs in detecting network differences.

Significant differences are found in left-side tasks but not right-side, indicating contralateral activity importance.

Threshold methods detect task-related differences that MSTs fail to identify.

Abstract

We analyse the electroencephalogram signals in the beta band of working memory representation recorded from young healthy volunteers performing several different Visual Short-Term Memory (VSTM) tasks which have proven useful in the assessment of clinical and preclinical Alzheimer's disease. We compare network analysis using Maximum Spanning Trees (MSTs) with network analysis obtained using 20% and 25% connection thresholds on the VSTM data. MSTs are a promising method of network analysis negating the more classical use of thresholds which are so far chosen arbitrarily. However, we find that the threshold analyses outperforms MSTs for detection of functional network differences. Particularly, MSTs fail to find any significant differences. Further, the thresholds detect significant differences between shape and shape-colour binding tasks when these are tested in the left side of the display screen, but no such differences are detected when these tasks are tested for in the right side of the display screen. This provides evidence that contralateral activity is a significant factor in sensitivity for detection of cognitive task differences.