Classification of Depth of Coma Using Complexity Measures and Nonlinear Features of Electroencephalogram Signals

Abstract

In recent years, some electrophysiological analysis methods of consciousness have been proposed. Most of these studies are based on visual interpretation or statistical analysis, and there is hardly any work classifying the level of consciousness in a deep coma. In this study, we perform an analysis of electroencephalography complexity measures by quantifying features efficiency in differentiating patients in different consciousness levels. Several measures of complexity have been proposed to quantify the complexity of signals. Our aim is to lay the foundation of a system that will objectively define the level of consciousness by performing a complexity analysis of Electroencephalogram (EEG) signals. Therefore, a nonlinear analysis of EEG signals obtained with a recording scheme proposed by us from 39 patients with Glasgow Coma Scale (GCS) between 3 and 8 was performed. Various entropy values (approximate entropy, permutation entropy, etc.) obtained from different algorithms, Hjorth parameters, Lempel–Ziv complexity and Kolmogorov complexity values were extracted from the signals as features. The features were analyzed statistically and the success of features in classifying different levels of consciousness was measured by various classifiers. Consequently, levels of consciousness in deep coma (GCS between 3 and 8) were classified with an accuracy of 90.3%. To the authors’ best knowledge, this is the first demonstration of the discriminative nonlinear features extracted from tactile and auditory stimuli EEG signals in distinguishing different GCSs of comatose patients.

Quantitative Electroencephalography Analysis for Improved Assessment of Consciousness Levels in Deep Coma Patients Using a Proposed Stimulus Stage

“…As a result of this study, consciousness levels were classified into two classes (low level of consciousness and high level of consciousness) with 83.3% accuracy. In another study [ 98 , 99 ] we carried out, the classification of the level of consciousness with the features obtained as a result of the nonlinear analysis of the EEG signals was achieved with an accuracy of 90.3%. Unlike the previous two studies, the spectral content of the EEG waves was shown to provide discrimination in different levels of consciousness with an accuracy of 96.44% in this study.…”

The potential of the Lempel–Ziv complexity of the EEG in diagnosing cognitive impairment in patients with temporal lobe epilepsy

“…We collected information of 22 clinical features, including: (1) gender; (2) age; (3) age at onset; (4) length of time between the initial onset and current visit 20 ; (5) a family history of epilepsy (defined as whether first-or seconddegree relatives had epilepsy); (6) a history of head surgery or TBI; (7) a history of central nervous system (CNS) infections; (8) a history of perinatal injuries and febrile convulsions; (9) presence of abnormal cranial MRI findings; (10) presence of hippocampal atrophy and/or sclerosis; (11) seizure types (focal, focal to bilateral tonic-clonic); (12) generalized convulsive status epilepticus (seizures lasting for ≥5 min); (13) seizure frequency in the past year-sparse (≤1), occasional (2-3), and frequent (≥4); (14) whether taking ≥2 types of antiepileptic medications at presentation; (15) whether taking valproic acid (VPA) at presentation; (16) whether taking phenytoin (PHT) at presentation; (17) whether taking topiramate (TPM) at presentation; (18) an aura of epilepsy; (19) anxiety assessment by the Hamilton Anxiety Rating Scale (HAM-A) at current visit, categorized as none, probable, definite, or significant according to the score; (20) depression assessment by the Hamilton Depression Rating Scale (HAM-D) at current visit, categorized as none, probable, or definite according to the score; and (21) educational status, classified as primary school and below (0-6 years), middle school (7-9 years), high school (10-12 years), or university and above (>12 years).…”

“…16 LZC has also been used in the field of psychiatric disorders to study altered brain dynamics in patients with schizophrenia (SCZ) 17 and to measure the level of consciousness in comatose patients. 18 Based on these facts, we hypothesized that the LZC might be exploited as an indicator of comorbid CI conditions in TLE patients. Therefore, this study aimed to investigate whether LZC could be applied as a potential quantitative electroencephalogram biomarker for diagnosing CI in TLE patients with TLE by comparing the clinical features of corresponding control subjects.…”

“…Additionally, it has been demonstrated that LZC has the potential to serve as a biomarker for the early diagnosis of CI in Alzheimer's disease (AD) patients 16 . LZC has also been used in the field of psychiatric disorders to study altered brain dynamics in patients with schizophrenia (SCZ) 17 and to measure the level of consciousness in comatose patients 18 …”

A study on EEG differences between active counting and focused breathing tasks for more sensitive detection of consciousness

“…Altintop et al extracted EEG features such as entropy, Hjorth parameter, complexity, etc. and used algorithms such as Multilayer Perceptron Neural Networks and Random Forests to classify the level of consciousness ( Altintop et al, 2022 , 2023 ). Meanwhile, algorithms such as the synthetic minority oversampling technique (SMOTE) and the spatio-temporal self-constructing graph neural network (ST-SCGNN) also provide solutions to the data imbalance and cross-subject classification in consciousness detection research ( Chawla et al, 2002 ; Pan et al, 2023 ).…”