Assessing Functional Neural Connectivity as an Indicator of Cognitive Performance

Abstract : Studies in recent years have demonstrated that neural organization and structure impact an individuals ability to perform a given task. Specifical-ly, more efficient functional networks have been shown to produce better per-formance. We apply this principle to evaluation of a working memory task by providing two novel approaches for characterizing functional network connec-tivity from electroencephalography (EEG). Our first approach represents func-tional connectivity structure through the distribution of eigenvalues making up channel coherence matrices in multiple frequency bands. Our second approach uses a connectivity matrix at each frequency band, assessing variability in aver-age path lengths and degree across the network. We also use features based on the pattern of frequency band power across the EEG channels. Failures in digit and sentence recall on single trials are detected using a Gaussian classifier for each feature set at each frequency band. The classifier results are then fused across frequency bands, with the resulting detection performance summarized using the area under the receiver operating characteristic curve (AUC) statistic. Fused AUC results of 0.63/0.58/0.61 for digit recall failure and 0.57/0.59/0.47 for sentence recall failure are obtained from the connectivity structure, graph variability, and channel power features respectively.