Recovering EEG brain signals: artifact suppression with wavelet enhanced independent component analysis

Exploring aperiodic activity in first episode schizophrenia spectrum psychosis: A resting-state EEG analysis

Abnormalities in brain oscillatory patterns have long been observed in schizophrenia and psychotic disorders more broadly. However, far less is known about aperiodic neural activity in these disorders, which has been linked to excitation/inhibition balance and neuronal population spiking within the brain. Here, we analysed resting-state electroencephalographic (EEG) recordings from 43 first episode schizophrenia spectrum psychosis (FESSP) patients and 28 healthy controls to examine whether aperiodic activity is disrupted in FESSP. We further assessed potential associations between aperiodic activity in FESSP and clinical symptom severity using the Brief Psychiatric Rating Scale (BPRS), the Scale for the Assessment of Negative Symptoms (SANS), and the Scale for the Assessment of Positive Symptoms (SAPS). We found no significant differences in either the 1/f-like aperiodic exponent or the broadband aperiodic offset between the FESSP and healthy control groups when analysing the global neural signal averaged across all EEG electrodes. Bayesian analyses further supported these non-significant findings. However, additional non-parametric cluster-based permutation analyses did identify reduced aperiodic offset in the FESSP group, relative to controls across broad central, temporal, parietal and select frontal regions. No associations were found between either exponent or offset and clinical symptom severity when examining all FESSP participants, irrespective of antipsychotic medication status. However, offset was shown to predict BPRS and SANS scores in medication naive patients. In sum, this research presents an initial analysis of aperiodic neural activity in FESSP, offering preliminary evidence of altered aperiodic offset in this disorder. This contributes to a broader understanding of disrupted neural dynamics in early psychosis.

Machine learning based classification of presence utilizing psychophysiological signals in immersive virtual environments

In Virtual Reality (VR), a higher level of presence positively influences the experience and engagement of a user. There are several parameters that are responsible for generating different levels of presence in VR, including but not limited to, graphical fidelity, multi-sensory stimuli, and embodiment. However, standard methods of measuring presence, including self-reported questionnaires, are biased. This research focuses on developing a robust model, via machine learning, to detect different levels of presence in VR using multimodal neurological and physiological signals, including electroencephalography and electrodermal activity. An experiment has been undertaken whereby participants (N = 22) were each exposed to three different levels of presence (high, medium, and low) in a random order in VR. Four parameters within each level, including graphics fidelity, audio cues, latency, and embodiment with haptic feedback, were systematically manipulated to differentiate the levels. A number of multi-class classifiers were evaluated within a three-class classification problem, using a One-vs-Rest approach, including Support Vector Machine, k-Nearest Neighbour, Extra Gradient Boosting, Random Forest, Logistic Regression, and Multiple Layer Perceptron. Results demonstrated that the Multiple Layer Perceptron model obtained the highest macro average accuracy of 93 ± 0.03 % . Posthoc analysis revealed that relative band power, which is expressed as the ratio of power in a specific frequency band to the total baseline power, in both the frontal and parietal regions, including beta over theta and alpha ratio, and differential entropy were most significant in detecting different levels of presence.

Using deep learning and pretreatment EEG to predict response to sertraline, bupropion, and placebo

OBJECTIVE

Predicting an individual's response to antidepressant medication remains one of the most challenging tasks in the treatment of major depressive disorder (MDD). Our objective was to use the large EMBARC study database to develop an electroencephalography (EEG)-based method to predict response to antidepressant treatment.

METHODS

Pre-treatment EEG data were collected from study participants treated with either sertraline (N = 105), placebo (N = 119), or bupropion (N = 35). After preprocessing, the robust exact low-resolution electromagnetic tomography (ReLORETA) brain source localization method was used to reconstruct the source signals in 54 brain regions. Connectivity between regions was determined using symbolic transfer entropy (STE). A convolutional neural network (CNN) classified participants as responders or non-responders to each treatment.

RESULTS

Classification accuracy was 91.0%, 95.4%, and 86.8% for sertraline, placebo, and bupropion, respectively. The most highly predictive features were connectivity between i) the anterior cingulate cortex and superior parietal lobule (alpha frequency), ii) the anterior cingulate cortex and orbitofrontal area (beta frequency), and iii) the orbitofrontal area and anterior cingulate cortex (gamma frequency).

CONCLUSION

CNN analysis of EEG connectivity may accurately predict response to sertraline, bupropion, and placebo.

SIGNIFICANCE

The suggested method may offer clinicians an accessible and cost-effective tool for speedy treatment and helps pharmaceutical firms to test new antidepressants efficiently.

A biomarker of brain arousal mediates the intergenerational link between maternal and child post-traumatic stress disorder

This study examined whether there is a biological basis in the child's resting brain activity for the intergenerational link between maternal interpersonal violence-related posttraumatic stress disorder (IPV-PTSD) and child subclinical symptoms. We used high-density EEG recordings to investigate the resting brain activity in a sample of 57 children, 34 from mothers with IPV-PTSD, and 23 from mothers without PTSD. These children were part of a prospective, longitudinal study focusing on the offspring of mothers with and without IPV-PTSD, reporting how the severity of a mother's IPV-PTSD can impact her child's emotional regulation and risk for developing mental illness. However, we had not yet looked into potential EEG biomarkers during resting state that might mediate and/or moderate effects of maternal IPV-PTSD severity on child mental health, and in particular the risk for PTSD. The alpha band spectral power as well as the aperiodic exponent of the power spectrum (PLE; power-law exponent) were examined as mediators of maternal IPV-PTSD and child PTSD. While there was no difference in alpha spectral power between the two groups, PLE was significantly reduced in children of mothers with IPV-PTSD compared to control children, indicating cortical hyper-arousal. Interestingly, child PLE was negatively correlated with the severity of maternal IPV-PTSD, suggesting an intergenerational interaction. This interpretation was reinforced by a negative correlation between child PLE and child PTSD symptoms. Finally, causal analyses using structural equation modelling indicated that child PLE mediated the relationship between maternal PTSD severity and child PTSD. Our observations suggest that maternal IPV-PTSD has an intergenerational impact on the child neurobehavioral development through a correlated abnormal marker of brain arousal (i.e. child PLE). These findings are potentially relevant to psychotherapy research and to the development of more effective psycho-neurobehavioral therapies (i.e. neurofeedback) among affected individuals.

Resting state EEG assisted imagined vowel phonemes recognition by native and non-native speakers using brain connectivity measures

Communication is challenging for disabled individuals, but with advancement of brain-computer interface (BCI) systems, alternative communication systems can be developed. Current BCI spellers, such as P300, SSVEP, and MI, have drawbacks like reliance on external stimuli or conversation irrelevant mental tasks. In contrast to these systems, Imagined speech based BCI systems rely on directly decoding the vowels/words user is thinking, making them more intuitive, user friendly and highly popular among Brain-Computer-Interface (BCI) researchers. However, more research needs to be conducted on how subject-specific characteristics such as mental state, age, handedness, nativeness and resting state activity affects the brain's output during imagined speech. In an overt speech, it is evident that native and non-native speakers' brains function differently. Therefore, this paper explores how nativeness to language affects EEG signals while imagining vowel phonemes, using brain-map analysis and scalogram and also investigates the inclusion of features extracted from resting state EEG with imagined state EEG. The Fourteen-channel EEG for Imagined Speech (FEIS) dataset was used to analyse the EEG signals recorded while imagining vowel phonemes for 16 subjects (nine native English and seven non-native Chinese). For the classification of vowel phonemes, different connectivity measures such as covariance, coherence, and Phase Synchronous Index-PSI were extracted and analysed using statistics based Multivariate Analysis of Variance (MANOVA) approach. Different fusion strategies (difference, concatenation, Common Spatial Pattern-CSP and Canonical Correlation Analysis-CCA) were carried out to incorporate resting state EEG connectivity measures with imagined state connectivity measures for enhancing the accuracy of imagined vowel phoneme recognition. Simulation results revealed that concatenating imagined state and rest state covariance and PSI features provided the maximum accuracy of 92.78% for native speakers and 94.07% for non-native speakers.

Mnemonic brain state engagement is diminished in healthy aging

Healthy older adults typically show impaired episodic memory - memory for when and where an event oc-curred - but intact semantic memory - knowledge for general information and facts. As older adults also have difficulty inhibiting the retrieval of prior knowledge from memory, their selective decline in episodic memory may be due to a tendency to over engage the retrieval state, a brain state in which attention is focused internally in an attempt to access prior knowledge. The retrieval state trades off with the encoding state, a brain state which supports the formation of new memories. Therefore, episodic memory declines in older adults may be the result of differential engagement in mnemonic brain states. Our hypothesis is that older adults are biased toward a retrieval state. We recorded scalp electroencephalography while young, middle-aged and older adults performed a memory task in which they were explicitly directed to either encode the currently presented object stimulus or retrieve a previously presented, categorically-related object stimulus. We used multivariate pattern analysis of spectral activity to decode engagement in the retrieval vs. encoding state. We find that all three age groups can follow top-down instructions to selectively engage in encoding or retrieval and that we can decode mnemonic states for all age groups. However, we find that mnemonic brain state engagement is diminished for older adults relative to middle-aged adults. Our interpretation is that a combination of executive control deficits and a modest bias to retrieve modulates older adults' mnemonic state engagement. Together, these findings suggest that dif-ferential mnemonic state engagement may underlie age-related memory changes.

Top-Down Task Goals Induce the Retrieval State

Engaging the retrieval state (Tulving, 1983) impacts processing and behavior (Long and Kuhl, 2019, 2021; Smith et al., 2022), but the extent to which top-down factors-explicit instructions and goals-versus bottom-up factors-stimulus properties such as repetition and similarity-jointly or independently induce the retrieval state is unclear. Identifying the impact of bottom-up and top-down factors on retrieval state engagement is critical for understanding how control of task-relevant versus task-irrelevant brain states influence cognition. We conducted between-subjects recognition memory tasks on male and female human participants in which we varied test phase goals. We recorded scalp electroencephalography and used an independently validated mnemonic state classifier (Long, 2023) to measure retrieval state engagement as a function of top-down task goals (recognize old vs detect new items) and bottom-up stimulus repetition (hits vs correct rejections (CRs)). We find that whereas the retrieval state is engaged for hits regardless of top-down goals, the retrieval state is only engaged during CRs when the top-down goal is to recognize old items. Furthermore, retrieval state engagement is greater for low compared to high confidence hits when the task goal is to recognize old items. Together, these results suggest that top-down demands to recognize old items induce the retrieval state independent from bottom-up factors, potentially reflecting the recruitment of internal attention to enable access of a stored representation.

Successful retrieval is its own reward

The ability to successfully remember past events is critical to our daily lives, yet the neural mechanisms underlying the motivation to retrieve is unclear. Although reward-system activity and feedback-related signals have been observed during memory retrieval, whether this signal reflects intrinsic reward or goal-attainment is unknown. Adjudicating between these two alternatives is crucial for understanding how individuals are motivated to engage in retrieval and how retrieval supports later remembering. To test these two accounts, we conducted between-subjects recognition memory tasks on human participants undergoing scalp electroencephalography and varied test-phase goals (recognize old vs. detect new items). We used an independently validated feedback classifier to measure positive feedback evidence. We find positive feedback following successful retrieval regardless of task goals. Together, these results suggest that successful retrieval is intrinsically rewarding. Such a feedback signal may promote future retrieval attempts as well as bolster later memory for the successfully retrieved events.

Transdiagnostic psychopathology in the light of robust single-trial event-related potentials

Recent evidence indicates that event-related potentials (ERPs) as measured on the electroencephalogram (EEG) are more closely related to transdiagnostic, dimensional measures of psychopathology (TDP) than to diagnostic categories. A comprehensive examination of correlations between well-studied ERPs and measures of TDP is called for. In this study, we recruited 50 patients with emotional disorders undergoing 14 weeks of transdiagnostic group psychotherapy as well as 37 healthy comparison subjects (HC) matched in age and sex. HCs were assessed once and patients three times throughout treatment (N = 172 data sets) with a battery of well-studied ERPs and psychopathology measures consistent with the TDP framework The Hierarchical Taxonomy of Psychopathology (HiTOP). ERPs were quantified using robust single-trial analysis (RSTA) methods and TDP correlations with linear regression models as implemented in the EEGLAB toolbox LIMO EEG. We found correlations at several levels of the HiTOP hierarchy. Among these, a reduced P3b was associated with the general p-factor. A reduced error-related negativity correlated strongly with worse symptomatology across the Internalizing spectrum. Increases in the correct-related negativity correlated with symptoms loading unto the Distress subfactor in the HiTOP. The Flanker N2 was related to specific symptoms of Intrusive Cognitions and Traumatic Re-experiencing and the mismatch negativity to maladaptive personality traits at the lowest levels of the HiTOP hierarchy. Our study highlights the advantages of RSTA methods and of using validated TDP constructs within a consistent framework. Future studies could utilize machine learning methods to predict TDP from a set of ERP features at the subject level.

EEGminer: discovering interpretable features of brain activity with learnable filters

Objective. The patterns of brain activity associated with different brain processes can be used to identify different brain states and make behavioural predictions. However, the relevant features are not readily apparent and accessible. Our aim is to design a system for learning informative latent representations from multichannel recordings of ongoing EEG activity.Approach: We propose a novel differentiable decoding pipeline consisting of learnable filters and a pre-determined feature extraction module. Specifically, we introduce filters parameterized by generalized Gaussian functions that offer a smooth derivative for stable end-to-end model training and allow for learning interpretable features. For the feature module, we use signal magnitude and functional connectivity estimates.Main results.We demonstrate the utility of our model on a new EEG dataset of unprecedented size (i.e. 721 subjects), where we identify consistent trends of music perception and related individual differences. Furthermore, we train and apply our model in two additional datasets, specifically for emotion recognition on SEED and workload classification on simultaneous task EEG workload. The discovered features align well with previous neuroscience studies and offer new insights, such as marked differences in the functional connectivity profile between left and right temporal areas during music listening. This agrees with the specialisation of the temporal lobes regarding music perception proposed in the literature.Significance. The proposed method offers strong interpretability of learned features while reaching similar levels of accuracy achieved by black box deep learning models. This improved trustworthiness may promote the use of deep learning models in real world applications. The model code is available athttps://github.com/SMLudwig/EEGminer/.

Robust single-trial event-related potentials differentiate between distress and fear disorders

Recent evidence indicates that measures of brain functioning as indexed by event-related potentials (ERPs) on the electroencephalogram align more closely to transdiagnostic measures of psychopathology than to categorical taxonomies. The Hierarchical Taxonomy of Psychopathology (HiTOP) is a transdiagnostic, dimensional framework aiming to solve issues of comorbidity, symptom heterogeneity, and arbitrary diagnostic boundaries. Based on shared features, the emotional disorders are allocated into subfactors Distress and Fear. Evidence indicates that disorders that are close in the HiTOP hierarchy share etiology, symptom profiles, and treatment outcomes. However, further studies testing the biological underpinnings of the HiTOP are called for. In this study, we assessed differences between Distress and Fear in a range of well-studied ERP components. In total, 50 patients with emotional disorders were divided into two groups (Distress, N = 25; Fear, N = 25) according to HiTOP criteria and compared against 37 healthy comparison (HC) subjects. Addressing issues in traditional ERP preprocessing and analysis methods, we applied robust single-trial analysis as implemented in the EEGLAB toolbox LIMO EEG. Several ERP components were found to differ between the groups. Surprisingly, we found no difference between Fear and HC for any of the ERPs. This suggests that some well-established results from the literature, e.g., increased error-related negativity in OCD, are not a shared neurobiological correlate of the Fear subfactor. Conversely, for Distress, we found reductions compared to Fear and HC in several ERP components across paradigms. Future studies could utilize HiTOP-validated psychopathology measures to more precisely define subfactor groups.

Evaluating the effectiveness of artifact correction and rejection in event-related potential research

Eyeblinks and other large artifacts can create two major problems in event-related potential (ERP) research, namely confounds and increased noise. Here, we developed a method for assessing the effectiveness of artifact correction and rejection methods in minimizing these two problems. We then used this method to assess a common artifact minimization approach, in which independent component analysis (ICA) is used to correct ocular artifacts, and artifact rejection is used to reject trials with extreme values resulting from other sources (e.g., movement artifacts). This approach was applied to data from five common ERP components (P3b, N400, N170, mismatch negativity, and error-related negativity). Four common scoring methods (mean amplitude, peak amplitude, peak latency, and 50% area latency) were examined for each component. We found that eyeblinks differed systematically across experimental conditions for several of the components. We also found that artifact correction was reasonably effective at minimizing these confounds, although it did not usually eliminate them completely. In addition, we found that the rejection of trials with extreme voltage values was effective at reducing noise, with the benefits of eliminating these trials outweighing the reduced number of trials available for averaging. For researchers who are analyzing similar ERP components and participant populations, this combination of artifact correction and rejection approaches should minimize artifact-related confounds and lead to improved data quality. Researchers who are analyzing other components or participant populations can use the method developed in this study to determine which artifact minimization approaches are effective in their data.

Resting-State EEG Microstates and Power Spectrum in Borderline Personality Disorder: A High-Density EEG Study

Borderline personality disorder (BPD) is a debilitating psychiatric condition characterized by emotional dysregulation, unstable sense of self, and impulsive, potentially self-harming behavior. In order to provide new neurophysiological insights on BPD, we complemented resting-state EEG frequency spectrum analysis with EEG microstates (MS) analysis to capture the spatiotemporal dynamics of large-scale neural networks. High-density EEG was recorded at rest in 16 BPD patients and 16 age-matched neurotypical controls. The relative power spectrum and broadband MS spatiotemporal parameters were compared between groups and their inter-correlations were examined. Compared to controls, BPD patients showed similar global spectral power, but exploratory univariate analyses on single channels indicated reduced relative alpha power and enhanced relative delta power at parietal electrodes. In terms of EEG MS, BPD patients displayed similar MS topographies as controls, indicating comparable neural generators. However, the MS temporal dynamics were significantly altered in BPD patients, who demonstrated opposite prevalence of MS C (lower than controls) and MS E (higher than controls). Interestingly, MS C prevalence correlated positively with global alpha power and negatively with global delta power, while MS E did not correlate with any measures of spectral power. Taken together, these observations suggest that BPD patients exhibit a state of cortical hyperactivation, represented by decreased posterior alpha power, together with an elevated presence of MS E, consistent with symptoms of elevated arousal and/or vigilance. This is the first study to investigate resting-state MS patterns in BPD, with findings of elevated MS E and the suggestion of reduced posterior alpha power indicating a disorder-specific neurophysiological signature previously unreported in a psychiatric population.

The persistence of memory: prior memory responses modulate behavior and brain state engagement

Memory brain states may influence how we experience an event. Memory encoding and retrieval constitute neurally dissociable brain states that individuals can selectively engage based on top-down goals. To the extent that memory states linger in time - as suggested by prior behavioral work - memory states may influence not only the current experience, but also subsequent stimuli and judgments. Thus lingering memory states may have broad influences on cognition, yet this account has not been directly tested utilizing neural measures of memory states. Here we address this gap by testing the hypothesis that memory brain states are modulated by memory judgments, and that these brain states persist for several hundred milliseconds. We recorded scalp electroencephalography (EEG) while participants completed a recognition memory task. We used an independently validated multivariate mnemonic state classifier to assess memory state engagement. We replicate prior behavioral findings; however, our neural findings run counter to the predictions made on the basis of the behavioral data. Surprisingly, we find that prior responses modulate current memory state engagement on the basis of response congruency. That is, we find strong engagement of the retrieval state on incongruent trials - when a target is preceded by a correct rejection of a lure and when a lure is preceded by successful recognition of a target. These findings indicate that cortical brain states are influenced by prior judgments and suggest that a non-mnemonic, internal attention state may be recruited to in the face of changing demands in a dynamic environment.

Multi-Algorithm Artifact Correction (MAAC) procedure part one: Algorithm and example

The Multi-Algorithm Artifact Correction (MAAC) procedure is presented for electroencephalographic (EEG) data, as made freely available in the open-source EP Toolkit (Dien, 2010). First the major EEG artifact correction methods (regression, spatial filters, principal components analysis, and independent components analysis) are reviewed. Contrary to the dominant approach of picking one method that is thought to be most effective, this review concludes that none are globally superior, but rather each has strengths and weaknesses. Then each of the major artifact types are reviewed (Blink, Corneo-Retinal Dipole, Saccadic Spike Potential, and Movement). For each one, it is proposed that one of the major correction methods is best matched to address it, resulting in the MAAC procedure. The MAAC itself is then presented, as implemented in the EP Toolkit, in order to provide a sense of the user experience. The primary goal of this present paper is to make the conceptual argument for the MAAC approach.

EEG signals from tinnitus sufferers at identifying their sound tinnitus

The present database contains brain activity of subjective tinnitus sufferers at identifying their sound tinnitus. The main objective of this database is to provide spontaneous Electroencephalographic (EEG) activity at rest, and evoked EEG activity when tinnitus sufferers attempt to identify their sound tinnitus among 54 tinnitus sound examples. For the database, 37 volunteers were recruited: 15 ones without tinnitus (Control Group - CG), and 22 ones with tinnitus (Tinnitus Group - TG). For EEG recording, 30 channels were used to record two conditions: 1) basal condition, where the volunteer remained in a state of rest with the open eyes for two minutes; and 2) active condition, where the volunteer must have identified his/her sound stimulus by pressing a key. For the active condition, a sound-tinnitus library was generated in accordance with the most typical acoustic properties of tinnitus. The library consisted in ten pure tones (250 Hz, 500 Hz, 1 kHz, 2 kHz, 3 kHz, 3.5 kHz, 4 kHz, 6 kHz, 8 kHz, 10 kHz), a White Noise (WN), a Narrow Band noise-High frequencies (NBH, 4 kHz-10 kHz), a Narrow Band noise-Medium frequencies (NBM,1 kHz-4 kHz), a Narrow-Band noise Low frequencies (NBL, 250 Hz-1 kHz), ten pure tones combined with WN, ten pure tones superimposed with NBH, ten tones with NBM and ten pure tones combined with NBL. In total, 54 sound-tinnitus were applied for both groups. In the case of CG, volunteers must have identified a sound at 3.5 kHz. In addition to EEG information, a csv-file with audiometric and psychoacoustic information of volunteers is provided. For TG, this information refers to: 1) hearing level, 2) type of tinnitus, 3) tinnitus frequency, 4) tinnitus perception, 5) Hospital Anxiety and Depression Scale (HADS) and 6) Tinnitus Functional Index (TFI). For CG, the information refers to: 1) hearing level, and 2) HADS.

Language prediction in monolingual and bilingual speakers: an EEG study

Prediction of upcoming words is thought to be crucial for language comprehension. Here, we are asking whether bilingualism entails changes to the electrophysiological substrates of prediction. Prior findings leave it open whether monolingual and bilingual speakers predict upcoming words to the same extent and in the same manner. We address this issue with a naturalistic approach, employing an information-theoretic metric, surprisal, to predict and contrast the N400 brain potential in monolingual and bilingual speakers. We recruited 18 Iranian Azeri-Persian bilingual speakers and 22 Persian monolingual speakers. Subjects listened to a story in Persian while their electroencephalogram (EEG) was recorded. Bayesian item-level analysis was used. While in monolingual speakers N400 was sensitive to information-theoretic properties of both the current and previous words, in bilingual speakers N400 reflected the properties of the previous word only. Our findings show evidence for a processing delay in bilingual speakers which is consistent with prior research.

Top-down task goals induce the retrieval state

Engaging the retrieval state (Tulving, 1983) impacts processing and behavior (Long & Kuhl, 2019, 2021; Smith, Moore, & Long, 2022), but the extent to which top-down factors - explicit instructions and goals - vs. bottom-up factors - stimulus properties such as repetition and similarity - jointly or independently induce the retrieval state is unclear. Identifying the impact of bottom-up and top-down factors on retrieval state engagement is critical for understanding how control of task-relevant vs. task-irrelevant brain states influence cognition. We conducted between-subjects recognition memory tasks on male and female human participants in which we varied test phase goals. We recorded scalp electroencephalography and used an independently validated mnemonic state classifier (Long, 2023) to measure retrieval state engagement as a function of top-down task goals (recognize old vs. detect new items) and bottom-up stimulus repetition (hits vs. correct rejections). We find that whereas the retrieval state is engaged for hits regardless of top-down goals, the retrieval state is only engaged during correct rejections when the top-down goal is to recognize old items. Furthermore, retrieval state engagement is greater for low compared to high confidence hits when the task goal is to recognize old items. Together, these results suggest that top-down demands to recognize old items induce the retrieval state independent from bottom-up factors, potentially reflecting the recruitment of internal attention to enable access of a stored representation.

Significance Statement

Both top-down goals and automatic bottom-up influences may lead us into a retrieval brain state - a whole-brain pattern of activity that supports our ability to remember the past. Here we tested the extent to which top-down vs. bottom-up factors independently influence the retrieval state by manipulating participants' goals and stimulus repetition during a memory test. We find that in response to the top-down goal to recognize old items, the retrieval state is engaged for both old and new probes, suggesting that top-down and bottom-up factors independently engage the retrieval state. Our interpretation is that top-down demands recruit internal attention in service of the attempt to access a stored representation.

Semantic associations restore neural encoding mechanisms

Lapses in attention can negatively impact later memory of an experience. Attention and encoding resources are thought to decline as more experiences are encountered in succession, accounting for the primacy effect in which memory is better for items encountered early compared to late in a study list. However, accessing prior knowledge during study can facilitate subsequent memory, suggesting a potential avenue to counteract this decline. Here, we investigated the extent to which semantic associations-shared meaning between experiences-can counteract declines in encoding resources. Our hypothesis is that semantic associations restore neural encoding mechanisms, which in turn improves memory. We recorded scalp electroencephalography (EEG) while male and female human participants performed a delayed free recall task. Half of the items from late in each study list were semantically associated with an item presented earlier in the list. We find that semantic associations improve memory specifically for late list items and selectively modulate the neural signals engaged during the study of late list items. Relative to other recalled items, late list items that are subsequently semantically clustered-recalled consecutively with their semantic associate-elicit increased high-frequency activity and decreased low-frequency activity, a hallmark of successful encoding. Our findings demonstrate that semantic associations restore neural encoding mechanisms and improve later memory. More broadly, these findings suggest that prior knowledge modulates the orientation of attention to influence encoding mechanisms.

Low frequency independent components: Internal neuromarkers linking cortical LFPs to behavior

Local field potentials (LFPs) in the primate motor cortex have been shown to reflect information related to volitional movements. However, LFPs are composite signals that receive contributions from multiple neural sources, producing a complex mix of component signals. Using a blind source separation approach, we examined the components of neural activity recorded using multielectrode arrays in motor areas of macaque monkeys during a grasping and lifting task. We found a set of independent components in the low-frequency LFP with high temporal and spatial consistency associated with each task stage. We observed that ICs often arise from electrodes distributed across multiple cortical areas and provide complementary information to external behavioral markers, specifically in task stage detection and trial alignment. Taken together, our results show that it is possible to separate useful independent components of the LFP associated with specific task-related events, potentially representing internal markers of transition between cortical network states.

Diagnostic deep learning algorithms that use resting EEG to distinguish major depressive disorder, bipolar disorder, and schizophrenia from each other and from healthy volunteers

BACKGROUND

Mood disorders and schizophrenia affect millions worldwide. Currently, diagnosis is primarily determined by reported symptomatology. As symptoms may overlap, misdiagnosis is common, potentially leading to ineffective or destabilizing treatment. Diagnostic biomarkers could significantly improve clinical care by reducing dependence on symptomatic presentation.

METHODS

We used deep learning analysis (DLA) of resting electroencephalograph (EEG) to differentiate healthy control (HC) subjects (N = 239), from those with major depressive disorder (MDD) (N = 105), MDD-atypical (MDD-A) (N = 27), MDD-psychotic (MDD-P) (N = 35), bipolar disorder-depressed episode (BD-DE) (N = 71), BD-manic episode (BD-ME) (N = 49), and schizophrenia (SCZ) (N = 122) and also differentiate subjects with mental disorders on a pair-wise basis. DSM-III-R diagnoses were determined and supplemented by computerized Quick Diagnostic Interview Schedule. After EEG preprocessing, robust exact low-resolution electromagnetic tomography (ReLORETA) computed EEG sources for 82 brain regions. 20 % of all subjects were then set aside for independent testing. Feature selection methods were then used for the remaining subjects to identify brain source regions that are discriminating between diagnostic categories.

RESULTS

Pair-wise classification accuracies between 90 % and 100 % were obtained using independent test subjects whose data were not used for training purposes. The most frequently selected features across various pairs are in the postcentral, supramarginal, and fusiform gyri, the hypothalamus, and the left cuneus. Brain sites discriminating SCZ from HC were mainly in the left hemisphere while those separating BD-ME from HC were on the right.

LIMITATIONS

The use of superseded DSM-III-R diagnostic system and relatively small sample size in some disorder categories that may increase the risk of overestimation.

CONCLUSIONS

DLA of EEG could be trained to autonomously classify psychiatric disorders with over 90 % accuracy compared to an expert clinical team using standardized operational methods.

Ongoing EEG artifact correction using blind source separation

OBJECTIVE

Analysis of the electroencephalogram (EEG) for epileptic spike and seizure detection or brain-computer interfaces can be severely hampered by the presence of artifacts. The aim of this study is to describe and evaluate a fast automatic algorithm for ongoing correction of artifacts in continuous EEG recordings, which can be applied offline and online.

METHODS

The automatic algorithm for ongoing correction of artifacts is based on fast blind source separation. It uses a sliding window technique with overlapping epochs and features in the spatial, temporal and frequency domain to detect and correct ocular, cardiac, muscle and powerline artifacts.

RESULTS

The approach was validated in an independent evaluation study on publicly available continuous EEG data with 2035 marked artifacts. Validation confirmed that 88% of the artifacts could be removed successfully (ocular: 81%, cardiac: 84%, muscle: 98%, powerline: 100%). It outperformed state-of-the-art algorithms both in terms of artifact reduction rates and computation time.

CONCLUSIONS

Fast ongoing artifact correction successfully removed a good proportion of artifacts, while preserving most of the EEG signals.

SIGNIFICANCE

The presented algorithm may be useful for ongoing correction of artifacts, e.g., in online systems for epileptic spike and seizure detection or brain-computer interfaces.

Response-locked theta dissociations reveal potential feedback signal following successful retrieval

Successful memory retrieval relies on memory processes to access an internal representation and decision processes to evaluate and respond to the accessed representation, both of which are supported by fluctuations in theta (4-8Hz) activity. However, the extent to which decision making processes are engaged following a memory response is unclear. Here, we recorded scalp electroencephalography (EEG) while human participants performed a recognition memory task. We focused on response-locked data, allowing us to investigate the processes that occur prior to and following a memory response. We replicate previous work and find that prior to a memory response theta power is greater for identification of previously studied items (hits) relative to rejection of novel lures (correct rejections; CRs). Following the memory response, the theta power dissociation 'flips' whereby theta power is greater for CRs relative to hits. We find that the post-response 'flip' is more robust for hits that are committed quickly, potentially reflecting a positive feedback signal for strongly remembered experiences. Our findings suggest that there are potentially distinct processes occurring before and after a memory response that are modulated by successful memory retrieval.

EEG microstates in early-to-middle childhood show associations with age, biological sex, and alpha power

Electroencephalographic (EEG) microstates can provide a unique window into the temporal dynamics of large-scale brain networks across brief (millisecond) timescales. Here, we analysed fundamental temporal features of microstates extracted from the broadband EEG signal in a large (N = 139) cohort of children spanning early-to-middle childhood (4-12 years of age). Linear regression models were used to examine if participants' age and biological sex could predict the temporal parameters GEV, duration, coverage, and occurrence, for five microstate classes (A-E) across both eyes-closed and eyes-open resting-state recordings. We further explored associations between these microstate parameters and posterior alpha power after removal of the 1/f-like aperiodic signal. The microstates obtained from our neurodevelopmental EEG recordings broadly replicated the four canonical microstate classes (A to D) frequently reported in adults, with the addition of the more recently established microstate class E. Biological sex served as a significant predictor in the regression models for four of the five microstate classes (A, C, D, and E). In addition, duration and occurrence for microstate E were both found to be positively associated with age for the eyes-open recordings, while the temporal parameters of microstates C and E both exhibited associations with alpha band spectral power. Together, these findings highlight the influence of age and sex on large-scale functional brain networks during early-to-middle childhood, extending understanding of neural dynamics across this important period for brain development.

Evaluating the effectiveness of artifact correction and rejection in event-related potential research

Eyeblinks and other large artifacts can create two major problems in event-related potential (ERP) research, namely confounds and increased noise. Here, we developed a method for assessing the effectiveness of artifact correction and rejection methods at minimizing these two problems. We then used this method to assess a common artifact minimization approach, in which independent component analysis (ICA) is used to correct ocular artifacts, and artifact rejection is used to reject trials with extreme values resulting from other sources (e.g., movement artifacts). This approach was applied to data from five common ERP components (P3b, N400, N170, mismatch negativity, and error-related negativity). Four common scoring methods (mean amplitude, peak amplitude, peak latency, and 50% area latency) were examined for each component. We found that eyeblinks differed systematically across experimental conditions for several of the components. We also found that artifact correction was reasonably effective at minimizing these confounds, although it did not usually eliminate them completely. In addition, we found that the rejection of trials with extreme voltage values was effective at reducing noise, with the benefits of eliminating these trials outweighing the reduced number of trials available for averaging. For researchers who are analyzing similar ERP components and participant populations, this combination of artifact correction and rejection approaches should minimize artifact-related confounds and lead to improved data quality. Researchers who are analyzing other components or participant populations can use the method developed in this study to determine which artifact minimization approaches are effective in their data.

Subhairline Electroencephalography for the Detection of Large Vessel Occlusion Stroke

BACKGROUND

Endovascular thrombectomy is standard treatment for patients with anterior circulation large vessel occlusion stroke (LVO-a). Prehospital identification of these patients would enable direct routing to an endovascular thrombectomy-capable hospital and consequently reduce time-to-endovascular thrombectomy. Electroencephalography (EEG) has previously proven to be promising for LVO-a stroke detection. Fast and reliable electrode application, however, can remain a challenge. A potential alternative is subhairline EEG. We evaluated the diagnostic accuracy of subhairline EEG for LVO-a stroke detection.

METHODS AND RESULTS

We included adult patients with a suspected stroke or known LVO-a stroke and symptom onset time <24 hours. A single 3-minute EEG recording was performed at the emergency department, before endovascular thrombectomy, using 9 self-adhesive electrodes placed on the forehead and behind the ears. We evaluated the diagnostic accuracies of EEG features quantifying frequency band power and brain symmetry (pairwise derived Brain Symmetry Index) for LVO-a stroke detection using receiver operating characteristic analysis. EEG data were of sufficient quality for analysis in 51/52 (98%) included patients. Of these patients, 16 (31%) had an LVO-a stroke, 16 (31%) a non-LVO-a ischemic stroke, 5 (10%) a transient ischemic attack, and 14 (27%) a stroke mimic. Median symptom-onset-to-EEG-time was 266 (interquartile range 130-709) minutes. The highest diagnostic accuracy for LVO-a stroke detection was reached by the pairwise derived Brain Symmetry Index in the theta frequency band (area under the receiver operating characteristic curve 0.90; sensitivity 86%; specificity 83%).

CONCLUSIONS

Subhairline EEG could detect LVO-a stroke with high diagnostic accuracy and had high data reliability. These data suggest that subhairline EEG is potentially suitable as a prehospital stroke triage instrument.

Obsessive-compulsive disorder (OCD) is associated with increased engagement of frontal brain regions across multiple event-related potentials

BACKGROUND

Obsessive-compulsive disorder (OCD) is a psychiatric condition leading to significant distress and poor quality of life. Successful treatment of OCD is restricted by the limited knowledge about its pathophysiology. This study aimed to investigate the pathophysiology of OCD using electroencephalographic (EEG) event-related potentials (ERPs), elicited from multiple tasks to characterise disorder-related differences in underlying brain activity across multiple neural processes.

METHODS

ERP data were obtained from 25 OCD patients and 27 age- and sex-matched healthy controls (HCs) by recording EEG during flanker and go/nogo tasks. Error-related negativity (ERN) was elicited by the flanker task, while N200 and P300 were generated using the go/nogo task. Primary comparisons of the neural response amplitudes and the topographical distribution of neural activity were conducted using scalp field differences across all time points and electrodes.

RESULTS

Compared to HCs, the OCD group showed altered ERP distributions. Contrasting with the previous literature on ERN and N200 topographies in OCD where fronto-central negative voltages were reported, we detected positive voltages. Additionally, the P300 was found to be less negative in the frontal regions. None of these ERP findings were associated with OCD symptom severity.

CONCLUSIONS

These results indicate that individuals with OCD show altered frontal neural activity across multiple executive function-related processes, supporting the frontal dysfunction theory of OCD. Furthermore, due to the lack of association between altered ERPs and OCD symptom severity, they may be considered potential candidate endophenotypes for OCD.

Videoconference fatigue from a neurophysiological perspective: experimental evidence based on electroencephalography (EEG) and electrocardiography (ECG)

In the recent past, many organizations and people have substituted face-to-face meetings with videoconferences. Among others, tools like Zoom, Teams, and Webex have become the "new normal" of human social interaction in many domains (e.g., business, education). However, this radical adoption and extensive use of videoconferencing tools also has a dark side, referred to as videoconference fatigue (VCF). To date only self-report evidence has shown that VCF is a serious issue. However, based on self-reports alone it is hardly possible to provide a comprehensive understanding of a cognitive phenomenon like VCF. Against this background, we examined VCF also from a neurophysiological perspective. Specifically, we collected and analyzed electroencephalography (continuous and event-related) and electrocardiography (heart rate and heart rate variability) data to investigate whether VCF can also be proven on a neurophysiological level. We conducted a laboratory experiment based on a within-subjects design (N = 35). The study context was a university lecture, which was given in a face-to-face and videoconferencing format. In essence, the neurophysiological data-together with questionnaire data that we also collected-show that 50 min videoconferencing, if compared to a face-to-face condition, results in changes in the human nervous system which, based on existing literature, can undoubtedly be interpreted as fatigue. Thus, individuals and organizations must not ignore the fatigue potential of videoconferencing. A major implication of our study is that videoconferencing should be considered as a possible complement to face-to-face interaction, but not as a substitute.

EEG source functional connectivity in patients after a recent suicide attempt

OBJECTIVE

Electroencephalogram (EEG) based frequency measures within the alpha frequency range (AFR), including functional connectivity, show potential in assessing the underlying pathophysiology of depression and suicide-related outcomes. We investigated the association between AFR connectivity, suicidal thoughts and behaviors, and depression in a transdiagnostic sample of patients after a recent suicide attempt (SA).

METHODS

Lagged source-based measures of linear and nonlinear whole-brain connectivity within the standard AFR ([sAFR], 8-12 Hz) and the individually referenced AFR (iAFR) were applied to 70 15-minute resting-state EEGs from patients after a SA and 70 age- and gender-matched healthy controls (HC). Hypotheses were tested using network-based statistics and multiple regression models.

RESULTS

Results showed no significant differences between patients after a SA and HC in any of the assessed connectivity modalities. However, a subgroup analysis revealed significantly increased nonlinear connectivity within the sAFR for patients after a SA with a depressive disorder or episode ([DD], n = 53) compared to matched HC. Furthermore, a multiple regression model, including significant main effects for group and global nonlinear connectivity within the sAFR outperformed all other models in explaining variance in depressive symptom severity.

CONCLUSIONS

Our study further supports the importance of the AFR in pathomechanisms of suicidality and depression. The iAFR does not seem to improve validity of phase-based connectivity.

SIGNIFICANCE

Our results implicate distinct neurophysiological patterns in suicidal subgroups. Exploring the potential of these patterns for treatment stratification might advance targeted interventions for suicidal thoughts and behaviors.

Tracking gaze position from EEG: Exploring the possibility of an EEG-based virtual eye-tracker

INTRODUCTION

Ocular artifact has long been viewed as an impediment to the interpretation of electroencephalogram (EEG) signals in basic and applied research. Today, the use of blind source separation (BSS) methods, including independent component analysis (ICA) and second-order blind identification (SOBI), is considered an essential step in improving the quality of neural signals. Recently, we introduced a method consisting of SOBI and a discriminant and similarity (DANS)-based identification method, capable of identifying and extracting eye movement-related components. These recovered components can be localized within ocular structures with a high goodness of fit (>95%). This raised the possibility that such EEG-derived SOBI components may be used to build predictive models for tracking gaze position.

METHODS

As proof of this new concept, we designed an EEG-based virtual eye-tracker (EEG-VET) for tracking eye movement from EEG alone. The EEG-VET is composed of a SOBI algorithm for separating EEG signals into different components, a DANS algorithm for automatically identifying ocular components, and a linear model to transfer ocular components into gaze positions.

RESULTS

The prototype of EEG-VET achieved an accuracy of 0.920° and precision of 1.510° of a visual angle in the best participant, whereas an average accuracy of 1.008° ± 0.357° and a precision of 2.348° ± 0.580° of a visual angle across all participants (N = 18).

CONCLUSION

This work offers a novel approach that readily co-registers eye movement and neural signals from a single-EEG recording, thus increasing the ease of studying neural mechanisms underlying natural cognition in the context of free eye movement.

BrainWave-Scattering Net: a lightweight network for EEG-based motor imagery recognition

Objective.Brain-computer interfaces (BCIs) enable a direct communication of the brain with the external world, using one's neural activity, measured by electroencephalography (EEG) signals. In recent years, convolutional neural networks (CNNs) have been widely used to perform automatic feature extraction and classification in various EEG-based tasks. However, their undeniable benefits are counterbalanced by the lack of interpretability properties as well as the inability to perform sufficiently when only limited amount of training data is available.Approach.In this work, we introduce a novel, lightweight, fully-learnable neural network architecture that relies on Gabor filters to delocalize EEG signal information into scattering decomposition paths along frequency and slow-varying temporal modulations.Main results.We utilize our network in two distinct modeling settings, for building either a generic (training across subjects) or a personalized (training within a subject) classifier.Significance.In both cases, using two different publicly available datasets and one in-house collected dataset, we demonstrate high performance for our model with considerably less number of trainable parameters as well as shorter training time compared to other state-of-the-art deep architectures. Moreover, our network demonstrates enhanced interpretability properties emerging at the level of the temporal filtering operation and enables us to train efficient personalized BCI models with limited amount of training data.

Spatiotemporal Dynamics of Memory Encoding and Memory Retrieval States

Memory encoding and memory retrieval are neurally distinct brain states that can be differentiated on the basis of cortical network activity. However, it is unclear whether sustained engagement of one network or fluctuations between multiple networks give rise to these memory states. The spatiotemporal dynamics of memory states may have important implications for memory behavior and cognition; however, measuring temporally resolved signals of cortical networks poses a challenge. Here, we recorded scalp electroencephalography from participants performing a mnemonic state task in which they were biased toward memory encoding or retrieval. We performed a microstate analysis to measure the temporal dynamics of cortical networks throughout this mnemonic state task. We find that Microstate E, a putative analog of the default mode network, shows temporally sustained dissociations between memory encoding and retrieval, with greater engagement during retrieve compared with encode trials. We further show that decreased engagement of Microstate E is a general property of encoding, rather than a reflection of retrieval suppression. Thus, memory success, as well as cognition more broadly, may be influenced by the ability to engage or disengage Microstate E in a goal-dependent manner.

The developmental trajectory of functional excitation-inhibition balance relates to language abilities in autistic and allistic children

Autism is a neurodevelopmental condition that has been related to an overall imbalance between the brain's excitatory (E) and inhibitory (I) systems. Such an EI imbalance can lead to structural and functional cortical deviances and thus alter information processing in the brain, ultimately giving rise to autism traits. However, the developmental trajectory of EI imbalances across childhood and adolescence has not been investigated yet. Therefore, its relationship to autism traits is not well understood. In the present study, we determined a functional measure of the EI balance (f-EIB) from resting-state electrophysiological recordings for a final sample of 92 autistic children from 6 to 17 years of age and 100 allistic (i.e., non-autistic) children matched by age, sex, and nonverbal-IQ. We related the developmental trajectory of f-EIB to behavioral assessments of autism traits as well as language ability. Our results revealed differential EI trajectories for autistic compared to allistic children. Importantly, the developmental trajectory of f-EIB values related to individual language ability. In particular, elevated excitability in late childhood and early adolescence was linked to decreased listening comprehension. Our findings provide evidence against a general EI imbalance in autistic children when correcting for non-verbal IQ. Instead, we show that the developmental trajectory of EI balance shares variance with autism trait development at a specific age range. This is consistent with the proposal that the late development of inhibitory brain activity is a key substrate of autism traits.

In-the-Wild Affect Analysis of Children with ASD Using Heart Rate

Recognizing the affective state of children with autism spectrum disorder (ASD) in real-world settings poses challenges due to the varying head poses, illumination levels, occlusion and a lack of datasets annotated with emotions in in-the-wild scenarios. Understanding the emotional state of children with ASD is crucial for providing personalized interventions and support. Existing methods often rely on controlled lab environments, limiting their applicability to real-world scenarios. Hence, a framework that enables the recognition of affective states in children with ASD in uncontrolled settings is needed. This paper presents a framework for recognizing the affective state of children with ASD in an in-the-wild setting using heart rate (HR) information. More specifically, an algorithm is developed that can classify a participant's emotion as positive, negative, or neutral by analyzing the heart rate signal acquired from a smartwatch. The heart rate data are obtained in real time using a smartwatch application while the child learns to code a robot and interacts with an avatar. The avatar assists the child in developing communication skills and programming the robot. In this paper, we also present a semi-automated annotation technique based on facial expression recognition for the heart rate data. The HR signal is analyzed to extract features that capture the emotional state of the child. Additionally, in this paper, the performance of a raw HR-signal-based emotion classification algorithm is compared with a classification approach based on features extracted from HR signals using discrete wavelet transform (DWT). The experimental results demonstrate that the proposed method achieves comparable performance to state-of-the-art HR-based emotion recognition techniques, despite being conducted in an uncontrolled setting rather than a controlled lab environment. The framework presented in this paper contributes to the real-world affect analysis of children with ASD using HR information. By enabling emotion recognition in uncontrolled settings, this approach has the potential to improve the monitoring and understanding of the emotional well-being of children with ASD in their daily lives.

Spectral features of resting-state EEG in Parkinson's Disease: A multicenter study using functional data analysis

OBJECTIVE

This study aims 1) To analyse differences in resting-state electroencephalogram (rs-EEG) spectral features of Parkinson's Disease (PD) and healthy subjects (non-PD) using Functional Data Analysis (FDA) and 2) To explore, in four independent cohorts, the external validity and reproducibility of the findings using both epoch-to-epoch FDA and averaged-epochs approach.

METHODS

We included 169 subjects (85 non-PD; 84 PD) from four centres. Rs-EEG signals were preprocessed with a combination of automated pipelines. Sensor-level relative power spectral density (PSD), dominant frequency (DF), and DF variability (DFV) features were extracted. Differences in each feature were compared between PD and non-PD on averaged epochs and using FDA to model the epoch-to-epoch change of each feature.

RESULTS

For averaged epochs, significantly higher theta relative PSD in PD was found across all datasets. Also, higher pre-alpha relative PSD was observed in three of four datasets in PD patients. For FDA, similar findings were achieved in theta, but all datasets showed consistently significant posterior pre-alpha differences across multiple epochs.

CONCLUSIONS

Increased generalised theta, with posterior pre-alpha relative PSD, was the most reproducible finding in PD.

SIGNIFICANCE

Rs-EEG theta and pre-alpha findings are generalisable in PD. FDA constitutes a reliable and powerful tool to analyse epoch-to-epoch the rs-EEG.

Classification of children with ADHD through task-related EEG recordings via Swarm-Decomposition-based Phase Locking Value. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2023;2023:1-5. [PMID: 38082916 DOI: 10.1109/embc40787.2023.10340329] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

Attention Deficit/Hyperactivity Disorder (ADHD) is a common neurodevelopmental disorder mainly affecting children. ADHD children brain activity is reported to present alterations from neurotypically developed children, yet establishment of an EEG biomarker, which is of high importance in clinical practice and research, has not been achieved. In this work, task-related EEG recordings from 61 ADHD and 60 age-matched non-ADHD children are analyzed to examine the underlying Cross-Frequency Coupling phenomena. The proposed framework introduces personalized brain rhythm extraction in the form of oscillatory modes via Swarm Decomposition, allowing for the transition from sensor-level connectivity to source-level connectivity. Oscillatory modes are then subjected to a phase locking value-based feature extraction and the efficiency of the extracted features in separating ADHD from non-ADHD individuals is evaluated by means of a nested 5-fold cross validation scheme. The experimental results of the proposed framework (Area Under the Receiver Operating Characteristics Curve-AUROC: 0.9166) when benchmarked against the commonly used filter-based brain rhythm extraction (AUROC: 0.8361) underscore its efficiency and demonstrate its overall superiority over other state-of-the-art functional connectivity approaches in this classification task for this dataset.Clinical relevance-This framework provides novel insights about brain regions of interest that are involved in ADHD task-related function and holds promise in providing objective ADHD biomarkers by extending classic sensor-level connectivity to source-level.

Machine Learning-Based Detection of Parkinson's Disease From Resting-State EEG: A Multi-Center Study

Resting-state EEG (rs-EEG) has been demonstrated to aid in Parkinson's disease (PD) diagnosis. In particular, the power spectral density (PSD) of low-frequency bands (δ and θ) and high-frequency bands (α and β) has been shown to be significantly different in patients with PD as compared to subjects without PD (non-PD). However, rs-EEG feature extraction and the interpretation thereof can be time-intensive and prone to examiner variability. Machine learning (ML) has the potential to automatize the analysis of rs-EEG recordings and provides a supportive tool for clinicians to ease their workload. In this work, we use rs-EEG recordings of 84 PD and 85 non-PD subjects pooled from four datasets obtained at different centers. We propose an end-to-end pipeline consisting of preprocessing, extraction of PSD features from clinically-validated frequency bands, and feature selection. Following, we assess the classification ability of the features via ML algorithms to stratify between PD and non-PD subjects. Further, we evaluate the effect of feature harmonization, given the multi-center nature of the datasets. Our validation results show, on average, an improvement in PD detection ability (69.6% vs. 75.5% accuracy) by logistic regression when harmonizing the features and performing univariate feature selection (k = 202 features). Our final results show an average global accuracy of 72.2% with balanced accuracy results for all the centers included in the study: 60.6%, 68.7%, 77.7%, and 82.2%, respectively.Clinical relevance- We present an end-to-end pipeline to extract clinically relevant features from rs-EEG recordings that can facilitate the analysis and detection of PD. Further, we provide an ML system that shows a good performance in detecting PD, even in the presence of centers with different acquisition protocols. Our results show the relevance of harmonizing features and provide a good starting point for future studies focusing on rs-EEG analysis and multi-center data.

Obsessive-compulsive disorder (OCD) is associated with increased electroencephalographic (EEG) delta and theta oscillatory power but reduced delta connectivity

Obsessive-Compulsive Disorder (OCD) is a mental health condition causing significant decline in the quality of life of sufferers and the limited knowledge on the pathophysiology hinders successful treatment. The aim of the current study was to examine electroencephalographic (EEG) findings of OCD to broaden our understanding of the disease. Resting-state eyes-closed EEG data was recorded from 25 individuals with OCD and 27 healthy controls (HC). The 1/f arrhythmic activity was removed prior to computing oscillatory powers of all frequency bands (delta, theta, alpha, beta, gamma). Cluster-based permutation was used for between-group statistical analyses, and comparisons were performed for the 1/f slope and intercept parameters. Functional connectivity (FC) was measured using coherence and debiased weighted phase lag index (d-wPLI), and statistically analyzed using the Network Based Statistic method. Compared to HC, the OCD group showed increased oscillatory power in the delta and theta bands in the fronto-temporal and parietal brain regions. However, there were no significant between-group findings in other bands or 1/f parameters. The coherence measure showed significantly reduced FC in the delta band in OCD compared to HC but the d-wPLI analysis showed no significant differences. OCD is associated with raised oscillatory power in slow frequency bands in the fronto-temporal brain regions, which agrees with the previous literature and therefore is a potential biomarker. Although delta coherence was found to be lower in OCD, due to inconsistencies found between measures and the previous literature, further research is required to ascertain definitive conclusions.

The intersection of the retrieval state and internal attention

Large-scale brain states or distributed patterns of brain activity modulate downstream processing and behavior. Sustained attention and memory retrieval states impact subsequent memory, yet how these states relate to one another is unclear. I hypothesize that internal attention is a central process of the retrieval state. The alternative is that the retrieval state specifically reflects a controlled, episodic retrieval mode, engaged only when intentionally accessing events situated within a spatiotemporal context. To test my hypothesis, I developed a mnemonic state classifier independently trained to measure retrieval state evidence and applied this classifier to a spatial attention task. I find that retrieval state evidence increases during delay and response intervals when participants are maintaining spatial information. Critically, retrieval state evidence is positively related to the amount of maintained spatial location information and predicts target detection reaction times. Together, these findings support the hypothesis that internal attention is a central process of the retrieval state.

Comparative analysis of acoustic therapies for tinnitus treatment based on auditory event-related potentials

Introduction

So far, Auditory Event-Related Potential (AERP) features have been used to characterize neural activity of patients with tinnitus. However, these EEG patterns could be used to evaluate tinnitus evolution as well. The aim of the present study is to propose a methodology based on AERPs to evaluate the effectiveness of four acoustic therapies for tinnitus treatment.

Methods

The acoustic therapies were: (1) Tinnitus Retraining Therapy (TRT), (2) Auditory Discrimination Therapy (ADT), (3) Therapy for Enriched Acoustic Environment (TEAE), and (4) Binaural Beats Therapy (BBT). In addition, relaxing music was included as a placebo for both: tinnitus sufferers and healthy individuals. To meet this aim, 103 participants were recruited, 53% were females and 47% were males. All the participants were treated for 8 weeks with one of these five sounds, which were moreover tuned in accordance with the acoustic features of their tinnitus (if applied) and hearing loss. They were electroencephalographically monitored before and after their acoustic therapy, and wherefrom AERPs were estimated. The sound effect of acoustic therapies was evaluated by examining the area under the curve of those AERPs. Two parameters were obtained: (1) amplitude and (2) topographical distribution.

Results

The findings of the investigation showed that after an 8-week treatment, TRT and ADT, respectively achieved significant neurophysiological changes over somatosensory and occipital regions. On one hand, TRT increased the tinnitus perception. On the other hand, ADT redirected the tinnitus attention, what in turn diminished the tinnitus perception. Tinnitus handicapped inventory outcomes verified these neurophysiological findings, revealing that 31% of patients in each group reported that TRT increased tinnitus perception, but ADT diminished it.

Discussion

Tinnitus has been identified as a multifactorial condition highly associated with hearing loss, age, sex, marital status, education, and even, employment. However, no conclusive evidence has been found yet. In this study, a significant (but low) correlation was found between tinnitus intensity and right ear hearing loss, left ear hearing loss, heart rate, area under the curve of AERPs, and acoustic therapy. This study raises the possibility to assign acoustic therapies by neurophysiological response of patient.

An Adaptive Joint CCA-ICA Method for Ocular Artifact Removal and its Application to Emotion Classification

BACKGROUND

The quality of Electroencephalogram (EEG) signals is critical for revealing the neural mechanism of emotions. However, ocular artifacts decreased the signal to noise ratio (SNR) and covered the inherent cognitive component of EEGs, which pose a great challenge in neuroscience research.

NEW METHOD

We proposed a novel unsupervised learning algorithm to adaptively remove the ocular artifacts by combining canonical correlation analysis (CCA), independent component analysis (ICA), higher-order statistics, empirical mode decomposition (EMD), and wavelet denoising techniques. Specifically, the combination of CCA and ICA aimed to improve the quality of source separation, while the higher-order statistics further located the source of ocular artifacts. Subsequently, these noised sources were further corrected by EMD and wavelet denoising to improve SNR of EEG signals.

RESULTS

We evaluated the performance of our proposed method with simulation studies and real EEG applications. The results of simulation study showed our proposed method could significantly improve the quality of signals under almost all noise conditions compared to four state-of-art methods. Consistently, the experiments of real EEG applications showed that the proposed methods could efficiently restrict the components of ocular artifacts and preserve the inherent information of cognition processing to improve the reliability of related analysis such as power spectral density (PSD) and emotion recognition.

COMPARISON WITH EXISTING METHODS

Our proposed model outperforms the comparative methods in EEG recovery, which further improve the application performance such as PSD analysis and emotion recognition.

CONCLUSIONS

The superior performance of our proposed method suggests that it is promising for removing ocular artifacts from EEG signals, which offers an efficient EEG preprocessing technology for the development of brain computer interface such as emotion recognition.

Which Multivariate Multi-Scale Entropy Algorithm Is More Suitable for Analyzing the EEG Characteristics of Mild Cognitive Impairment?

So far, most articles using the multivariate multi-scale entropy algorithm mainly use algorithms to analyze the multivariable signal complexity without clearly describing what characteristics of signals these algorithms measure and what factors affect these algorithms. This paper analyzes six commonly used multivariate multi-scale entropy algorithms from a new perspective. It clarifies for the first time what characteristics of signals these algorithms measure and which factors affect them. It also studies which algorithm is more suitable for analyzing mild cognitive impairment (MCI) electroencephalograph (EEG) signals. The simulation results show that the multivariate multi-scale sample entropy (mvMSE), multivariate multi-scale fuzzy entropy (mvMFE), and refined composite multivariate multi-scale fuzzy entropy (RCmvMFE) algorithms can measure intra- and inter-channel correlation and multivariable signal complexity. In the joint analysis of coupling and complexity, they all decrease with the decrease in signal complexity and coupling strength, highlighting their advantages in processing related multi-channel signals, which is a discovery in the simulation. Among them, the RCmvMFE algorithm can better distinguish different complexity signals and correlations between channels. It also performs well in anti-noise and length analysis of multi-channel data simultaneously. Therefore, we use the RCmvMFE algorithm to analyze EEG signals from twenty subjects (eight control subjects and twelve MCI subjects). The results show that the MCI group had lower entropy than the control group on the short scale and the opposite on the long scale. Moreover, frontal entropy correlates significantly positively with the Montreal Cognitive Assessment score and Auditory Verbal Learning Test delayed recall score on the short scale.

RELAX part 2: A fully automated EEG data cleaning algorithm that is applicable to Event-Related-Potentials

OBJECTIVE

Electroencephalography (EEG) is often used to examine neural activity time-locked to stimuli presentation, referred to as Event-Related Potentials (ERP). However, EEG is influenced by non-neural artifacts, which can confound ERP comparisons. Artifact cleaning reduces artifacts, but often requires time-consuming manual decisions. Most automated methods filter frequencies <1 Hz out of the data, so are not recommended for ERPs (which contain frequencies <1 Hz). Our aim was to test the RELAX (Reduction of Electroencephalographic Artifacts) pre-processing pipeline for use on ERP data.

METHODS

The cleaning performance of multiple versions of RELAX were compared to four commonly used EEG cleaning pipelines across both artifact cleaning metrics and the amount of variance in ERPs explained by different conditions in a Go-Nogo task. Results RELAX with Multi-channel Wiener Filtering (MWF) and wavelet-enhanced independent component analysis applied to artifacts identified with ICLabel (wICA_ICLabel) cleaned data most effectively and produced amongst the most dependable ERP estimates. RELAX with wICA_ICLabel only or MWF_only may detect effects better for some ERPs.

CONCLUSIONS

RELAX shows high artifact cleaning performance even when data is high-pass filtered at 0.25 Hz (applicable to ERP analyses).

SIGNIFICANCE

RELAX is easy to implement via EEGLAB in MATLAB and freely available on GitHub. Given its performance and objectivity we recommend RELAX to improve artifact cleaning and consistency across ERP research.

Introducing RELAX: An automated pre-processing pipeline for cleaning EEG data - Part 1: Algorithm and application to oscillations

OBJECTIVE

Electroencephalographic (EEG) data are often contaminated with non-neural artifacts which can confound experimental results. Current artifact cleaning approaches often require costly manual input. Our aim was to provide a fully automated EEG cleaning pipeline that addresses all artifact types and improves measurement of EEG outcomes METHODS: We developed RELAX (the Reduction of Electroencephalographic Artifacts). RELAX cleans continuous data using Multi-channel Wiener filtering [MWF] and/or wavelet enhanced independent component analysis [wICA] applied to artifacts identified by ICLabel [wICA_ICLabel]). Several versions of RELAX were compared using three datasets (N = 213, 60 and 23 respectively) against six commonly used pipelines across a range of artifact cleaning metrics, including measures of remaining blink and muscle activity, and the variance explained by experimental manipulations after cleaning.

RESULTS

RELAX with MWF and wICA_ICLabel showed amongst the best performance at cleaning blink and muscle artifacts while preserving neural signal. RELAX with wICA_ICLabel only may perform better at differentiating alpha oscillations between working memory conditions.

CONCLUSIONS

RELAX provides automated, objective and high-performing EEG cleaning, is easy to use, and freely available on GitHub.

SIGNIFICANCE

We recommend RELAX for data cleaning across EEG studies to reduce artifact confounds, improve outcome measurement and improve inter-study consistency.

Using CNN Saliency Maps and EEG Modulation Spectra for Improved and More Interpretable Machine Learning-Based Alzheimer's Disease Diagnosis

Biomarkers based on resting-state electroencephalography (EEG) signals have emerged as a promising tool in the study of Alzheimer's disease (AD). Recently, a state-of-the-art biomarker was found based on visual inspection of power modulation spectrograms where three "patches" or regions from the modulation spectrogram were proposed and used for AD diagnostics. Here, we propose the use of deep neural networks, in particular convolutional neural networks (CNNs) combined with saliency maps, trained on power modulation spectrogram inputs to find optimal patches in a data-driven manner. Experiments are conducted on EEG data collected from fifty-four participants, including 20 healthy controls, 19 patients with mild AD, and 15 moderate-to-severe AD patients. Five classification tasks are explored, including the three-class problem, early-stage detection (control vs. mild-AD), and severity level detection (mild vs. moderate-to-severe). Experimental results show the proposed biomarkers outperform the state-of-the-art benchmark across all five tasks, as well as finding complementary modulation spectrogram regions not previously seen via visual inspection. Lastly, experiments are conducted on the proposed biomarkers to test their sensitivity to age, as this is a known confound in AD characterization. Across all five tasks, none of the proposed biomarkers showed a significant relationship with age, thus further highlighting their usefulness for automated AD diagnostics.

Discriminating between bipolar and major depressive disorder using a machine learning approach and resting-state EEG data

OBJECTIVE

Distinguishing major depressive disorder (MDD) from bipolar disorder (BD) is a crucial clinical challenge as effective treatment is quite different for each condition. In this study electroencephalography (EEG) was explored as an objective biomarker for distinguishing MDD from BD using an efficient machine learning algorithm (MLA) trained by a relatively large and balanced dataset.

METHODS

A 3 step MLA was applied: (1) a multi-step preprocessing method was used to improve the quality of the EEG signal, (2) symbolic transfer entropy (STE), an effective connectivity measure, was applied to the resultant EEG and (3) the MLA used the extracted STE features to distinguish MDD (N = 71) from BD (N = 71) subjects.

RESULTS

14 connectivity features were selected by the proposed algorithm. Most of the selected features were related to the frontal, parietal, and temporal lobe electrodes. The major involved regions were the Broca region in the frontal lobe and the somatosensory association cortex in the parietal lobe. These regions are near electrodes FC5 and CPz and are involved in processing language and sensory information, respectively. The resulting classifier delivered an evaluation accuracy of 88.5% and a test accuracy of 89.3%, using 80% of the data for training and evaluation and the remaining 20% for testing, respectively.

CONCLUSIONS

The high evaluation and test accuracies of our algorithm, derived from a large balanced training sample suggests that this method may hold significant promise as a clinical tool.

SIGNIFICANCE

The proposed MLA may provide an inexpensive and readily available tool that clinicians may use to enhance diagnostic accuracy and shorten time to effective treatment.

Optimized adaptive neuro-fuzzy inference system based on hybrid grey wolf-bat algorithm for schizophrenia recognition from EEG signals

Schizophrenia is a chronic mental disorder that impairs a person's thinking capacity, feelings and emotions, behavioural traits, etc., Emotional distortions, delusions, hallucinations, and incoherent speech are all some of the symptoms of schizophrenia, and cause disruption of routine activities. Computer-assisted diagnosis of schizophrenia is significantly needed to give its patients a higher quality of life. Hence, an improved adaptive neuro-fuzzy inference system based on the Hybrid Grey Wolf-Bat Algorithm for accurate prediction of schizophrenia from multi-channel EEG signals is presented in this study. The EEG signals are pre-processed using a Butterworth band pass filter and wICA initially, from which statistical, time-domain, frequency-domain, and spectral features are extracted. Discriminating features are selected using the ReliefF algorithm and are then forwarded to ANFIS for classification into either schizophrenic or normal. ANFIS is optimized by the Hybrid Grey Wolf-Bat Algorithm (HWBO) for better efficiency. The method is experimented on two separate EEG datasets-1 and 2, demonstrating an accuracy of 99.54% and 99.35%, respectively, with appreciable F1-score and MCC. Further experiments reveal the efficiency of the Hybrid Wolf-Bat algorithm in optimizing the ANFIS parameters when compared with traditional ANFIS model and other proven algorithms like genetic algorithm-ANFIS, particle optimization-ANFIS, crow search optimization algorithm-ANFIS and ant colony optimization algorithm-ANFIS, showing high R2 value and low RSME value. To provide a bias free classification, tenfold cross validation is performed which produced an accuracy of 97.8% and 98.5% on the two datasets respectively. Experimental outcomes demonstrate the superiority of the Hybrid Grey Wolf-Bat Algorithm over the similar techniques in predicting schizophrenia.

Circulant Singular Spectrum Analysis and Discrete Wavelet Transform for Automated Removal of EOG Artifacts from EEG Signals

Background: Portable electroencephalogram (EEG) systems are often used in health care applications to record brain signals because their ease of use. An electrooculogram (EOG) is a common, low frequency, high amplitude artifact of the eye blink signal that might confuse disease diagnosis. As a result, artifact removal approaches in single EEG portable devices are in high demand. Materials: Dataset 2a from the BCI Competition IV was employed. It contains the EEG data from nine subjects. To determine the EOG effect, each session starts with 5 min of EEG data. This recording lasted for two minutes with the eyes open, one minute with the eyes closed, and one minute with eye movements. Methodology: This article presents the automated removal of EOG artifacts from EEG signals. Circulant Singular Spectrum Analysis (CiSSA) was used to decompose the EOG contaminated EEG signals into intrinsic mode functions (IMFs). Next, we identified the artifact signal components using kurtosis and energy values and removed them using 4-level discrete wavelet transform (DWT). Results: The proposed approach was evaluated on synthetic and real EEG data and found to be effective in eliminating EOG artifacts while maintaining low frequency EEG information. CiSSA-DWT achieved the best signal to artifact ratio (SAR), mean absolute error (MAE), relative root mean square error (RRMSE), and correlation coefficient (CC) of 1.4525, 0.0801, 18.274, and 0.9883, respectively. Comparison: The developed technique outperforms existing artifact suppression techniques according to performance measures. Conclusions: This advancement is important for brain science and can contribute as an initial pre-processing step for research related to EEG signals.

Estimating the Depth of Anesthesia from EEG Signals Based on a Deep Residual Shrinkage Network

The reliable monitoring of the depth of anesthesia (DoA) is essential to control the anesthesia procedure. Electroencephalography (EEG) has been widely used to estimate DoA since EEG could reflect the effect of anesthetic drugs on the central nervous system (CNS). In this study, we propose that a deep learning model consisting mainly of a deep residual shrinkage network (DRSN) and a 1 × 1 convolution network could estimate DoA in terms of patient state index (PSI) values. First, we preprocessed the four raw channels of EEG signals to remove electrical noise and other physiological signals. The proposed model then takes the preprocessed EEG signals as inputs to predict PSI values. Then we extracted 14 features from the preprocessed EEG signals and implemented three conventional feature-based models as comparisons. A dataset of 18 patients was used to evaluate the models' performances. The results of the five-fold cross-validation show that there is a relatively high similarity between the ground-truth PSI values and the predicted PSI values of our proposed model, which outperforms the conventional models, and further, that the Spearman's rank correlation coefficient is 0.9344. In addition, an ablation experiment was conducted to demonstrate the effectiveness of the soft-thresholding module for EEG-signal processing, and a cross-subject validation was implemented to illustrate the robustness of the proposed method. In summary, the procedure is not merely feasible for estimating DoA by mimicking PSI values but also inspired us to develop a precise DoA-estimation system with more convincing assessments of anesthetization levels.