EEG System Research Articles

Optimizing Electrode Configurations for Wearable EEG Seizure Detection Using Machine Learning

Epilepsy, a prevalent neurological disorder, profoundly affects patients’ quality of life due to the unpredictable nature of seizures. The development of a reliable and user-friendly wearable EEG system capable of detecting and predicting seizures has the potential to revolutionize epilepsy care. However, optimizing electrode configurations for such systems, which is crucial for balancing accuracy and practicality, remains to be explored. This study addresses this gap by developing a systematic approach to optimize electrode configurations for a seizure detection machine-learning algorithm. Our approach was applied to an extensive database of prolonged annotated EEG recordings from 158 epilepsy patients. Multiple electrode configurations ranging from one to eighteen were assessed to determine the optimal number of electrodes. Results indicated that the performance was initially maintained as the number of electrodes decreased, but a drop in performance was found to have occurred at around eight electrodes. Subsequently, a comprehensive analysis of all eight-electrode configurations was conducted using a computationally intensive workflow to identify the optimal configurations. This approach can inform the mechanical design process of an EEG system that balances seizure detection accuracy with the ease of use and portability. Additionally, this framework holds potential for optimizing hardware in other machine learning applications. The study presents a significant step towards the development of an efficient wearable EEG system for seizure detection.

Role of negative feedback in EEG and peripheral systems

Role of negative feedback in EEG and peripheral systems

A Dataset of Scalp EEG Recordings of Alzheimer’s Disease, Frontotemporal Dementia and Healthy Subjects from Routine EEG

Recently, there has been a growing research interest in utilizing the electroencephalogram (EEG) as a non-invasive diagnostic tool for neurodegenerative diseases. This article provides a detailed description of a resting-state EEG dataset of individuals with Alzheimer’s disease and frontotemporal dementia, and healthy controls. The dataset was collected using a clinical EEG system with 19 scalp electrodes while participants were in a resting state with their eyes closed. The data collection process included rigorous quality control measures to ensure data accuracy and consistency. The dataset contains recordings of 36 Alzheimer’s patients, 23 frontotemporal dementia patients, and 29 healthy age-matched subjects. For each subject, the Mini-Mental State Examination score is reported. A monopolar montage was used to collect the signals. A raw and preprocessed EEG is included in the standard BIDS format. For the preprocessed signals, established methods such as artifact subspace reconstruction and an independent component analysis have been employed for denoising. The dataset has significant reuse potential since Alzheimer’s EEG Machine Learning studies are increasing in popularity and there is a lack of publicly available EEG datasets. The resting-state EEG data can be used to explore alterations in brain activity and connectivity in these conditions, and to develop new diagnostic and treatment approaches. Additionally, the dataset can be used to compare EEG characteristics between different types of dementia, which could provide insights into the underlying mechanisms of these conditions.

A garment that measures brain activity: proof of concept of an EEG sensor layer fully implemented with smart textiles.

This paper presents the first garment capable of measuring brain activity with accuracy comparable to that of state-of-the art dry electroencephalogram (EEG) systems. The main innovation is an EEG sensor layer (i.e., the electrodes, the signal transmission, and the cap support) made entirely of threads, fabrics, and smart textiles, eliminating the need for metal or plastic materials. The garment is connected to a mobile EEG amplifier to complete the measurement system. As a first proof of concept, the new EEG system (Garment-EEG) was characterized with respect to a state-of-the-art Ag/AgCl dry-EEG system (Dry-EEG) over the forehead area of healthy participants in terms of: (1) skin-electrode impedance; (2) EEG activity; (3) artifacts; and (4) user ergonomics and comfort. The results show that the Garment-EEG system provides comparable recordings to Dry-EEG, but it is more susceptible to artifacts under adverse recording conditions due to poorer contact impedances. The textile-based sensor layer offers superior ergonomics and comfort compared to its metal-based counterpart. We provide the datasets recorded with Garment-EEG and Dry-EEG systems, making available the first open-access dataset of an EEG sensor layer built exclusively with textile materials. Achieving user acceptance is an obstacle in the field of neurotechnology. The introduction of EEG systems encapsulated in wearables has the potential to democratize neurotechnology and non-invasive brain-computer interfaces, as they are naturally accepted by people in their daily lives. Furthermore, supporting the EEG implementation in the textile industry may result in lower cost and less-polluting manufacturing processes compared to metal and plastic industries.

Electrocortical Dynamics of Usual Walking and the Planning to Step over Obstacles in Parkinson's Disease.

The neural correlates of locomotion impairments observed in people with Parkinson's disease (PD) are not fully understood. We investigated whether people with PD present distinct brain electrocortical activity during usual walking and the approach phase of obstacle avoidance when compared to healthy individuals. Fifteen people with PD and fourteen older adults walked overground in two conditions: usual walking and obstacle crossing. Scalp electroencephalography (EEG) was recorded using a mobile 64-channel EEG system. Independent components were clustered using a k-means clustering algorithm. Outcome measures included absolute power in several frequency bands and alpha/beta ratio. During the usual walk, people with PD presented a greater alpha/beta ratio in the left sensorimotor cortex than healthy individuals. While approaching obstacles, both groups reduced alpha and beta power in the premotor and right sensorimotor cortices (balance demand) and increased gamma power in the primary visual cortex (visual demand). Only people with PD reduced alpha power and alpha/beta ratio in the left sensorimotor cortex when approaching obstacles. These findings suggest that PD affects the cortical control of usual walking, leading to a greater proportion of low-frequency (alpha) neuronal firing in the sensorimotor cortex. Moreover, the planning for obstacle avoidance changes the electrocortical dynamics associated with increased balance and visual demands. People with PD rely on increased sensorimotor integration to modulate locomotion.

A Systematic Comparison of High-End and Low-Cost EEG Amplifiers for Concealed, Around-the-Ear EEG Recordings.

Wearable electroencephalography (EEG) has the potential to improve everyday life through brain-computer interfaces (BCI) for applications such as sleep improvement, adaptive hearing aids, or thought-based digital device control. To make these innovations more practical for everyday use, researchers are looking to miniaturized, concealed EEG systems that can still collect neural activity precisely. For example, researchers are using flexible EEG electrode arrays that can be attached around the ear (cEEGrids) to study neural activations in everyday life situations. However, the use of such concealed EEG approaches is limited by measurement challenges such as reduced signal amplitudes and high recording system costs. In this article, we compare the performance of a lower-cost open-source amplification system, the OpenBCI Cyton+Daisy boards, with a benchmark amplifier, the MBrainTrain Smarting Mobi. Our results show that the OpenBCI system is a viable alternative for concealed EEG research, with highly similar noise performance, but slightly lower timing precision. This system can be a great option for researchers with a smaller budget and can, therefore, contribute significantly to advancing concealed EEG research.

Exergaming in older adults: the effects of game characteristics on brain activity and physical activity.

Exergames are increasingly used in rehabilitation settings for older adults to train physical and cognitive abilities. To meet the potential that exergames hold, they need to be adapted to the individual abilities of the player and their training objectives. Therefore, it is important to know whether and how game characteristics affect their playing. The aim of this study is to investigate the effect of two different kinds of exergame (step game and balance game) played at two difficulty levels on brain activity and physical activity. Twenty-eight older independently living adults played two different exergames at two difficulty levels each. In addition, the same movements as during gaming (leaning sideways with feet in place and stepping sideways) were performed as reference movements. Brain activity was recorded using a 64-channel EEG system to assess brain activity, while physical activity was recorded using an accelerometer at the lower back and a heart rate sensor. Source-space analysis was applied to analyze the power spectral density in theta (4 Hz-7 Hz) and alpha-2 (10 Hz-12 Hz) frequency bands. Vector magnitude was applied to the acceleration data. Friedman ANOVA revealed significantly higher theta power for the exergaming conditions compared to the reference movement for both games. Alpha-2 power showed a more diverse pattern which might be attributed to task-specific conditions. Acceleration decreased significantly from the reference movement to the easy condition to the hard condition for both games. The results indicate that exergaming increases frontal theta activity irrespective of type of game or difficulty level, while physical activity decreases with increasing difficulty level. Heart rate was found to be an inappropriate measure in this population older adults. These findings contribute to understanding of how game characteristics affect physical and cognitive activity and consequently need to be taken into account when choosing appropriate games and game settings for exergame interventions.

Electroencephalography Signal Analysis for Human Activities Classification: A Solution Based on Machine Learning and Motor Imagery.

Electroencephalography (EEG) is a fundamental tool for understanding the brain's electrical activity related to human motor activities. Brain-Computer Interface (BCI) uses such electrical activity to develop assistive technologies, especially those directed at people with physical disabilities. However, extracting signal features and patterns is still complex, sometimes delegated to machine learning (ML) algorithms. Therefore, this work aims to develop a ML based on the Random Forest algorithm to classify EEG signals from subjects performing real and imagery motor activities. The interpretation and correct classification of EEG signals allow the development of tools controlled by cognitive processes. We evaluated our ML Random Forest algorithm using a consumer and a research-grade EEG system. Random Forest efficiently distinguishes imagery and real activities and defines the related body part, even with consumer-grade EEG. However, interpersonal variability of the EEG signals negatively affects the classification process.

Evaluation of Automated Seizure Detection Measurements in Cardiac Arrest Patients Undergoing Ceribell Rapid-EEG (S30.009)

<h3>Objective:</h3> To retrospectively evaluate the performance of the Clarity™ automated seizure detection system (Ceribell, Inc) for the detection of seizures and status epilepticus in cardiac arrest patients. <h3>Background:</h3> In cardiac arrest patients who remain comatose after return of spontaneous circulation, seizures and EEG abnormalities are common. Thus, guidelines recommend urgent EEG initiation for evaluation of seizures in this population. Point-of-care EEG systems, such as Ceribell™ Rapid-EEG, allow for prompt initiation of EEG monitoring, albeit through a limited-channel montage. Rapid-EEG incorporates an automated seizure detection software (Clarity™) to measure seizure burden in real time and alert clinicians when a high seizure burden, consistent with possible status epilepticus, is identified. External validation of Clarity is still needed. <h3>Design/Methods:</h3> This study was a retrospective review of Ceribell Rapid-EEG recordings from all the patients who were admitted to the medical intensive care unit at Kent Hospital (Warwick, RI, USA) between 6/1/2021 and 3/18/2022 for management after cardiac arrest and who underwent Rapid-EEG monitoring as part of their routine clinical care (n=21). Board-certified epileptologists identified events that met criteria for seizures or status epilepticus, as per the 2021 American Clinical Neurophysiology Society’s Standardized Critical Care EEG Terminology, and evaluated any seizure burden detections generated by Clarity. <h3>Results:</h3> In this study, 4 of 21 cardiac arrest patients (19.0%) who underwent Rapid-EEG monitoring had multiple electrographic seizures, and 2 of those patients (9.5%) had electrographic status epilepticus within the first 24 hours of the study. None of these ictal abnormalities were detected by the Clarity seizure detection system. Clarity showed 0% seizure burden during all these events. <h3>Conclusions:</h3> The presence of frequent seizures and/or status epilepticus may go undetected by currently available automated seizure detection systems. Timely and careful review of all raw Rapid-EEG recordings by a qualified human EEG reader is necessary to guide clinical care. <b>Disclosure:</b> Dr. Villamar has a non-compensated relationship as a Member of Editorial Board with Neurology: Clinical Practice that is relevant to AAN interests or activities. Dr. Villamar has a non-compensated relationship as a Member of Editorial Board with The Neurohospitalist that is relevant to AAN interests or activities. The institution of Dr. Ayub has received research support from Brown Physicians Incorporated. Dr. Koenig has received personal compensation in the range of $5,000-$9,999 for serving on a Speakers Bureau for Fuji SonoSite. Dr. Koenig has received personal compensation in the range of $5,000-$9,999 for serving on a Speakers Bureau for Medscape.

External Validation of Novel Method of Seizure Onset Zone Localization Based on Neural Resonance (P2-1.006)

<h3>Objective:</h3> We aimed to validate a recently published technique that used neural resonance to localize seizure onset zones (SOZ) with a retrospective dataset collected at an external institution. Further, we critically examined the need for a larger, tailored prospective validation study. <h3>Background:</h3> Accurate localization of the SOZ could improve surgical outcomes in medically refractory epilepsy patients. A recent study successfully used a novel metric of neural resonance to retrospectively identify SOZ regions and predict surgical success. The technique leverages distinct electrophysiological features of evoked responses during single pulse electrode stimulation (SPES) and incorporates them into a dynamical model. We aimed to validate these findings with a retrospective cohort of six patients to assess whether neural resonance predicted surgical outcomes. <h3>Design/Methods:</h3> We collected intracranial electroencephalographic (iEEG) data from six patients that underwent intracranial monitoring, single-pulse electrical stimulation protocol, and resection surgery between June 2020 and May 2021. Four out of six patients were stimulated in both SOZ regions and non-SOZ regions and thus were tested using the logistic regression model trained on the original dataset at the primary study institution. <h3>Results:</h3> Three of the four patients had successful surgical outcomes. Of the four patients tested with the logistic regression model, only one out of four was predicted correctly; the model predicted success for one true success and the failure patient. <h3>Conclusions:</h3> We hypothesize that the non-reproducibility of the original findings are resultant of differences in a research-driven SPES protocol and a clinically driven stimulation protocol. The external validation dataset stimulated a fewer number of sites, used a different clinical EEG and stimulation system, and varied stimulation parameters in a different subspace. However, this work highlights the need for a large, prospective validation dataset that is multi-center and encompasses a wide range of parameters; the gathering of this dataset is currently underway. <b>Disclosure:</b> Mr. Barnagian has nothing to disclose. Dr. Smith has nothing to disclose. Dr. Kang has nothing to disclose. Mark Hays has nothing to disclose. Dr. Gonzalez has nothing to disclose. Dr. Sarma has stock in Neurologic Solutions, Inc.. Dr. Barot has nothing to disclose.

Development of Brain-Computer Interface Technology Using Scalp Electroencephalography

Studies on electroencephalography-based brain computer interface (EEG-based BCI) has been widely studied since around 2000. In the studies, three methods, event-related desynchronization/synchronization (ERD/ERS) during a motor imagery task, a P300 component of event-related potential, and steady state visual evoked potential (SSVEP) has been studied as standard methods. Since around 2013, with the acceleration of research in the United States and other countries, there has been a wide variety of studies that is not limited to the standard methods, such as research and development toward practical application and studies on extracting new brain activity signals. Some of the research results have been developed as commercial products. In this paper, after reviewing the studies on EEG-based BCI, topics in the research and development toward practical application such as new EEG systems and artifact rejection methods are introduced, topics in the studies on extracting new brain activity signals such as applying deep learning, emotion estimation and visual image reconstruction are also introduced, and topics in combination of BCI and information and communications technology and combination of BCI and XR technology are introduced. Finally, prospects of BCI technology are discussed.

Analysis of spatio-temporal propagation of occipito-frontal spikes in childhood epilepsies by 3D sequential voltage mapping and dipole localization.

We sought to study the spatio-temporal propagation of occipito-frontal spikes in childhood epilepsies by voltage mapping and dipole localization and identify types of occipito-frontal spikes based on onset, propagation, and stability of their dipoles. Sleep EEG data of children, aged 1-14 years, with a minimum 1 h of recording from June 2018 to June 2021, were analyzed to identify occipito-frontal spikes. In total, 150 successive occipito-frontal spikes were manually selected from each EEG and using a source localization software were averaged using automated pattern matching with a threshold of 80%, and sequential 3D voltage maps of averaged spike were analyzed. Stability quotient (SQ) was calculated as the total number of averages/150. Stable dipole was defined as SQ ≥ .8. Dipole analysis was performed with principal component analysis using an age-appropriate template head model. Ten children with occipito-frontal spikes were identified; five with self-limited epilepsy with autonomic seizures (SeLEAS) and five with non-SeLEAS epilepsies. Three types of occipito-frontal spikes were identified: (1) narrow occipito-frontal spikes with stable dipoles seen in all five children with SeLEAS which were "apparently" synchronous and bilateral clone-like with an occipito-frontal interval of 10-30 ms and a homogeneous propagation pattern from a unilateral medial parieto-occipital region to an ipsilateral mesial frontal region; (2) wide occipito-frontal spikes with stable dipoles seen in one child with non-SeLEAS and developmental and/or epileptic encephalopathy with spike-wave activation in sleep (D/EE-SWAS) with an occipito-frontal interval of 45 ms, caused by focal spike propagation from a deeper temporal focus to ipsilateral peri-rolandic cortex; and (3) wide occipito-frontal spikes with unstable dipoles seen in four children with non-SeLEAS lesional epilepsies with an occipito-frontal latency of >50 ms and heterogeneous propagation patterns with poor intra-individual dipole stability. We successfully identified different types of occipito-frontal spikes in childhood epilepsies. Although the term "occipito-frontal" is used to describe these spikes on the 10-20 EEG system, true propagation from occipital to frontal regions is not necessary. It is possible to differentiate idiopathic from symptomatic cases by analyzing the stability quotient and the occipito-frontal interval of occipito-frontal spikes.

Prediction of Cognitive Load from Electroencephalography Signals Using Long Short-Term Memory Network

In recent years, the development of adaptive models to tailor instructional content to learners by measuring their cognitive load has become a topic of active research. Brain fog, also known as confusion, is a common cause of poor performance, and real-time detection of confusion is a challenging and important task for applications in online education and driver fatigue detection. In this study, we propose a deep learning method for cognitive load recognition based on electroencephalography (EEG) signals using a long short-term memory network (LSTM) with an attention mechanism. We obtained EEG signal data from a database of brainwave information and associated data on mental load. We evaluated the performance of the proposed LSTM technique in comparison with random forest, Adaptive Boosting (AdaBoost), support vector machine, eXtreme Gradient Boosting (XGBoost), and artificial neural network models. The experimental results demonstrated that the proposed approach had the highest accuracy of 87.1% compared to those of other algorithms, including random forest (64%), AdaBoost (64.31%), support vector machine (60.9%), XGBoost (67.3%), and artificial neural network models (71.4%). The results of this study support the development of a personalized adaptive learning system designed to measure and actively respond to learners' cognitive load in real time using wireless portable EEG systems.

How robustly do multivariate EEG patterns track individual-subject lexico-semantic processing of visual stimuli?

ABSTRACT Electroencephalography may be a valuable tool for assessing lexico-semantic processing in conditions where behavioural measures are unreliable. Detecting and quantifying effects in individuals is crucial for clinical applications, but individual-subject analyses are frequently not reported, and are hampered by low signal-to-noise. Multivariate analyses (MVPA) may be more sensitive than traditional approaches, so we asked how robustly they could detect differential neural responses to semantically matched and mismatched word/picture pairs in individuals. With clinical application in mind, we compared data from a research-grade EEG system to concurrently recorded data from the wireless Emotiv EPOC + . In both EEG systems, despite robust group-level effects, we only detected statistically significant processing of lexico-semantic condition in 50% of individuals. Surprisingly, detection rates were similar for MVPA and univariate analyses. MVPA may be advantageous when individual responses are heterogeneous, but in this simple paradigm, lexico-semantic processing could not be reliably detected at the individual level.

A Visuospatial Planning Task Coupled with Eye-Tracker and Electroencephalogram Systems.

The planning process, characterized by the capability to formulate an organized plan to reach a goal, is essential for human goal-directed behavior. Since planning is compromised in several neuropsychiatric disorders, the implementation of proper clinical and experimental tests to examine planning is critical. Due to the nature of the deployment of planning, in which several cognitive domains participate, the assessment of planning and the design of behavioral paradigms coupled with neuroimaging methods are current challenges in cognitive neuroscience. A planning task was evaluated in combination with an electroencephalogram (EEG) system and eye movement recordings in 27 healthy adult participants. Planning can be separated into two stages: a mental planning stage in which a sequence of steps is internally represented and an execution stage in which motor action is used to achieve a previously planned goal. Our protocol included a planning task and a control task. The planning task involved solving 36 maze trials, each representing a zoo map. The task had four periods: i) planning, where the subjects were instructed to plan a path to visit the locations of four animals according to a set of rules; ii) maintenance, where the subjects had to retain the planned path in their working memory; iii) execution, where the subjects used eye movements to trace the previously planned path as indicated by the eye-tracker system; and iv) response, where the subjects reported the order of the visited animals. The control task had a similar structure, but the cognitive planning component was removed by modifying the task goal. The spatial and temporal patterns of the EEG revealed that planning induces a gradual and lasting rise in frontal-midline theta activity (FMθ) over time. The source of this activity was identified within the prefrontal cortex by source analyses. Our results suggested that the experimental paradigm combining EEG and eye-tracker systems was optimal for evaluating cognitive planning.

How low can you go? Measuring human event-related brain potentials from a two-channel EEG system

Over the past ten years, there has been a rapid increase in the availability and use of mobile electroencephalography (mEEG) in research. Indeed, researchers using mEEG have recorded EEG and event-related brain potentials in a wide range of environments - for example, while walking (Debener et al., 2012), riding a bike (Scanlon et al., 2020), or even in a shopping mall (Krigolson et al., 2021). However, given that low-cost, ease-of-use, and setup speed provide the primary advantages of an mEEG system over large array traditional EEG systems, an important and unresolved question is just how many electrodes does an mEEG system need to collect research-quality EEG data? Here, we tested whether or not a two-channel forehead-mounted mEEG system – the “Patch” – could measure event-related brain potentials within their established amplitude and latency characteristics (Luck, 2014). In the present study, participants performed a visual oddball task while we recorded EEG data from the Patch. Our results demonstrated that we could capture and quantify the N200 and P300 event-related brain potential components using a minimal electrode array forehead-mounted EEG system. Our data further support the idea that mEEG can be used for quick and rapid EEG-based assessments, such as measuring the impact of concussions on the sports field (Fickling et al., 2021) or assessing the impact of stroke severity in a hospital (Wilkinson et al., 2020).

Hyperscanning EEG Paradigm Applied to Remote vs. Face-To-Face Learning in Managerial Contexts: Which Is Better?

We propose a hyperscanning research design, where electroencephalographic (EEG) data were collected on an instructor and teams of learners. We compared neurophysiological measures within the frequency domain (delta, theta, alpha, and beta EEG bands) in the two conditions: face-to-face and remote settings. Data collection was carried out using wearable EEG systems. Conversational analysis was previously applied to detect comparable EEG time blocks and semantic topics. The digitalization of training can be considered a challenge but also a chance for organizations. However, if not carefully addressed, it might constitute a criticality. Limited research explored how remote, as opposed to face-to-face, training affects cognitive, (such as memory and attention), affective, and social processes in workgroups. Data showed an alpha desynchronization and, conversely, a theta and beta synchronization for the face-to-face condition. Moreover, trainees showed different patterns for beta power depending on the setting condition, with significantly increased power spectral density (PSD) in the face-to-face condition. These results highlight the relevance of neurophysiological measures in testing the e-learning process, in relation to the emotional engagement, memory encoding, and attentional processing.

Noise characteristics in spaceflight multichannel EEG.

The cognitive performance of the crew has a major impact on mission safety and success in space flight. Monitoring of cognitive performance during long-duration space flight therefore is of paramount importance and can be performed using compact state-of-the-art mobile EEG. However, signal quality of EEG may be compromised due to the vicinity to various electronic devices and constant movements. We compare noise characteristics between in-flight extraterrestrial microgravity and ground-level terrestrial electroencephalography (EEG) recordings. EEG data recordings from either aboard International Space Station (ISS) or on earth's surface, utilizing three EEG amplifiers and two electrode types, were compared. In-flight recordings showed noise level of an order of magnitude lower when compared to pre- and post-flight ground-level recordings with the same EEG system. Noise levels between ground-level recordings with actively shielded cables, and in-flight recordings without shielded cables, were similar. Furthermore, noise level characteristics of shielded ground-level EEG recordings, using wet and dry electrodes, and in-flight EEG recordings were similar. Actively shielded mobile dry EEG systems will support neuroscientific research and neurocognitive monitoring during spaceflight, especially during long-duration space missions.

Supporting the Detection of Early Alzheimer's Disease with a Four-Channel EEG Analysis.

Alzheimer's disease (AD) is the most prevalent form of dementia. Although there is no current cure, medical treatment can help to control its progression. Hence, early-stage diagnosis is crucial to maximize the living standards of the patients. Biochemical markers and medical imaging in combination with neuropsychological tests represent the most extended diagnosis procedure. However, these techniques require specialized personnel and long processing time. Furthermore, the access to some of these techniques is often limited in crowded healthcare systems and rural areas. In this context, electroencephalography (EEG), a non-invasive technique to obtain endogenous brain information, has been proposed for the diagnosis of early-stage AD. Despite the valuable information provided by clinical EEG and high density montages, these approaches are impractical in conditions such as those described above. Consequently, in this study, we evaluated the feasibly of using a reduced EEG montage with only four channels to detect early-stage AD. For this purpose, we involved eight clinically diagnosed AD patients and eight healthy controls. The results we obtained reveal similar accuracies ([Formula: see text]-value[Formula: see text]0.66) for the reduced montage (0.86) and a 16-channel montage (0.87). This suggests that a four-channel wearable EEG system could be an effective tool for supporting early-stage AD detection.

Automated Seizure Detection in Patients with Cardiac Arrest: A Retrospective Review of Ceribell™ Rapid-EEG Recordings.

In patients with cardiac arrest who remain comatose after return of spontaneous circulation, seizures and other abnormalities on electroencephalogram (EEG) are common. Thus, guidelines recommend urgent initiation of EEG for the evaluation of seizures in this population. Point-of-care EEG systems, such as Ceribell™ Rapid Response EEG (Rapid-EEG), allow for prompt initiation of EEG monitoring, albeit through a reduced-channel montage. Rapid-EEG incorporates an automated seizure detection software (Clarity™) to measure seizure burden in real time and alert clinicians at the bedside when a high seizure burden, consistent with possible status epilepticus, is identified. External validation of Clarity is still needed. Our goal was to evaluate the real-world performance of Clarity for the detection of seizures and status epilepticus in a sample of patients with cardiac arrest. This study was a retrospective review of Rapid-EEG recordings from all the patients who were admitted to the medical intensive care unit at Kent Hospital (Warwick, RI) between 6/1/2021 and 3/18/2022 for management after cardiac arrest and who underwent Rapid-EEG monitoring as part of their routine clinical care (n = 21). Board-certified epileptologists identified events that met criteria for seizures or status epilepticus, as per the 2021 American Clinical Neurophysiology Society's Standardized Critical Care EEG Terminology, and evaluated any seizure burden detections generated by Clarity. In this study, 4 of 21 patients with cardiac arrest (19.0%) who underwent Rapid-EEG monitoring had multiple electrographic seizures, and 2 of those patients (9.5%) had electrographic status epilepticus within the first 24h of the study. None of these ictal abnormalities were detected by the Clarity seizure detection system. Clarity showed 0% seizure burden throughout the entirety of all four Rapid-EEG recordings, including the EEG pages that showed definite seizures or status epilepticus. The presence of frequent electrographic seizures and/or status epilepticus can go undetected by Clarity. Timely and careful review of all raw Rapid-EEG recordings by a qualified human EEG reader is necessary to guide clinical care, regardless of Clarity seizure burden measurements.