Short EEG Segments Research Articles

Machine learning classification of maladaptive rumination and cognitive distraction in terms of frequency specific complexity

In this study, cognitive and behavioral emotion regulation strategies (ERS) are classified by using machine learning models driven by a new local EEG complexity approach so called Frequency Specific Complexity (FSC) in resting-states (eyes-opened (EO), eyes-closed (EC)). According to international 10–20 electrode placement system, FSC is defined as entropy estimations in Alpha (8-12Hz) and Beta (12.5-30Hz) frequency band intervals of non-overlapped short EEG segments to observe local EEG complexity variations at 62 points on scalp surface. The healthy adults who use both rumination and cognitive distraction frequently are included in the 1st groups, while the others who use these strategies rarely are included in the 2nd group with respect to Cognitive Emotion Regulation Questionnaire (CERQ) scores of them. EEG data and CERQ scores are downloaded from publicly available data-base LEMON. In order to test the reliability of the proposed method, five different supervised machine learning methods in addition to two Extreme Learning Machine models are examined with 5-fold cross-validation for discrimination of the contrasting groups. The highest classification accuracy (CA) of 99.47% is provided by Class-specific Cost Regulation Extreme Learning Machines in EC state. Regarding cortical regions (anterio-frontal, central, temporal, parieto-occipital), the regional FSC estimations did not provide the higher performance, however, corresponding statistical distribution shows the decrease in EEG complexity at mostly anterior cortex in the 1st group characterized by maladaptive rumination. In conclusion, FSC can be proposed to investigate cognitive dysfunctions often caused by the use of rumination.

A novel approach to the study of spatio-temporal brain dynamics using change-based complexity

Brain complexity and neural oscillations are of vital significance for understanding brain dynamics. Although widely used in the quantification of complex behavior of the brain, standard complexity measures are hampered by some theoretical and implementation issues which limit their applicability to the study of nonlinear brain signals. Further, they have been used for spatial analysis but are insensitive to the temporal structure of data and not applicable to short EEG segments. We demonstrated the ability of a change-based complexity measure (Aksentijevic-Gibson complexity) to analyze neural activity in both spatial and temporal domains. We examined EEG recordings from a group of adolescents with schizophrenia and an age-matched group of healthy controls. AG revealed that the spatial complexity was significantly lower in the patient group across all electrodes with the lowest complexity at the frontal area of the brain. By focusing on outer frontal regions and temporal data averaged over schizophrenia adolescents, we observed periodic drops in complexity and low-delta oscillations at the left electrode F7 and numerous irregularly placed drops at the right side (F8). Periodicity was caused by zero complexity troughs in several individuals associated with large voltage declensions and connected with hypofrontality supporting left frontal pathology. Both averaged spatial and temporal complexities of healthy and schizophrenia adolescents were significantly different from the complexities of random sequences confirming that neural activity is more regular than a true random process. As a final step, we performed the analysis of short EEG segments for the two subjects (one control, one patient) in order to search for differences in neural oscillations. The examination revealed a clear 33 Hz gamma rhythm in a healthy participant and only a fast beta rhythm of 27 Hz in a patient as well as the presence of a full range of rhythms in a healthy EEG and only theta oscillations in that of a patient. The results support the large body of work which associates schizophrenia with lowered complexity, low-frequency rhythms and the scarcity of high-frequency oscillations.

Special Patterns of Dynamic Brain Networks Discriminate Between Face and Non-face Processing: A Single-Trial EEG Study.

Face processing is a spatiotemporal dynamic process involving widely distributed and closely connected brain regions. Although previous studies have examined the topological differences in brain networks between face and non-face processing, the time-varying patterns at different processing stages have not been fully characterized. In this study, dynamic brain networks were used to explore the mechanism of face processing in human brain. We constructed a set of brain networks based on consecutive short EEG segments recorded during face and non-face (ketch) processing respectively, and analyzed the topological characteristic of these brain networks by graph theory. We found that the topological differences of the backbone of original brain networks (the minimum spanning tree, MST) between face and ketch processing changed dynamically. Specifically, during face processing, the MST was more line-like over alpha band in 0–100 ms time window after stimuli onset, and more star-like over theta and alpha bands in 100–200 and 200–300 ms time windows. The results indicated that the brain network was more efficient for information transfer and exchange during face processing compared with non-face processing. In the MST, the nodes with significant differences of betweenness centrality and degree were mainly located in the left frontal area and ventral visual pathway, which were involved in the face-related regions. In addition, the special MST patterns can discriminate between face and ketch processing by an accuracy of 93.39%. Our results suggested that special MST structures of dynamic brain networks reflected the potential mechanism of face processing in human brain.

Classification with a Deferral Option and Low-Trust Filtering for Automated Seizure Detection.

Wearable technology will become available and allow prolonged electroencephalography (EEG) monitoring in the home environment of patients with epilepsy. Neurologists analyse the EEG visually and annotate all seizures, which patients often under-report. Visual analysis of a 24-h EEG recording typically takes one to two hours. Reliable automated seizure detection algorithms will be crucial to reduce this analysis. We investigated such algorithms on a dataset of behind-the-ear EEG measurements. Our first aim was to develop a methodology where part of the data is deferred to a human expert, who performs perfectly, with the goal of obtaining an (almost) perfect detection sensitivity (DS). Prediction confidences are determined by temperature scaling of the classification model outputs and trust scores. A DS of approximately 90% (99%) can be achieved when deferring around 10% (40%) of the data. Perfect DS can be achieved when deferring 50% of the data. Our second contribution demonstrates that a common modelling strategy, where predictions from several short EEG segments are combined to obtain a final prediction, can be improved by filtering out untrustworthy segments with low trust scores. The false detection rate shows a relative decrease between 21% and 43%, and the DS shows a small increase or decrease.

Recognizing Arm Motions by Fluctuation Analysis of EEG Signals

We consider the task of recognition of fragments of multichannel electroencephalogram (EEG) records corresponding to motions of the human arm and to mental representation of these motions. It is shown that the problem of recognition can be solved by processing short EEG segments by the method of fluctuation analysis. The obtained results suggest that fluctuation analysis can be used as an algorithm of the digital signal processing in development of the neurointerface software.

Распознавание движений руки по сигналам электроэнцефалограммы на основе флуктуационного анализа

AbstractWe consider the task of recognition of fragments of multichannel electroencephalogram (EEG) records corresponding to motions of the human arm and to mental representation of these motions. It is shown that the problem of recognition can be solved by processing short EEG segments by the method of fluctuation analysis. The obtained results suggest that fluctuation analysis can be used as an algorithm of the digital signal processing in development of the neurointerface software.

A flexible method for the automated offline-detection of artifacts in multi-channel electroencephalogram recordings.

Electroencephalogram (EEG) signal quality is often compromised by artifacts that corrupt quantitative EEG measurements used in clinical applications and EEG-related studies. Techniques such as filtering, regression analysis and blind source separation are often used to remove these artifacts. However, these preprocessing steps do not allow for complete artifact correction. We propose a method for the automated offline-detection of remaining artifacts after preprocessing in multi-channel EEG recordings. In contrast to existing methods it requires neither adaptive parameters varying between recordings nor a topography template. It is suited for short EEG segments and is flexible with regard to target applications. The algorithm was developed and tested on 60 clinical EEG samples of 20 seconds each that were recorded both in resting state and during cognitive activation to gain a realistic artifact set. Five EEG features were used to quantify temporal and spatial signal variations. Two distance measures for the single-channel and multi-channel variations of these features were defined. The global thresholds were determined by three-fold cross-validation and Youden's J statistic in conjunction with receiver operating characteristics (ROC curves). We observed high sensitivity of 95.5%±4.8 and specificity of 88.8%±2.1. The method has thus shown great potential and is promising as a possible tool for both EEG-based clinical applications and EEG-related research.

Classification of obsessive compulsive disorder by EEG complexity and hemispheric dependency measurements.

In the present study, both single channel electroencephalography (EEG) complexity and two channel interhemispheric dependency measurements have newly been examined for classification of patients with obsessive-compulsive disorder (OCD) and controls by using support vector machine classifiers. Three embedding entropy measurements (approximate entropy, sample entropy, permutation entropy (PermEn)) are used to estimate single channel EEG complexity for 19-channel eyes closed cortical measurements. Mean coherence and mutual information are examined to measure the level of interhemispheric dependency in frequency and statistical domain, respectively for eight distinct electrode pairs placed on the scalp with respect to the international 10-20 electrode placement system. All methods are applied to short EEG segments of 2 s. The classification performance is measured 20 times with different 2-fold cross-validation data for both single channel complexity features (19 features) and interhemispheric dependency features (eight features). The highest classification accuracy of 85 ±5.2% is provided by PermEn at prefrontal regions of the brain. Even if the classification success do not provided by other methods as high as PermEn, the clear differences between patients and controls at prefrontal regions can also be obtained by using other methods except coherence. In conclusion, OCD, defined as illness of orbitofronto-striatal structures [Beucke et al., JAMA Psychiatry70 (2013) 619-629; Cavedini et al., Psychiatry Res.78 (1998) 21-28; Menzies et al., Neurosci. Biobehav. Rev.32(3) (2008) 525-549], is caused by functional abnormalities in the pre-frontal regions. Particularly, patients are characterized by lower EEG complexity at both pre-frontal regions and right fronto-temporal locations. Our results are compatible with imaging studies that define OCD as a sub group of anxiety disorders exhibited a decreased complexity (such as anorexia nervosa [Toth et al., Int. J. Psychophysiol.51(3) (2004) 253-260] and panic disorder [Bob et al., Physiol. Res.55 (2006) S113-S119]).

Hyperactivity and sensation seeking as autoregulatory attempts to stabilize brain arousal in ADHD and mania?

Hypoarousal as indicated by skin conductance and electroencephalography (EEG) has been discussed as a pathogenetic factor in attention-deficit/hyperactivity disorder (ADHD). The aim of this paper was to review these arousal-related pathogenetic concepts and to present the more recently proposed vigilance regulation model of affective disorders and ADHD. The latter builds on methodological advances in classifying short EEG segments into vigilance stages (Vigilance Algorithm Leipzig, VIGALL), indicating different states of global brain function ("brain arousal"). VIGALL allows the objective assessment of vigilance regulation under defined conditions, e.g. how fast vigilance declines to lower vigilance stages associated with drowsiness during 15-20-min EEG recordings under resting conditions with eyes closed. According to the vigilance regulation model, the hyperactivity and sensation seeking observed in overtired children, ADHD and mania may be interpreted as an autoregulatory attempt to create a stimulating environment in order to stabilize vigilance. The unstable regulation of vigilance observed in both mania and ADHD may thus explain the attention deficits, which become especially prominent in monotonous sustained attention tasks. Among the arguments supporting the vigilance regulation model are the facts that destabilizing vigilance (e.g., via sleep deprivation) can trigger or exacerbate symptoms of ADHD or mania, whereas stabilizing vigilance (e.g., via psychostimulants, reducing sleep deficits) alleviates these symptoms. The potential antimanic effects of methylphenidate are presently being studied in an international randomized controlled trial. We propose vigilance regulation as a converging biomarker, which could be useful for identifying treatment responders to psychostimulants and forming pathophysiologically more homogeneous ADHD subgroups for research purposes.

EPA-0973 – Disturbed regulation of wakefulness as a pathogenetic factor in affective disorders and ADHD

Within the vigilance regulation model the hyperactivity and sensation seeking observed in overtired children, ADHD and mania are interpreted as an autoregulatory attempt to stabilize vigilance (central nervous arousal) by increasing external stimulation. Correspondingly the withdrawal and sensation avoidance in major depression is interpreted as a reaction to a state of tonically high vigilance (1, 2). Using an EEG-based algorithm to classify automatically short EEG-segments into different vigilance stages as observed during the transition from active wakefulness to drowsiness and sleep onset (VIGALL), both patients with ADHD and mania show an unstable vigilance regulation with rapid drops to lower vigilance stages under quiet rest. The contrary was found in unmedicated patients with major depression (2). Studies will be presented supporting the validity of VIGALL (simulataneous EEG-fMRI and EEG/FDG-PET studies, as well as the neurophysiological, clinical and predictive validity of the vigilance regulation model of affective disorders. Among the far reaching consequences of the vigilance model is the question whether psychostimulants have similar beneficial effects in mania as observed in ADHD (3), an aspect which is presently studied in an international, randomized controlled trial (4).

Comparative analysis of changes in short EEG segments during music perception based on event-related synchronization/desynchronization and wavelet synchronicity

The goal of the pilot study was to analyze the characteristics of changes in short EEG segments recorded from 32 sites during perception of musical melodies by healthy subjects depending on logical (recognition) and emotional (pleasant/unpleasant) estimation of the melody. For this purpose, the changes in event-related synchronization/desynchronization and the indices of wavelet synchrony of EEG responses were compared in 31 healthy subjects (18 to 60 years old). It has been shown that melody recognition during logical estimation of music is accompanied by event-related desynchronization in the left frontal-parietal-temporal area. Emotional estimation of a melody is characterized by event-related synchronization in the left frontal-temporal area for pleasant melodies, desynchronization in the temporal area for unpleasant melodies, and desynchronization in the occipital area for melodies inducing no emotional response. The analysis of EEG wavelet synchronization characterizing reactive changes in the interaction between cortical areas shows that the most distinct topographic differences are associated with the type of music processing: logical (familiar/unfamiliar) or emotional (pleasant/unpleasant). The changes in interhemispheric connections between the associative cortical areas (central, frontal, temporal) are greater during emotional estimation, while the changes in inter- and intrahemispheric connections between the projection areas of the acoustic analyzer (temporal area) are greater during logical estimation. It is assumed that the revealed event-related synchronization/desynchronization is most likely to reflect the activation component of musical fragment estimation, whereas wavelet analysis provides insight into the character of musical stimulus processing.

EEG-based assessment of wakefulness regulation in patients with mental disorders

Sleep disturbances are common symptoms of mental disorders and have been investigated using e.g. the Multiple Sleep Latency Test' (MSLT) (1). However, the MSLT does not measure the degree of wakefulness before sleep onset, information that might be diagnostically valuable. Different stages can be observed from full wakefulness to sleep onset in the electroencephalogram (EEG) (2–4). Specific types of wakefulness regulation are characterized by a distinct temporal passing through these wakefulness stages and accumulate in affective mental disorders (5,6). In a consecutive process Hegerl et al. develop an algorithm that automatically classifies short EEG segments into different wakefulness stages, based on the frequency and topographical distribution of the neuroelectric activity (7,8). Two psychiatric patient groups could be discriminated based upon their wakefulness regulation (7). Patients with obsessive-compulsive disorder showed hardly declines, those with Borderline personality disorder early declines to low wakefulness stages. Extending the sample current data will be presented. 1) Carskadon MA et al, Sleep 1986; 9: 519–524 2) Roth B, Electroenc Clin Neurophysiol 1961; 13: 395–399 3) Bente D, Habil 1964 4) Marzano C et al, Sleep 2007; 30: 610–616 5) Small JG et al, J Affect Dis 1999; 53: 217–224 6) Ulrich G et al, Eur Psychiatr 1999; 17: 217–229 7) Hegerl U et al, Eur Arch Psychiatr Clin Neurosci 2008; 258: 137–143 8) Olbrich O et al, NI 2009; 45: 319–332

Detection and evolution of rhytmic components in ictal EEG using short segment spectra and discriminant analysis

An automated method for analysis of ictal EEG is described which aims to reliably detect one or several rhythmic components in short EEG segments (2 sec) and to display their presence, frequency, amplitude, location, and temporal evolution. Spectra were estimated and compared using fast Fourier transform (FFT) and autoregressive modelling (AR). A subsequent linear discriminant analysis decided whether a spectral peak is likely to be caused by rhythmic activity or by the inherent statistical variability. FFT was found to perform better than AR in the detection of rhythmic components, yielding a false-positive rate of 0.825%, a false-negative rate of 2% (signal to noise ratio −4.6 dB), a frequency resolution of 2 Hz, and a temporal resolution of 0.5 sec. Seizure analysis revealed that the ictal scalp EEG of even short seizures can show a complex evolution of rhythmic patterns which are impossible or difficult to recognize by visual inspection or conventional spectral analysis. The following phenomena are demonstrated: superposition of two rhythmic components suggesting two cerebral regions discharging simultaneously and independently with their own pacemakers, sudden and gradual change of frequencies, and gradual development of harmonic frequencies. It is suggested that a more precise correlation between rhythmic generators and seizure symptomatology might allow more predictable pharmacological responses in antiepileptic therapy.