Spatio-temporal analysis of EEG signal during consciousness using convolutional neural network

Abstract

Electroencephalogram (EEG) measurement could help to distinguish the level of consciousness in an individual without requiring a behavioral response, which could be useful as a diagnostic aid in patients with disorders of consciousness. In this study, we explored the EEG-evoked perturbation and analyzed consciousness using event-related spectral perturbation and convolutional neural network. We observed a novel EEG neurophysiological signature that can be used to monitor brain activity during unconsciousness. Also, the performance accuracy in the parietal region was higher than in the frontal region. The sensitivity for conscious experience was 90.9%, whereas sensitivity for unconscious experience was at the chance level in the parietal region. These results could be evidence for the importance of the posterior hot zone and could help shed light on the internal neural dynamics related to conscious experience.