Unsupervised machinelearning classifcation of electrophysiologically active electrodes during human cognitive task performance

Brent M. Berry

Abstract:

Identifcation of active electrodes that record task-relevant neurophysiological activity is needed
for clinical and industrial applications as well as for investigating brain functions. We developed an
unsupervised, fully automated approach to classify active electrodes showing event-related intracranial
EEG (iEEG) responses from 115 patients performing a free recall verbal memory task. Our approach
employed new interpretable metrics that quantify spectral characteristics of the normalized iEEG signal
based on power-in-band and synchrony measures. Unsupervised clustering of the metrics identifed
distinct sets of active electrodes across diferent subjects. In the total population of 11,869 electrodes,
our method achieved 97% sensitivity and 92.9% specifcity with the most efcient metric. We validated
our results with anatomical localization revealing signifcantly greater distribution of active electrodes
in brain regions that support verbal memory processing. We propose our machine-learning framework
for objective and efcient classifcation and interpretation of electrophysiological signals of brain
activities supporting memory and cognition.