EEG entropy measures indicate decrease of cortical information processing in Disorders of Consciousness

Abstract

Objective: Clinical assessments that rely on behavioral responses to differentiate Disorders of Consciousness are at times inapt because of some patients' motor disabilities. To objectify patients' conditions of reduced consciousness the present study evaluated the use of electroencephalography to measure residual brain activity.

Methods: We analyzed entropy values of 18 scalp EEG channels of 15 severely brain-damaged patients with clinically diagnosed Minimally-Conscious-State (MCS) or Unresponsive-Wakefulness-Syndrome (UWS) and compared the results to a sample of 24 control subjects. Permutation entropy (PeEn) and symbolic transfer entropy (STEn), reflecting information processes in the EEG, were calculated for all subjects. Participants were tested on a modified active own-name paradigm to identify correlates of active instruction following.

Results: PeEn showed reduced local information content in the EEG in patients, that was most pronounced in UWS. STEn analysis revealed altered directed information flow in the EEG of patients, indicating impaired feed-backward connectivity. Responses to auditory stimulation yielded differences in entropy measures, indicating reduced information processing in MCS and UWS.

Conclusions: Local EEG information content and information flow are affected in Disorders of Consciousness. This suggests local cortical information capacity and feedback information transfer as neural correlates of consciousness.

Significance: The utilized EEG entropy analyses were able to relate to patient groups with different Disorders of Consciousness.

Keywords: Disorders of consciousness; Electroencephalography; Information theory; Non-linear analysis; Own-name paradigm; Permutation entropy; Symbolic transfer entropy.