Resting-state electroencephalography based deep-learning for the detection of Parkinson's disease

Parkinson's disease (PD) is one of the most serious and challenging neurodegenerative disorders to diagnose. Clinical diagnosis on observing motor symptoms is the gold standard, yet by this point nerve cells are degenerated resulting in a lower efficacy of therapeutic treatments. In this study, we introduce a deep-learning approach based on a recently-proposed 20-Layer Convolutional Neural Network (CNN) applied on the visual realization of the Wavelet domain of a resting-state EEG. The proposed approach was able to efficiently and accurately detect PD as well as distinguish subjects with PD on medications from subjects who are off medication. The gradient-weighted class activation mapping (Grad-CAM) was used to visualize the features based on which the approach provided the predictions. A significantly high accuracy, sensitivity, specificity, AUC, and Weighted Kappa Score up to 99.9% were achieved and the visualization of the regions in the Wavelet images that contributed to the deep-learning approach decisions was provided. The proposed framework can then serve as an effective computer-aided diagnostic tool that will support physicians and scientists in further understanding the nature of PD and providing an objective and confident opinion regarding the clinical diagnosis of the disease.

Intelligent Algorithm-Based Quantitative Electroencephalography in Evaluating Cerebral Small Vessel Disease Complicated by Cognitive Impairment

To analyze the application value of artificial intelligence model based on Visual Geometry Group- (VGG-) 16 combined with quantitative electroencephalography (QEEG) in cerebral small vessel disease (CSVD) with cognitive impairment, 72 patients with CSVD complicated by cognitive impairment were selected as the research subjects. As per Diagnostic and Statistical Manual (5th Edition), they were divided into the vascular dementia (VD) group of 34 cases and vascular cognitive impairment with no dementia (VCIND) group of 38 cases. The two groups were analyzed for the clinical information, neuropsychological test results, and monitoring results of QEEG based on intelligent algorithms for more than 2 hours. The accuracy rate of VGG was 84.27% and Kappa value was 0.7, while that of modified VGG (nVGG) was 88.76% and Kappa value was 0.78. The improved VGG algorithm obviously had higher accuracy. The test results found that the QEEG identified 8 normal, 19 mild, 10 moderate, and 0 severe cases in the VCIND group, while in the VD group, the corresponding numbers were 4, 13, 11, and 7; in the VCIND group, 7 cases had the normal QEEG, 11 cases had background changes, 9 cases had abnormal waves, and 11 cases had in both background changes and abnormal waves, and in the VD group, the corresponding numbers were 5, 2, 5, and 22, respectively; in the VCIND group, QEEG of 18 patients had no abnormal waves, QEEG of 11 patients had a few abnormal waves, and QEEG of 9 patients had many abnormal waves, and QEEG of 0 people had a large number of abnormal waves, and in the VD group, the corresponding numbers were 7, 6, 12, and 9. The above data were statistically different between the two groups (P < 0.05). Hence, QEEG based on intelligent algorithms can make a good assessment of CSVD with cognitive impairment, which had good clinical application value.

Review on Epileptic Seizure Prediction: Machine Learning and Deep Learning Approaches

Epileptic seizures occur due to brain abnormalities that can indirectly affect patient's health. It occurs abruptly without any symptoms and thus increases the mortality rate of humans. Almost 1% of world's population suffers from epileptic seizures. Prediction of seizures before the beginning of onset is beneficial for preventing seizures by medication. Nowadays, modern computational tools, machine learning, and deep learning methods have been used to predict seizures using EEG. However, EEG signals may get corrupted with background noise, and artifacts such as eye blinks and physical movements of muscles may lead to "pops" in the signal, resulting in electrical interference, which is cumbersome to detect through visual inspection for longer duration recordings. These limitations in automatic detection of interictal spikes and epileptic seizures are preferred, which is an essential tool for examining and scrutinizing the EEG recording more precisely. These restrictions bring our attention to present a review of automated schemes that will help neurologists categorize epileptic and nonepileptic signals. While preparing this review paper, it is observed that feature selection and classification are the main challenges in epilepsy prediction algorithms. This paper presents various techniques depending on various features and classifiers over the last few years. The methods presented will give a detailed understanding and ideas about seizure prediction and future research directions.

A Survey of Neuromonitoring Practices in North American Pediatric Intensive Care Units

BACKGROUND

Neuromonitoring is the use of continuous measures of brain physiology to detect clinically important events in real-time. Neuromonitoring devices can be invasive or non-invasive and are typically used on patients with acute brain injury or at high risk for brain injury. The goal of this study was to characterize neuromonitoring infrastructure and practices in North American pediatric intensive care units (PICUs).

METHODS

An electronic, web-based survey was distributed to 70 North American institutions participating in the Pediatric Neurocritical Care Research Group. Questions related to the clinical use of neuromonitoring devices, integrative multimodality neuromonitoring capabilities, and neuromonitoring infrastructure were included. Survey results were presented using descriptive statistics.

RESULTS

The survey was completed by faculty at 74% (52 of 70) of institutions. All 52 institutions measure intracranial pressure and have electroencephalography capability, whereas 87% (45 of 52) use near-infrared spectroscopy and 40% (21/52) use transcranial Doppler. Individual patient monitoring decisions were driven by institutional protocols and collaboration between critical care, neurology, and neurosurgery attendings. Reported device utilization varied by brain injury etiology. Only 15% (eight of 52) of institutions utilized a multimodality neuromonitoring platform to integrate and synchronize data from multiple devices. A database of neuromonitoring patients was maintained at 35% (18 of 52) of institutions. Funding for neuromonitoring programs was variable with contributions from hospitals (19%, 10 of 52), private donations (12%, six of 52), and research funds (12%, six of 52), although 73% (40 of 52) have no dedicated funds.

CONCLUSIONS

Neuromonitoring indications, devices, and infrastructure vary by institution in North American pediatric critical care units. Noninvasive modalities were utilized more liberally, although not uniformly, than invasive monitoring. Further studies are needed to standardize the acquisition, interpretation, and reporting of clinical neuromonitoring data, and to determine whether neuromonitoring systems impact neurological outcomes.

Research on Night Light Comfort of Pedestrian Space in Urban Park

The outdoor light environment significantly affects aspects of public psychological and physiological health. This study conducted experiments to quantify the effects of the light environment on visitor light comfort in urban park pedestrian space. Nine sets of lighting conditions with different average horizontal illuminance (2 lx, 6 lx, 10 lx) and colour temperatures (5600 K, 4300 K, 3000 K) were established virtual reality scenarios. Subjective light comfort was evaluated, and electroencephalogram (EEG) was measured on 18 subjects to comprehensively study the effects of different light environments on human light comfort. The results of the comprehensive evaluation showed that colour temperature had a very significant impact on subjective light comfort, with warm light being generally more favourable than cool light in enhancing human subjective light comfort. The results of the EEG analysis show that the average horizontal illuminance is an important factor in the level of physiological fatigue, and that physiological fatigue can be maintained in a superior state at an appropriate level of illuminance. Based on the results of both subjective and objective factors, a comprehensive analysis was carried out to propose a range of average horizontal illuminance (4.08 lx, 6.99 lx) and a range of colour temperature (3126 K, 4498 K) for the comprehensive light comfort zone in urban park pedestrian space.

Dynamic Electrode-to-Image (DETI) mapping reveals the human brain's spatiotemporal code of visual information

A number of neuroimaging techniques have been employed to understand how visual information is transformed along the visual pathway. Although each technique has spatial and temporal limitations, they can each provide important insights into the visual code. While the BOLD signal of fMRI can be quite informative, the visual code is not static and this can be obscured by fMRI’s poor temporal resolution. In this study, we leveraged the high temporal resolution of EEG to develop an encoding technique based on the distribution of responses generated by a population of real-world scenes. This approach maps neural signals to each pixel within a given image and reveals location-specific transformations of the visual code, providing a spatiotemporal signature for the image at each electrode. Our analyses of the mapping results revealed that scenes undergo a series of nonuniform transformations that prioritize different spatial frequencies at different regions of scenes over time. This mapping technique offers a potential avenue for future studies to explore how dynamic feedforward and recurrent processes inform and refine high-level representations of our visual world.

The visual information that we sample from our environment undergoes a series of neural modifications, with each modification state (or visual code) consisting of a unique distribution of responses across neurons along the visual pathway. However, current noninvasive neuroimaging techniques provide an account of that code that is coarse with respect to time or space. Here, we present dynamic electrode-to-image (DETI) mapping, an analysis technique that capitalizes on the high temporal resolution of EEG to map neural signals to each pixel within a given image to reveal location-specific modifications of the visual code. The DETI technique reveals maps of features that are associated with the neural signal at each pixel and at each time point. DETI mapping shows that real-world scenes undergo a series of nonuniform modifications over both space and time. Specifically, we find that the visual code varies in a location-specific manner, likely reflecting that neural processing prioritizes different features at different image locations over time. DETI mapping therefore offers a potential avenue for future studies to explore how each modification state informs and refines the conceptual meaning of our visual world.

Generative Adversarial Networks-Based Data Augmentation for Brain-Computer Interface

The performance of a classifier in a brain-computer interface (BCI) system is highly dependent on the quality and quantity of training data. Typically, the training data are collected in a laboratory where the users perform tasks in a controlled environment. However, users' attention may be diverted in real-life BCI applications and this may decrease the performance of the classifier. To improve the robustness of the classifier, additional data can be acquired in such conditions, but it is not practical to record electroencephalogram (EEG) data over several long calibration sessions. A potentially time- and cost-efficient solution is artificial data generation. Hence, in this study, we proposed a framework based on the deep convolutional generative adversarial networks (DCGANs) for generating artificial EEG to augment the training set in order to improve the performance of a BCI classifier. To make a comparative investigation, we designed a motor task experiment with diverted and focused attention conditions. We used an end-to-end deep convolutional neural network for classification between movement intention and rest using the data from 14 subjects. The results from the leave-one subject-out (LOO) classification yielded baseline accuracies of 73.04% for diverted attention and 80.09% for focused attention without data augmentation. Using the proposed DCGANs-based framework for augmentation, the results yielded a significant improvement of 7.32% for diverted attention ( ) and 5.45% for focused attention ( ). In addition, we implemented the method on the data set IVa from BCI competition III to distinguish different motor imagery tasks. The proposed method increased the accuracy by 3.57% ( ). This study shows that using GANs for EEG augmentation can significantly improve BCI performance, especially in real-life applications, whereby users' attention may be diverted.

Envelope reconstruction of speech and music highlights stronger tracking of speech at low frequencies

The human brain tracks amplitude fluctuations of both speech and music, which reflects acoustic processing in addition to the encoding of higher-order features and one's cognitive state. Comparing neural tracking of speech and music envelopes can elucidate stimulus-general mechanisms, but direct comparisons are confounded by differences in their envelope spectra. Here, we use a novel method of frequency-constrained reconstruction of stimulus envelopes using EEG recorded during passive listening. We expected to see music reconstruction match speech in a narrow range of frequencies, but instead we found that speech was reconstructed better than music for all frequencies we examined. Additionally, models trained on all stimulus types performed as well or better than the stimulus-specific models at higher modulation frequencies, suggesting a common neural mechanism for tracking speech and music. However, speech envelope tracking at low frequencies, below 1 Hz, was associated with increased weighting over parietal channels, which was not present for the other stimuli. Our results highlight the importance of low-frequency speech tracking and suggest an origin from speech-specific processing in the brain.

Electroencephalographic evidence of gray matter lesions among multiple sclerosis patients: A case-control study

This study aimed to investigate evidence of gray matter brain lesions in multiple sclerosis (MS) patients by evaluating the resting state alpha rhythm of brain electrical activity.The study included 50 patients diagnosed with MS recruited from the MS clinic with 50 age and gender-matched control participants. The study investigated parameters of posterior dominant rhythm (PDR) in the electroencephalography (EEG) recordings including wave frequency and amplitude. Functional disability among the patients was evaluated according to the expanded disability status scale. Univariate statistical analysis was completed using one-way analysis of variance and t test with a P value of less than .05 to indicate statistical significance.Patients with MS had significantly lower PDR frequency and amplitude values compared to the controls (P value < .01) and 34% of the MS patients had a PDR frequency of less than 8.5 Hz. The PDR frequency was negatively associated with the level of functional disability among the patients (P value <.001) and 4% of the patients had abnormal epileptiform discharges.Background slowing of resting alpha rhythms and epileptiform discharges are suggestive of gray matter degeneration and may help in the prediction and follow-up of cortical damage and functional disabilities among MS patients. Therefore, electroencephalography monitoring of the PDR spectrum may serve as an alternative or complementary tool with other imaging techniques to detect and monitor cerebral cortical lesions.

A large-scale brain network mechanism for increased seizure propensity in Alzheimer's disease

People with Alzheimer’s disease (AD) are 6-10 times more likely to develop seizures than the healthy aging population. Leading hypotheses largely consider hyperexcitability of local cortical tissue as primarily responsible for increased seizure prevalence in AD. However, in the general population of people with epilepsy, large-scale brain network organization additionally plays a role in determining seizure likelihood and phenotype. Here, we propose that alterations to large-scale brain network organization seen in AD may contribute to increased seizure likelihood. To test this hypothesis, we combine computational modelling with electrophysiological data using an approach that has proved informative in clinical epilepsy cohorts without AD. EEG was recorded from 21 people with probable AD and 26 healthy controls. At the time of EEG acquisition, all participants were free from seizures. Whole brain functional connectivity derived from source-reconstructed EEG recordings was used to build subject-specific brain network models of seizure transitions. As cortical tissue excitability was increased in the simulations, AD simulations were more likely to transition into seizures than simulations from healthy controls, suggesting an increased group-level probability of developing seizures at a future time for AD participants. We subsequently used the model to assess seizure propensity of different regions across the cortex. We found the most important regions for seizure generation were those typically burdened by amyloid-beta at the early stages of AD, as previously reported by in-vivo and post-mortem staging of amyloid plaques. Analysis of these spatial distributions also give potential insight into mechanisms of increased susceptibility to generalized (as opposed to focal) seizures in AD vs controls. This research suggests avenues for future studies testing patients with seizures, e.g. co-morbid AD/epilepsy patients, and comparisons with PET and MRI scans to relate regional seizure propensity with AD pathologies.

People with Alzheimer’s disease (AD) are more likely to develop seizures than cognitively healthy people. In this study, we aimed to understand whether whole-brain network structure is related to this increased seizure likelihood. We used electroencephalography (EEG) to estimate brain networks from people with AD and healthy controls. We subsequently inserted these networks into a model brain and simulated disease progression by increasing the excitability of brain tissue. We found the simulated AD brains were more likely to develop seizures than the simulated control brains. No participants had seizures when we collected data, so our results suggest an increased probability of developing seizures at a future time for AD participants. Therefore functional brain network structure may play a role in increased seizure likelihood in AD. We also used the model to examine which brain regions were most important for generating seizures, and found that the seizure-generating regions corresponded to those typically affected in early AD. Our results also provide a potential explanation for why people with AD are more likely to have generalized seizures (i.e. seizures involving the whole brain, as opposed to ‘focal’ seizures which only involve certain areas) than the general population with epilepsy.

The effect of colour on reading performance in children, measured by a sensor hub: From the perspective of gender

In recent decades reported findings regarding gender differences in reading achievement, cognitive abilities and maturation process in boys and girls are conflicting. As reading is one of the most important processes in the maturation of an individual, the aim of the study was to better understand gender differences between primary school students. The study evaluates differences in Heart Rate Variability (HRV), Electroencephalography (EEG), Electrodermal Activities (EDA) and eye movement of participants during the reading task. Taking into account that colour may affect reading skills, in that it affects the emotional and physiological state of the body, the research attempts to provide a better understanding of gender differences in reading through examining the effect of colour, as applied to reading content. The physiological responses of 50 children (25 boys and 25 girls) to 12 different background and overlay colours of reading content were measured and summarised during the reading process. Our findings show that boys have shorter reading duration scores and a longer Saccade Count, Saccade Duration Total, and Saccade Duration Average when reading on a coloured background, especially purple, which could be caused by their motivation and by the type of reading task. Also, the boys had higher values for the Delta band and the Whole Range of EEG measurements in comparison to the girls when reading on coloured backgrounds, which could reflect the faster maturation of the girls. Regarding EDA measurements we did not find systematic differences between groups either on white or on coloured/overlay background. We found the most significant differences arose in the HRV parameters, namely (SDNN (ms), STD HR (beats/min), RMSSD (ms), NN50 (beats), pNN50 (%), CVRR) when children read the text on coloured/overlay backgrounds, where the girls showed systematically higher values on HRV measurements in comparison to the boys, mostly with yellow, red, and orange overlay colours.

Novelty is not surprise: Human exploratory and adaptive behavior in sequential decision-making

Classic reinforcement learning (RL) theories cannot explain human behavior in the absence of external reward or when the environment changes. Here, we employ a deep sequential decision-making paradigm with sparse reward and abrupt environmental changes. To explain the behavior of human participants in these environments, we show that RL theories need to include surprise and novelty, each with a distinct role. While novelty drives exploration before the first encounter of a reward, surprise increases the rate of learning of a world-model as well as of model-free action-values. Even though the world-model is available for model-based RL, we find that human decisions are dominated by model-free action choices. The world-model is only marginally used for planning, but it is important to detect surprising events. Our theory predicts human action choices with high probability and allows us to dissociate surprise, novelty, and reward in EEG signals.

Statistical power: Implications for planning MEG studies

Statistical power is key for robust, replicable science. Here, we systematically explored how numbers of trials and subjects affect statistical power in MEG sensor-level data. More specifically, we simulated "experiments" using the MEG resting-state dataset of the Human Connectome Project (HCP). We divided the data in two conditions, injected a dipolar source at a known anatomical location in the "signal condition", but not in the "noise condition", and detected significant differences at sensor level with classical paired t-tests across subjects, using amplitude, squared amplitude, and global field power (GFP) measures. Group-level detectability of these simulated effects varied drastically with anatomical origin. We thus examined in detail which spatial properties of the sources affected detectability, looking specifically at the distance from closest sensor and orientation of the source, and at the variability of these parameters across subjects. In line with previous single-subject studies, we found that the most detectable effects originate from source locations that are closest to the sensors and oriented tangentially with respect to the head surface. In addition, cross-subject variability in orientation also affected group-level detectability, boosting detection in regions where this variability was small and hindering detection in regions where it was large. Incidentally, we observed a considerable covariation of source position, orientation, and their cross-subject variability in individual brain anatomical space, making it difficult to assess the impact of each of these variables independently of one another. We thus also performed simulations where we controlled spatial properties independently of individual anatomy. These additional simulations confirmed the strong impact of distance and orientation and further showed that orientation variability across subjects affects detectability, whereas position variability does not. Importantly, our study indicates that strict unequivocal recommendations as to the ideal number of trials and subjects for any experiment cannot be realistically provided for neurophysiological studies and should be adapted according to the brain regions under study.

Diagnosis of Alzheimer's Disease by Time-Dependent Power Spectrum Descriptors and Convolutional Neural Network Using EEG Signal

Using strategies that obtain biomarkers where early symptoms coincide, the early detection of Alzheimer's disease and its complications is essential. Electroencephalogram is a technology that allows thousands of neurons with equal spatial orientation of the duration of cerebral cortex electrical activity to be registered by postsynaptic potential. Therefore, in this paper, the time-dependent power spectrum descriptors are used to diagnose the electroencephalogram signal function from three groups: mild cognitive impairment, Alzheimer's disease, and healthy control test samples. The final feature used in three modes of traditional classification methods is recorded: k-nearest neighbors, support vector machine, linear discriminant analysis approaches, and documented results. Finally, for Alzheimer's disease patient classification, the convolutional neural network architecture is presented. The results are indicated using output assessment. For the convolutional neural network approach, the accurate meaning of accuracy is 82.3%. 85% of mild cognitive impairment cases are accurately detected in-depth, but 89.1% of the Alzheimer's disease and 75% of the healthy population are correctly diagnosed. The presented convolutional neural network outperforms other approaches because performance and the k-nearest neighbors' approach is the next target. The linear discriminant analysis and support vector machine were at the low area under the curve values.

Information Transfer and Multifractal Analysis of EEG in Mild Blast-Induced TBI

Mild, blast-induced traumatic brain injury (mbTBI) is a common combat brain injury characterized by typically normal neuroimaging findings, with unpredictable future cognitive recovery. Traditional methods of electroencephalography (EEG) analysis (e.g., spectral analysis) have not been successful in detecting the degree of cognitive and functional impairment in mbTBI. We therefore collected resting state EEG (5 minutes, 64 leads) from twelve patients with a history of mbTBI, along with repeat neuropsychological testing (D-KEFS Tower test) to compare two new methods for analyzing EEG (multifractal detrended fluctuation analysis (MF-DFA) and information transfer modeling (ITM)) with spectral analysis. For MF-DFA, we extracted relevant parameters from the resultant multifractal spectrum from all leads and compared with traditional power by frequency band for spectral analysis. For ITM, because the number of parameters from each lead far exceeded the number of subjects, we utilized a reduced set of 10 leads which were compared with spectral analysis. We utilized separate 30 second EEG segments for training and testing statistical models based upon regression tree analysis. ITM and MF-DFA models both generally had improved accuracy at correlating with relevant measures of cognitive performance as compared to spectral analytic models ITM and MF-DFA both merit additional research as analytic tools for EEG and cognition in TBI.

Body site distribution of pediatric-onset morphea and association with extracutaneous manifestations

BACKGROUND

The distribution of pediatric-onset morphea and site-based likelihood for extracutaneous complications has not been well characterized.

OBJECTIVE

To characterize the lesional distribution of pediatric-onset morphea and to determine the sites with the highest association of extracutaneous manifestations.

METHODS

A retrospective cross-sectional study was performed. Using clinical photographs, morphea lesions were mapped onto body diagrams using customized software.

RESULTS

A total of 823 patients with 2522 lesions were included. Lesions were more frequent on the superior (vs inferior) anterior aspect of the head and extensor (vs flexor) extremities. Linear morphea lesions were more likely on the head and neck, whereas plaque and generalized morphea lesions were more likely on the trunk. Musculoskeletal complications were more likely with lesions on the extensor (vs flexor) extremity (odds ratio [OR], 2.0; 95% confidence interval [CI], 1.2-3.4), whereas neurologic manifestations were more likely with lesions on the anterior (vs posterior) (OR, 2.8; 95% CI, 1.7-4.6) and superior (vs inferior) aspect of the head (OR, 2.3; 95% CI, 1.6-3.4).

LIMITATIONS

Retrospective nature and the inclusion of only patients with clinical photographs.

CONCLUSION

The distribution of pediatric-onset morphea is not random and varies with body site and within individual body sites. The risk stratification of extracutaneous manifestations by body site may inform decisions about screening for extracutaneous manifestations, although prospective studies are needed.

Neural surprise in somatosensory Bayesian learning

Tracking statistical regularities of the environment is important for shaping human behavior and perception. Evidence suggests that the brain learns environmental dependencies using Bayesian principles. However, much remains unknown about the employed algorithms, for somesthesis in particular. Here, we describe the cortical dynamics of the somatosensory learning system to investigate both the form of the generative model as well as its neural surprise signatures. Specifically, we recorded EEG data from 40 participants subjected to a somatosensory roving-stimulus paradigm and performed single-trial modeling across peri-stimulus time in both sensor and source space. Our Bayesian model selection procedure indicates that evoked potentials are best described by a non-hierarchical learning model that tracks transitions between observations using leaky integration. From around 70ms post-stimulus onset, secondary somatosensory cortices are found to represent confidence-corrected surprise as a measure of model inadequacy. Indications of Bayesian surprise encoding, reflecting model updating, are found in primary somatosensory cortex from around 140ms. This dissociation is compatible with the idea that early surprise signals may control subsequent model update rates. In sum, our findings support the hypothesis that early somatosensory processing reflects Bayesian perceptual learning and contribute to an understanding of its underlying mechanisms.

Our environment features statistical regularities, such as a drop of rain predicting imminent rainfall. Despite the importance for behavior and survival, much remains unknown about how these dependencies are learned, particularly for somatosensation. As surprise signalling about novel observations indicates a mismatch between one’s beliefs and the world, it has been hypothesized that surprise computation plays an important role in perceptual learning. By analyzing EEG data from human participants receiving sequences of tactile stimulation, we compare different formulations of surprise and investigate the employed underlying learning model. Our results indicate that the brain estimates transitions between observations. Furthermore, we identified different signatures of surprise computation and thereby provide a dissociation of the neural correlates of belief inadequacy and belief updating. Specifically, early surprise responses from around 70ms were found to signal the need for changes to the model, with encoding of its subsequent updating occurring from around 140ms. These results provide insights into how somatosensory surprise signals may contribute to the learning of environmental statistics.

Lag-invariant detection of interactions in spatially-extended systems using linear inverse modeling

Measurements on physical systems result from the systems' activity being converted into sensor measurements by a forward model. In a number of cases, inversion of the forward model is extremely sensitive to perturbations such as sensor noise or numerical errors in the forward model. Regularization is then required, which introduces bias in the reconstruction of the systems' activity. One domain in which this is particularly problematic is the reconstruction of interactions in spatially-extended complex systems such as the human brain. Brain interactions can be reconstructed from non-invasive measurements such as electroencephalography (EEG) or magnetoencephalography (MEG), whose forward models are linear and instantaneous, but have large null-spaces and high condition numbers. This leads to incomplete unmixing of the forward models and hence to spurious interactions. This motivated the development of interaction measures that are exclusively sensitive to lagged, i.e. delayed interactions. The drawback of such measures is that they only detect interactions that have sufficiently large lags and this introduces bias in reconstructed brain networks. We introduce three estimators for linear interactions in spatially-extended systems that are uniformly sensitive to all lags. We derive some basic properties of and relationships between the estimators and evaluate their performance using numerical simulations from a simple benchmark model.

Evaluation of Low-Value Diagnostic Testing for 4 Common Conditions in the Veterans Health Administration

IMPORTANCE

Low-value care is associated with harm among patients and with wasteful health care spending but has not been well characterized in the Veterans Health Administration.

OBJECTIVES

To characterize the frequency of and variation in low-value diagnostic testing for 4 common conditions at Veterans Affairs medical centers (VAMCs) and to examine the correlation between receipt of low-value testing for each condition.

DESIGN, SETTING, AND PARTICIPANTS

This retrospective cohort study used Veterans Health Administration data from 127 VAMCs from fiscal years 2014 to 2015. Data were analyzed from April 2018 to March 2020.

EXPOSURES

Continuous enrollment in Veterans Health Administration during fiscal year 2015.

MAIN OUTCOMES AND MEASURES

Receipt of low-value testing for low back pain, headache, syncope, and sinusitis. For each condition, sensitive and specific criteria were used to evaluate the overall frequency and range of low-value testing, adjusting for sociodemographic and VAMC characteristics. VAMC-level variation was calculated using median adjusted odds ratios. The Pearson correlation coefficient was used to evaluate the degree of correlation between low-value testing for each condition at the VAMC level.

RESULTS

Among 1 022 987 veterans, the mean (SD) age was 60 (16) years, 1 008 336 (92.4%) were male, and 761 485 (69.8%) were non-Hispanic White. A total of 343 024 veterans (31.4%) were diagnosed with low back pain, 79 176 (7.3%) with headache, 23 776 (2.2%) with syncope, and 52 889 (4.8%) with sinusitis. With the sensitive criteria, overall and VAMC-level low-value testing frequency varied substantially across conditions: 4.6% (range, 2.7%-10.1%) for sinusitis, 12.8% (range, 8.6%-22.6%) for headache, 18.2% (range, 10.9%-24.6%) for low back pain, and 20.1% (range, 16.3%-27.7%) for syncope. With the specific criteria, the overall frequency of low-value testing across VAMCs was 2.4% (range, 1.3%-5.1%) for sinusitis, 8.6% (range, 6.2%-14.6%) for headache, 5.6% (range, 3.6%-7.7%) for low back pain, and 13.3% (range, 11.3%-16.8%) for syncope. The median adjusted odds ratio ranged from 1.21 for low back pain to 1.40 for sinusitis. At the VAMC level, low-value testing was most strongly correlated for syncope and headache (ρ = 0.56; P < .001) and low back pain and headache (ρ = 0.48; P < .001).

CONCLUSIONS AND RELEVANCE

In this cohort study, low-value diagnostic testing was common, varied substantially across VAMCs, and was correlated between veterans' receipt of different low-value tests at the VAMC level. The findings suggest a need to address low-value diagnostic testing, even in integrated health systems, with robust utilization management practices.

Convolutional neural network for detection and classification of seizures in clinical data

Epileptic seizure detection and classification in clinical electroencephalogram data still is a challenge, and only low sensitivity with a high rate of false positives has been achieved with commercially available seizure detection tools, which usually are patient non-specific. Epilepsy patients suffer from severe detrimental effects like physical injury or depression due to unpredictable seizures. However, even in hospitals due to the high rate of false positives, the seizure alert systems are of poor help for patients as tools of seizure detection are mostly trained on unrealistically clean data, containing little noise and obtained under controlled laboratory conditions, where patient groups are homogeneous, e.g. in terms of age or type of seizures. In this study authors present the approach for detection and classification of a seizure using clinical data of electroencephalograms and a convolutional neural network trained on features of brain synchronisation and power spectrum. Various deep learning methods were applied, and the network was trained on a very heterogeneous clinical electroencephalogram dataset. In total, eight different types of seizures were considered, and the patients were of various ages, health conditions and they were observed under clinical conditions. Despite this, the classifier presented in this paper achieved sensitivity and specificity equal to 0.68 and 0.67, accordingly, which is a significant improvement as compared to the known results for clinical data. Graphical abstract.

Evaluating the Acute Effect of Stereoscopic Recovery by Dichoptic Stimulation Using Electroencephalogram

Amblyopia is a common developmental disorder in adolescents and children. Stereoscopic loss is a symptom of amblyopia that can seriously affect the quality of patient's life. Recent studies have shown that the push-pull perceptual learning protocol had a positive effect on stereoscopic recovery. In this study, we developed a stereoscopic training method using a polarized visualization system according to the push-pull protocol. Dichoptic stimulation for 36 anisometropic and amblyopic subjects and 33 children with normal visual acuity (VA) has been conducted. Electroencephalogram (EEG) was used to evaluate the neurophysiological changes before, during, and after stimulation. For the anisometropic and amblyopic subjects, the statistical analysis demonstrated significant differences (p < 0.01) in the beta rhythm at the middle temporal and occipital lobes, while the EEG from the normal VA subjects indicated no significant changes when comparing the results before and after training. We concluded that the dichoptic training in our study can activate the middle temporal visual area and visual cortex. The EEG changes can be used to evaluate the training effects. This study also found that the beta band EEG acquired during visual stimulation at the dorsal visual stream can be potentially used for predicting acute training effect. The results facilitated the optimization of the individual training plan.

A Bayesian approach to joint modeling of matrix-valued imaging data and treatment outcome with applications to depression studies

In this paper, we propose a unified Bayesian joint modeling framework for studying association between a binary treatment outcome and a baseline matrix-valued predictor. Specifically, a joint modeling approach relating an outcome to a matrix-valued predictor through a probabilistic formulation of multilinear principal component analysis is developed. This framework establishes a theoretical relationship between the outcome and the matrix-valued predictor, although the predictor is not explicitly expressed in the model. Simulation studies are provided showing that the proposed method is superior or competitive to other methods, such as a two-stage approach and a classical principal component regression in terms of both prediction accuracy and estimation of association; its advantage is most notable when the sample size is small and the dimensionality in the imaging covariate is large. Finally, our proposed joint modeling approach is shown to be a very promising tool in an application exploring the association between baseline electroencephalography data and a favorable response to treatment in a depression treatment study by achieving a substantial improvement in prediction accuracy in comparison to competing methods.

Cortical Theta Activity and Postural Control in Non-Visual and High Cognitive Load Tasks: Impact for Clinical Studies

Due to the major role of balance in our everyday lives and the unsatisfying understanding of the role of neural mechanism on balance control, the focus of this study was to explore the role of the cerebral cortex and its effects on stability. We investigated the effects of non-visual and cognitive tasks on balance performance and cortical theta response in a small, convenient sample. The cognitive tasks were N-back and Sustained Attention Response Task (SART). Cortical theta activity showed strong correlations with balance performance metrics. Particularly, central regions showed an increase in theta power in more cognitively challenging tasks but not statistically significant. Parietal theta power had a statistically significant increase in tasks that led to a heavier reliance on proprioception and vestibular information. This study shows the efficacy of EEG recording during balance control tasks. Future studies on neurodegenerative diseases that affect neuromotor control could investigate these outcomes.

Sleep Spindle Detection Using RUSBoost and Synchrosqueezed Wavelet Transform

Sleep spindles are important electroencephalographic (EEG) waveforms in sleep medicine; however, it is burdensome even for experts to detect spindles, so automatic spindle detection methodologies have been investigated. Conventional methods utilize waveforms template matching or machine learning for detecting spindles. In the former approach, it is necessary to tune thresholds for individual adaptation, while the latter approach has the problem of imbalanced data because the amount of sleep spindles is small compared with the entire EEG data. The present work proposes a sleep spindle detection method that combines wavelet synchrosqueezed transform (SST) and random under-sampling boosting (RUSBoost). SST is a time-frequency analysis method suitable for extracting features of spindle waveforms. RUSBoost is a framework for coping with the imbalanced data problem. The proposed SST-RUS can deal with the imbalanced data in spindle detection and does not require threshold tuning because RUSBoost uses majority voting of weak classifiers for discrimination. The performance of SST-RUS was validated using an open-access database called the Montreal archives of sleep studies cohort 1 (MASS-C1), which showed an F-measure of 0.70 with a sensitivity of 76.9% and a positive predictive value of 61.2%. The proposed method can reduce the burden of PSG scoring.

Use of Machine Learning for Predicting Escitalopram Treatment Outcome From Electroencephalography Recordings in Adult Patients With Depression

IMPORTANCE

Social and economic costs of depression are exacerbated by prolonged periods spent identifying treatments that would be effective for a particular patient. Thus, a tool that reliably predicts an individual patient's response to treatment could significantly reduce the burden of depression.

OBJECTIVE

To estimate how accurately an outcome of escitalopram treatment can be predicted from electroencephalographic (EEG) data on patients with depression.

DESIGN, SETTING, AND PARTICIPANTS

This prognostic study used a support vector machine classifier to predict treatment outcome using data from the first Canadian Biomarker Integration Network in Depression (CAN-BIND-1) study. The CAN-BIND-1 study comprised 180 patients (aged 18-60 years) diagnosed with major depressive disorder who had completed 8 weeks of treatment. Of this group, 122 patients had EEG data recorded before the treatment; 115 also had EEG data recorded after the first 2 weeks of treatment.

INTERVENTIONS

All participants completed 8 weeks of open-label escitalopram (10-20 mg) treatment.

MAIN OUTCOMES AND MEASURES

The ability of EEG data to predict treatment outcome, measured as accuracy, specificity, and sensitivity of the classifier at baseline and after the first 2 weeks of treatment. The treatment outcome was defined in terms of change in symptom severity, measured by the Montgomery-Åsberg Depression Rating Scale, before and after 8 weeks of treatment. A patient was designated as a responder if the Montgomery-Åsberg Depression Rating Scale score decreased by at least 50% during the 8 weeks and as a nonresponder if the score decrease was less than 50%.

RESULTS

Of the 122 participants who completed a baseline EEG recording (mean [SD] age, 36.3 [12.7] years; 76 [62.3%] female), the classifier was able to identify responders with an estimated accuracy of 79.2% (sensitivity, 67.3%; specificity, 91.0%) when using only the baseline EEG data. For a subset of 115 participants who had additional EEG data recorded after the first 2 weeks of treatment, use of these data increased the accuracy to 82.4% (sensitivity, 79.2%; specificity, 85.5%).

CONCLUSIONS AND RELEVANCE

These findings demonstrate the potential utility of EEG as a treatment planning tool for escitalopram therapy. Further development of the classification tools presented in this study holds the promise of expediting the search for optimal treatment for each patient.

Automatic Sleep Staging Employing Convolutional Neural Networks and Cortical Connectivity Images

Understanding of the neuroscientific sleep mechanisms is associated with mental/cognitive and physical well-being and pathological conditions. A prerequisite for further analysis is the identification of the sleep macroarchitecture through manual sleep staging. Several computer-based approaches have been proposed to extract time and/or frequency-domain features with accuracy ranging from 80% to 95% compared with the golden standard of manual staging. However, their acceptability by the medical community is still suboptimal. Recently, utilizing deep learning methodologies increased the research interest in computer-assisted recognition of sleep stages. Aiming to enhance the arsenal of automatic sleep staging, we propose a novel classification framework based on convolutional neural networks. These receive as input synchronizations features derived from cortical interactions within various electroencephalographic rhythms (delta, theta, alpha, and beta) for specific cortical regions which are critical for the sleep deepening. These functional connectivity metrics are then processed as multidimensional images. We also propose to augment the small portion of sleep onset (N1 stage) through the Synthetic Minority Oversampling Technique in order to deal with the great difference in its duration when compared with the remaining sleep stages. Our results (99.85%) indicate the flexibility of deep learning techniques to learn sleep-related neurophysiological patterns.

Covariate-adjusted region-referenced generalized functional linear model for EEG data

Electroencephalography (EEG) studies produce region-referenced functional data in the form of EEG signals recorded across electrodes on the scalp. It is of clinical interest to relate the highly structured EEG data to scalar outcomes such as diagnostic status. In our motivating study, resting-state EEG is collected on both typically developing (TD) children and children with autism spectrum disorder (ASD) aged 2 to 12 years old. The peak alpha frequency (PAF), defined as the location of a prominent peak in the alpha frequency band of the spectral density, is an important biomarker linked to neurodevelopment and is known to shift from lower to higher frequencies as children age. To retain the most amount of information from the data, we consider the oscillations in the spectral density within the alpha band, rather than just the peak location, as a functional predictor of diagnostic status (TD vs ASD), adjusted for chronological age. A covariate-adjusted region-referenced generalized functional linear model is proposed for modeling scalar outcomes from region-referenced functional predictors, which utilizes a tensor basis formed from one-dimensional discrete and continuous bases to estimate functional effects across a discrete regional domain while simultaneously adjusting for additional nonfunctional covariates, such as age. The proposed methodology provides novel insights into differences in neural development of TD and ASD children. The efficacy of the proposed methodology is investigated through extensive simulation studies.

Higuchi's fractal dimension, but not frontal or posterior alpha asymmetry, predicts PID-5 anxiousness more than depressivity

Depression is a major cause of health disability. EEG measures may provide one or more economical biomarkers for the diagnosis of depression. Here we compared frontal alpha asymmetry (FAA), posterior alpha asymmetry (PAA), and Higuchi's fractal dimension (HFD) for their capacity to predict PID-5 depressivity and for the specificity of these predictions relative to PID-5 anxiousness. University students provided 8 or 10 minutes of resting EEG and PID-5 depressivity and PID-5 anxiousness questionnaire scores. FAA and PAA had no significant correlations with the measures at any electrode pair. There were distinct frontal and posterior factors underlying HFD that correlated significantly with anxiousness and with each other. Posterior HFD also correlated significantly with depressivity, though this was weaker than the correlation with anxiousness. The portion of depressivity variance accounted for by posterior HFD was not unique but shared with anxiousness. Inclusion of anxiety disorder patients into the sample rendered the frontal factor somewhat more predictive than the posterior one but generally strengthened the prior conclusions. Contrary to our predictions, none of our measures specifically predicted depressivity. Previous reports of links with depression may involve confounds with concurrent anxiety. Indeed, HFD may be a better measure of anxiety than depression; and its previous linkage to depression may be due to a confound between the two, given the high incidence of depression in cases of severe anxiety.

Scoping Review of EEG Studies in Construction Safety

Construction safety is critical in the success of a project. A considerable amount of effort has been placed on research and practice in order to reduce the potential risks on the construction site. Recent application of electroencephalogram (EEG) to construction research enables researchers to gain insight into construction workers’ physical and mental status during construction tasks. By summarizing existing studies that involve EEG and construction safety, the literature review aims to provide practical suggestions for future research and on-site safety management. The literature search and inclusion process included eleven eligible studies. Comprehensive analysis was conducted based on primary and secondary measures. The primary measures considered the frequency bands of EEG and the channels for detecting electrical activity of the brain. The secondary measures that were involved with physical and mental status with respect to EEG signal variations as a result of task, working hour, and work conditions. Although the field of study that combines EEG measures with construction tasks is still emerging, it is worth continuous attention in the future, as relevant findings would be of great value to the safety management and risk control in the construction industry.

Using centrality measures to extract core pattern of brain dynamics during the resting state

The patterns of brain dynamics were studied during resting state on a macroscopic scale for control subjects and multiple sclerosis patients. Macroscopic brain dynamics is defined after successive coarse-grainings and selection of significant patterns and transitions based on Markov representation of brain activity. The resulting networks show that control dynamics is merely organized according to a single principal pattern whereas patients dynamics depict more variable patterns. Centrality measures are used to extract core dynamical pattern in brain dynamics and classification technique allow to define MS dynamics with relevant error rate.

A Graph-Based Hierarchical Attention Model for Movement Intention Detection from EEG Signals

An EEG-based Brain-Computer Interface (BCI) is a system that enables a user to communicate with and intuitively control external devices solely using the user's intentions. Current EEG-based BCI research usually involves a subject-specific adaptation step before a BCI system is ready to be employed by a new user. However, the subject-independent scenario, in which a well-trained model can be directly applied to new users without pre-calibration, is particularly desirable yet rarely explored. Considering this critical gap, our focus in this paper is the subject-independent scenario of EEG-based human intention recognition. We present a G raph-based H ierarchical A ttention M odel (G-HAM) that utilizes the graph structure to represent the spatial information of EEG sensors and the hierarchical attention mechanism to focus on both the most discriminative temporal periods and EEG nodes. Extensive experiments on a large EEG dataset containing 105 subjects indicate that our model is capable of exploiting the underlying invariant EEG patterns across different subjects and generalizing the patterns to new subjects with better performance than a series of state-of-the-art and baseline approaches.

Graph-to-signal transformation based classification of functional connectivity brain networks

Complex network theory has been successful at unveiling the topology of the brain and showing alterations to the network structure due to brain disease, cognitive function and behavior. Functional connectivity networks (FCNs) represent different brain regions as the nodes and the connectivity between them as the edges of a graph. Graph theoretic measures provide a way to extract features from these networks enabling subsequent characterization and discrimination of networks across conditions. However, these measures are constrained mostly to binary networks and highly dependent on the network size. In this paper, we propose a novel graph-to-signal transform that overcomes these shortcomings to extract features from functional connectivity networks. The proposed transformation is based on classical multidimensional scaling (CMDS) theory and transforms a graph into signals such that the Euclidean distance between the nodes of the network is preserved. In this paper, we propose to use the resistance distance matrix for transforming weighted functional connectivity networks into signals. Our results illustrate how well-known network structures transform into distinct signals using the proposed graph-to-signal transformation. We then compute well-known signal features on the extracted graph signals to discriminate between FCNs constructed across different experimental conditions. Based on our results, the signals obtained from the graph-to-signal transformation allow for the characterization of functional connectivity networks, and the corresponding features are more discriminative compared to graph theoretic measures.

Two-Stage Frequency Recognition Method Based on Correlated Component Analysis for SSVEP-Based BCI

A canonical correlation analysis (CCA) is a state-of-the-art method for frequency recognition in steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) systems. Various extended methods have been developed, and among such methods, a combination method of CCA and individual-template-based CCA has achieved the best performance. However, the CCA requires the canonical vectors to be orthogonal, which may not be a reasonable assumption for the EEG analysis. In this paper, we propose using the correlated component analysis (CORRCA) rather than CCA to implement frequency recognition. CORRCA can relax the constraint of canonical vectors in CCA and generate the same projection vector for two multichannel EEG signals. Furthermore, we propose a two-stage method based on the basic CORRCA method (termed TSCORRCA). Evaluated on a benchmark data set of 35 subjects, the experimental results demonstrate that CORRCA significantly outperformed CCA, and TSCORRCA obtained the best performance among the compared methods. This paper demonstrates that CORRCA-based methods have a great potential for implementing high-performance SSVEP-based BCI systems.

Exploring Cognitive Flexibility With a Noninvasive BCI Using Simultaneous Steady-State Visual Evoked Potentials and Sensorimotor Rhythms

EEG-based brain-computer interface (BCI) technology creates non-biological pathways for conveying a user's mental intent solely through noninvasively measured neural signals. While optimizing the performance of a single task has long been the focus of BCI research, in order to translate this technology into everyday life, realistic situations, in which multiple tasks are performed simultaneously, must be investigated. In this paper, we explore the concept of cognitive flexibility, or multitasking, within the BCI framework by utilizing a 2-D cursor control task, using sensorimotor rhythms (SMRs), and a four-target visual attention task, using steady-state visual evoked potentials (SSVEPs), both individually and simultaneously. We found no significant difference between the accuracy of the tasks when executing them alone (SMR-57.9% ± 15.4% and SSVEP-59.0% ± 14.2%) and simultaneously (SMR-54.9% ± 17.2% and SSVEP-57.5% ± 15.4%). These modest decreases in performance were supported by similar, non-significant changes in the electrophysiology of the SSVEP and SMR signals. In this sense, we report that multiple BCI tasks can be performed simultaneously without a significant deterioration in performance; this finding will help drive these systems toward realistic daily use in which a user's cognition will need to be involved in multiple tasks at once.

Permutation Statistics for Connectivity Analysis between Regions of Interest in EEG and MEG Data

Connectivity estimates based on electroencephalography (EEG) and magnetoencephalography (MEG) are unique in their ability to provide neurophysiologically meaningful spectral and temporal information non-invasively. This multi-dimensional aspect of the MEG/EEG based connectivity increases the challenges of the analysis and interpretation of the data. Many MEG/EEG studies address this complexity by using a hypothesis-driven approach, which focuses on particular regions of interest (ROI). However, if an effect is distributed unevenly over a large ROI and variable across subjects, it may not be detectable using conventional methods. Here, we propose a novel approach, which enhances the statistical power for weak and spatially discontinuous effects. This results in the ability to identify statistically significant connectivity patterns with spectral, temporal, and spatial specificity while correcting for multiple comparisons using nonparametric permutation methods. We call this new approach the Permutation Statistics for Connectivity Analysis between ROI (PeSCAR). We demonstrate the processing steps with simulated and real human data. The open-source Matlab code implementing PeSCAR are provided online.

Spatial neuronal synchronization and the waveform of oscillations: Implications for EEG and MEG

Neuronal oscillations are ubiquitous in the human brain and are implicated in virtually all brain functions. Although they can be described by a prominent peak in the power spectrum, their waveform is not necessarily sinusoidal and shows rather complex morphology. Both frequency and temporal descriptions of such non-sinusoidal neuronal oscillations can be utilized. However, in non-invasive EEG/MEG recordings the waveform of oscillations often takes a sinusoidal shape which in turn leads to a rather oversimplified view on oscillatory processes. In this study, we show in simulations how spatial synchronization can mask non-sinusoidal features of the underlying rhythmic neuronal processes. Consequently, the degree of non-sinusoidality can serve as a measure of spatial synchronization. To confirm this empirically, we show that a mixture of EEG components is indeed associated with more sinusoidal oscillations compared to the waveform of oscillations in each constituent component. Using simulations, we also show that the spatial mixing of the non-sinusoidal neuronal signals strongly affects the amplitude ratio of the spectral harmonics constituting the waveform. Finally, our simulations show how spatial mixing can affect the strength and even the direction of the amplitude coupling between constituent neuronal harmonics at different frequencies. Validating these simulations, we also demonstrate these effects in real EEG recordings. Our findings have far reaching implications for the neurophysiological interpretation of spectral profiles, cross-frequency interactions, as well as for the unequivocal determination of oscillatory phase.

A Deep Learning Architecture for Temporal Sleep Stage Classification Using Multivariate and Multimodal Time Series

Sleep stage classification constitutes an important preliminary exam in the diagnosis of sleep disorders. It is traditionally performed by a sleep expert who assigns to each 30 s of the signal of a sleep stage, based on the visual inspection of signals such as electroencephalograms (EEGs), electrooculograms (EOGs), electrocardiograms, and electromyograms (EMGs). We introduce here the first deep learning approach for sleep stage classification that learns end-to-end without computing spectrograms or extracting handcrafted features, that exploits all multivariate and multimodal polysomnography (PSG) signals (EEG, EMG, and EOG), and that can exploit the temporal context of each 30-s window of data. For each modality, the first layer learns linear spatial filters that exploit the array of sensors to increase the signal-to-noise ratio, and the last layer feeds the learnt representation to a softmax classifier. Our model is compared to alternative automatic approaches based on convolutional networks or decisions trees. Results obtained on 61 publicly available PSG records with up to 20 EEG channels demonstrate that our network architecture yields the state-of-the-art performance. Our study reveals a number of insights on the spatiotemporal distribution of the signal of interest: a good tradeoff for optimal classification performance measured with balanced accuracy is to use 6 EEG with 2 EOG (left and right) and 3 EMG chin channels. Also exploiting 1 min of data before and after each data segment offers the strongest improvement when a limited number of channels are available. As sleep experts, our system exploits the multivariate and multimodal nature of PSG signals in order to deliver the state-of-the-art classification performance with a small computational cost.

Modeling neuronal avalanches and long-range temporal correlations at the emergence of collective oscillations: Continuously varying exponents mimic M/EEG results

We revisit the CROS ("CRitical OScillations") model which was recently proposed as an attempt to reproduce both scale-invariant neuronal avalanches and long-range temporal correlations. With excitatory and inhibitory stochastic neurons locally connected in a two-dimensional disordered network, the model exhibits a transition where alpha-band oscillations emerge. Precisely at the transition, the fluctuations of the network activity have nontrivial detrended fluctuation analysis (DFA) exponents, and avalanches (defined as supra-threshold activity) have power law distributions of size and duration. We show that, differently from previous results, the exponents governing the distributions of avalanche size and duration are not necessarily those of the mean-field directed percolation universality class (3/2 and 2, respectively). Instead, in a narrow region of parameter space, avalanche exponents obtained via a maximum-likelihood estimator vary continuously and follow a linear relation, in good agreement with results obtained from M/EEG data. In that region, moreover, the values of avalanche and DFA exponents display a spread with positive correlations, reproducing human MEG results.

Surrogate-Based Artifact Removal From Single-Channel EEG

OBJECTIVE

the recent emergence and success of electroencephalography (EEG) in low-cost portable devices, has opened the door to a new generation of applications processing a small number of EEG channels for health monitoring and brain-computer interfacing. These recordings are, however, contaminated by many sources of noise degrading the signals of interest, thus compromising the interpretation of the underlying brain state. In this paper, we propose a new data-driven algorithm to effectively remove ocular and muscular artifacts from single-channel EEG: the surrogate-based artifact removal (SuBAR).

METHODS

by means of the time-frequency analysis of surrogate data, our approach is able to identify and filter automatically ocular and muscular artifacts embedded in single-channel EEG.

RESULTS

in a comparative study using artificially contaminated EEG signals, the efficacy of the algorithm in terms of noise removal and signal distortion was superior to other traditionally-employed single-channel EEG denoizing techniques: wavelet thresholding and the canonical correlation analysis combined with an advanced version of the empirical mode decomposition. Even in the presence of mild and severe artifacts, our artifact removal method provides a relative error 4 to 5 times lower than traditional techniques.

SIGNIFICANCE

in view of these results, the SuBAR method is a promising solution for mobile environments, such as ambulatory healthcare systems, sleep stage scoring, or anesthesia monitoring, where very few EEG channels or even a single channel is available.

Embodying the camera: An EEG study on the effect of camera movements on film spectators´ sensorimotor cortex activation

One key feature of film consists in its power to bodily engage the viewer. Previous research has suggested lens and camera movements to be among the most effective stylistic devices involved in such engagement. In an EEG experiment we assessed the role of such movements in modulating specific spectators´ neural and experiential responses, likely reflecting such engagement. We produced short video clips of an empty room with a still, a zooming and a moving camera (steadicam) that might simulate the movement of an observer in different ways. We found an event related desynchronization of the beta components of the rolandic mu rhythm that was stronger for the clips produced with steadicam than for those produced with a still or zooming camera. No equivalent modulation in the attention related occipital areas was found, thus confirming the sensorimotor nature of spectators´ neural responses to the film clips. The present study provides the first empirical evidence that filmic means such as camera movements alone can modulate spectators’ bodily engagement with film.

SeqSleepNet: End-to-End Hierarchical Recurrent Neural Network for Sequence-to-Sequence Automatic Sleep Staging

Automatic sleep staging has been often treated as a simple classification problem that aims at determining the label of individual target polysomnography epochs one at a time. In this paper, we tackle the task as a sequence-to-sequence classification problem that receives a sequence of multiple epochs as input and classifies all of their labels at once. For this purpose, we propose a hierarchical recurrent neural network named SeqSleepNet (source code is available at http://github.com/pquochuy/SeqSleepNet). At the epoch processing level, the network consists of a filterbank layer tailored to learn frequency-domain filters for preprocessing and an attention-based recurrent layer designed for short-term sequential modeling. At the sequence processing level, a recurrent layer placed on top of the learned epoch-wise features for long-term modeling of sequential epochs. The classification is then carried out on the output vectors at every time step of the top recurrent layer to produce the sequence of output labels. Despite being hierarchical, we present a strategy to train the network in an end-to-end fashion. We show that the proposed network outperforms the state-of-the-art approaches, achieving an overall accuracy, macro F1-score, and Cohen's kappa of 87.1%, 83.3%, and 0.815 on a publicly available dataset with 200 subjects.

Deep brain activities can be detected with magnetoencephalography

The hippocampus and amygdala are key brain structures of the medial temporal lobe, involved in cognitive and emotional processes as well as pathological states such as epilepsy. Despite their importance, it is still unclear whether their  neural activity can be recorded non-invasively. Here, using simultaneous intracerebral and magnetoencephalography (MEG) recordings in patients with focal drug-resistant epilepsy, we demonstrate a direct contribution of amygdala and hippocampal activity to surface MEG recordings. In particular, a method of blind source separation, independent component analysis, enabled activity arising from large neocortical networks to be disentangled from that of deeper structures, whose amplitude at the surface was small but significant. This finding is highly relevant for our understanding of hippocampal and amygdala brain activity as it implies that their activity could potentially be measured non-invasively.

Mining Within-Trial Oscillatory Brain Dynamics to Address the Variability of Optimized Spatial Filters

Data-driven spatial filtering algorithms optimize scores, such as the contrast between two conditions to extract oscillatory brain signal components. Most machine learning approaches for the filter estimation, however, disregard within-trial temporal dynamics and are extremely sensitive to changes in training data and involved hyperparameters. This leads to highly variable solutions and impedes the selection of a suitable candidate for, e.g., neurotechnological applications. Fostering component introspection, we propose to embrace this variability by condensing the functional signatures of a large set of oscillatory components into homogeneous clusters, each representing specific within-trial envelope dynamics. The proposed method is exemplified by and evaluated on a complex hand force task with a rich within-trial structure. Based on electroencephalography data of 18 healthy subjects, we found that the components' distinct temporal envelope dynamics are highly subject-specific. On average, we obtained seven clusters per subject, which were strictly confined regarding their underlying frequency bands. As the analysis method is not limited to a specific spatial filtering algorithm, it could be utilized for a wide range of neurotechnological applications, e.g., to select and monitor functionally relevant features for brain-computer interface protocols in stroke rehabilitation.

Comparison of complex regional pain syndrome and fibromyalgia: Differences in beta and gamma bands on quantitative electroencephalography

Complex regional pain syndrome (CRPS) and fibromyalgia (FM) share many features. Both can cause severe pain and are considered to have a mechanism of action, including dysfunction of the sympathetic nervous system. However, they have clinical differences in pain range and degree. The present study aimed to find neurophysiologic differences between CRPS and FM using quantitative electroencephalography (QEEG). Thirty-eight patients with CRPS and 33 patients with FM were included in the analysis. Resting-state QEEG data were grouped into frontal, central, and posterior regions to analyze for regional differences. General linear models were utilized to test for group differences in absolute and relative powers. As a result, the CRPS group relative to FM group showed lower total absolute powers in the beta band (F = 5.159, P < .05), high beta (F = 14.120, P < .05), and gamma band (F = 15.034, P < .05). There were no significant differences between 2 groups in the delta, theta, and alpha bands. The present findings show that the CRPS and FM groups differ mainly in the high frequency, which may reflect their distinct pathophysiology and symptomatology. Our study suggests that the QEEG differences can be clinically useful in assessing brain function in patients with CRPS and FM.

Predicting neurological recovery with Canonical Autocorrelation Embeddings

Early prediction of the potential for neurological recovery after resuscitation from cardiac arrest is difficult but important. Currently, no clinical finding or combination of findings are sufficient to accurately predict or preclude favorable recovery of comatose patients in the first 24 to 48 hours after resuscitation. Thus, life-sustaining therapy is often continued for several days in patients whose irrecoverable injury is not yet recognized. Conversely, early withdrawal of life-sustaining therapy increases mortality among patients who otherwise might have gone on to recover. In this work, we present Canonical Autocorrelation Analysis (CAA) and Canonical Autocorrelation Embeddings (CAE), novel methods suitable for identifying complex patterns in high-resolution multivariate data often collected in highly monitored clinical environments such as intensive care units. CAE embeds sets of datapoints onto a space that characterizes their latent correlation structures and allows direct comparison of these structures through the use of a distance metric. The methodology may be particularly suitable when the unit of analysis is not just an individual datapoint but a dataset, as for instance in patients for whom physiological measures are recorded over time, and where changes of correlation patterns in these datasets are informative for the task at hand. We present a proof of concept to illustrate the potential utility of CAE by applying it to characterize electroencephalographic recordings from 80 comatose survivors of cardiac arrest, aiming to identify patients who will survive to hospital discharge with favorable functional recovery. Our results show that with very low probability of making a Type 1 error, we are able to identify 32.5% of patients who are likely to have a good neurological outcome, some of whom have otherwise unfavorable clinical characteristics. Importantly, some of these had 5% predicted chance of favorable recovery based on initial illness severity measures alone. Providing this information to support clinical decision-making could motivate the continuation of life-sustaining therapies for these patients.

Walking Imagery Evaluation in Brain Computer Interfaces via a Multi-View Multi-Level Deep Polynomial Network

Brain-computer interfaces based on motor imagery (MI) have been widely used to support the rehabilitation of motor functions of the upper limbs rather than lower limbs. This is probably because it is more difficult to detect the brain activities of lower limb MI. In order to reliably detect the brain activities of lower limbs to restore or improve the walking ability of the disabled, we propose a new paradigm of walking imagery (WI) in a virtual environment (VE), in order to elicit the reliable brain activities and achieve a significant training effect. First, we extract and fuse both the spatial and time-frequency features as a multi-view feature to represent the patterns in the brain activity. Second, we design a multi-view multi-level deep polynomial network (MMDPN) to explore the complementarity among the features so as to improve the detection of walking from an idle state. Our extensive experimental results show that the VE-based paradigm significantly performs better than the traditional text-based paradigm. In addition, the VE-based paradigm can effectively help users to modulate the brain activities and improve the quality of electroencephalography signals. We also observe that the MMDPN outperforms other deep learning methods in terms of classification performance.

The Riemannian Potato Field: A Tool for Online Signal Quality Index of EEG

Electroencephalographic (EEG) recordings are contaminated by instrumental, environmental, and biological artifacts, resulting in low signal-to-noise ratio. Artifact detection is a critical task for real-time applications where the signal is used to give a continuous feedback to the user. In these applications, it is therefore necessary to estimate online a signal quality index (SQI) in order to stop the feedback when the signal quality is unacceptable. In this paper, we introduce the Riemannian potato field (RPF) algorithm as such SQI. It is a generalization and extensionof theRiemannian potato, a previouslypublished real-time artifact detection algorithm, whose performance is degraded as the number of channels increases. The RPF overcomes this limitation by combining the outputs of several smaller potatoes into a unique SQI resulting in a higher sensitivity and specificity, regardless of the number of electrodes. We demonstrate these results on a clinical dataset totalizing more than 2200 h of EEG recorded at home, that is, in a non-controlled environment.

Correlation of EEG biomarkers of cannabis with measured driving impairment

Objective: The objective of this study was to use electroencephalogram (EEG) biomarkers derived from a short, easily administered neurocognitive testbed to determine acute cannabis intoxication and its effect on driving performance in a driving simulator.Methods: The data analyzed were from a study examining the relationship between psychomotor task performance, EEG data, and driving performance in a simulator. EEG data were collected using a STAT® X-24 EEG Wireless Sensor Headset, which was worn during the psychomotor and driving tasks. Driving data were collected for segments of consistent driving environments, including urban driving, urban curves, interstate, interstate curves, dark rural, and rural straightaways. Dependent measures included measures of lateral and longitudinal vehicle control.Results: There was a significant relationship between impaired driving performance as indicated by increased standard deviation of lane position and EEG power in slow theta band (3-5 Hz) in parietal and occipital areas.Conclusions: These results, combined with our prior reported results, suggest that EEG and electrocardiogram (ECG) acquired concurrent with neuropsychological tests hold potential to provide a highly sensitive, specific, and dose-dependent profile of cannabis intoxication and level of impairment.

Estimating coupling strength between multivariate neural series with multivariate permutation conditional mutual information

Recently, coupling between groups of neurons or different brain regions has been widely studied to provide insights into underlying mechanisms of brain functions. To comprehensively understand the effect of such coupling, it is necessary to accurately extract the coupling strength information among multivariate neural signals from the whole brain. This study proposed a new method named multivariate permutation conditional mutual information (MPCMI) to quantitatively estimate the coupling strength of multivariate neural signals (MNS). The performance of the MPCMI method was validated on the simulated MNS generated by multi-channel neural mass model (MNMM). The coupling strength feature of simulated MNS extracted by MPCMI showed better performance compared with standard methods, such as permutation conditional mutual information (PCMI), multivariate Granger causality (MVGC), and Granger causality analysis (GCA). Furthermore, the MPCMI was applied to estimate the coupling strengths of two-channel resting-state electroencephalographic (rsEEG) signals from different brain regions of 19 patients with amnestic mild cognitive impairment (aMCI) with type 2 diabetes mellitus (T2DM) and 20 normal control (NC) with T2DM in Alpha1 and Alpha2 frequency bands. Empirical results showed that the MPCMI could effectively extract the coupling strength features that were significantly different between the aMCI and the NC. Hence, the proposed MPCMI method could be an effective estimate of coupling strengths of MNS, and might be a viable biomarker for clinical applications.