EEG Duration Research Articles

Optimizing electroencephalogram duration for efficient detection of epileptiform abnormalities in diverse patient groups: a retrospective study

BackgroundThere is no standardized EEG duration guideline for detecting epileptiform abnormalities in patients, and research on this topic is scarce. This study aims to determine an optimal EEG duration for efficient detection of epileptiform abnormalities across different patient groups.MethodsRetrospective analysis was performed on EEG recordings and clinical data of patients with the first seizure and epilepsy. Patients were categorized based on various factors, including the interval time since the last seizure, use of anti-seizure medication (ASM), and seizure frequency. The detection ratio (DR) of epileptiform abnormalities and latency time for their discovery were calculated. Statistical analyses, including chi-square tests, logistic regression, and survival analysis were utilized to illustrate DR and latency times.ResultsIn whole-night EEG recordings, the DR was 37.6% for the first seizure group and 57.4% for the epilepsy group. Although the maximum latency times were 720 min in both two groups, DR in the first seizure group was distinctly decreased beyond 300 min. Significant factors influencing the DR included the use of ASM in the first seizure group (P < 0.05) and seizure frequency in the epilepsy group (P < 0.001). For epilepsy patients who experience a seizure at least once a month or undergo timely EEG recordings (within 24 h after a seizure), the DR significantly increases, and the maximum latency time is reduced to 600 min (P < 0.001). Additionally, the DR was significantly reduced after 240 min in epilepsy patients who had been seizure-free for more than one year.ConclusionsIn this retrospective study, we observed a maximum latency of 720 min for detecting epileptiform abnormalities in whole-night EEG recordings. Notably, epilepsy patients with a higher seizure frequency or timely EEG recordings demonstrated both a higher detection ratio and a shorter maximum latency time. For patients exhibiting a low detection ratio, such as those experiencing their first seizure or those with epilepsy who have been seizure-free for more than a year, a shorter EEG duration is recommended. These findings underscore the importance of implementing customized EEG strategies to meet the specific needs of different patient groups.

Assessing the Yield of Reduced Duration-EEG Recordings in Children: A Cross-Sectional Study.

Introduction An EEG is an important tool in the diagnosis of neurological diseases. Performing an EEG on children can be challenging due to their tendency to not cooperate for the recommended duration. We aim to optimize the duration of EEG recording in children by finding the optimal duration of recording. Materials and methods A single-center prospective observational study was done after appropriate ethical clearance. Children aged 0-14 were recruited and examined, and the recommended EEG was done. Data were collected and analyzed. Results Of the 112 EEGs analyzed, 29 EEGs were normal, i.e., no diagnostic anomaly was noticed. In the remaining 83 EEGs, if the duration of the EEG was reduced to 20 minutes, it resulted in missing the diagnostic anomaly in 20 cases (24.1%; 95% CI: 11.2%-26.2%). Reducing the duration of the EEG recording to 10 minutes resulted in missing 63 of the diagnostic anomalies (75.9%; 95% CI: 46.6%-65.6%). Of the 86 drug-inducedEEGs, 22 were normal (25.6%; 95% CI: 16.8%-36.1%). Of the 24 routine EEGs, seven were normal (29.2%; 95% CI: 12.6%-51.1%). Of the two sleep-deprived EEGs, neither was normal (0.0%; 95% CI: 0.0%-84.1%). Conclusion In our study, we observed that optimization of the duration ofEEG recording can be done to 20 minutes in all populations. We also observed that if we find a diagnostic abnormality early during EEG recording, then continuation of the EEG may not be necessary to make a valid report. Having said so, having a negative EEG may not necessarily rule out a diagnosis. We did not find the superiority of any of the EEG protocols over others, as their yield was comparable.

“Mail-slot” Technique for Minimally Invasive Placement of Subdural Grid Electrodes: A Single-institution Experience

BackgroundIn the management of multi-drug-resistant focal epilepsies, intracranial electrode implantation is employed for precise localization of the ictal onset zone. In select patients, subdural grid electrode implantation is utilized. Subdural grid placement traditionally requires large craniotomies to visualize the cortex prior to mapping. However, smaller craniotomies may enable shorter operations and reduced risks. We aimed to compare surgical outcomes between patients undergoing traditional large craniotomies with those undergoing tailored 'mini' craniotomies (the “Mail-Slot” technique) for subdural grid placement. MethodsThis retrospective cohort study included 23 patients who underwent subdural electrode implantation for epilepsy monitoring between 2014 and 2020. Patients were categorized into mini craniotomies (N=9) and traditional large craniotomies (N=14) groups. Demographics, operative details, and outcomes were reviewed. Craniotomy size and number of electrodes were determined via post-hoc radiographs. ResultsOf the 23 patients studied, the mini group had smaller craniotomy sizes (mean=22.71 cm2 vs. 65.17 cm2, p<0.001) and higher electrode-to-size ratios (mean=4.25 vs. 1.71, p<0.0001). The mini group had slightly fewer total electrodes (mean=88.67 vs. 107.43, p=0.047). No significant differences were found in operative duration, blood loss, invasive EEG duration, complications, or Engel scores between the groups. One patient per group required further invasive epilepsy monitoring for localization; all patients underwent therapeutic surgery. ConclusionOur findings suggest that mini craniotomies for subdural grid placement in epilepsy monitoring offer significant advantages, including smaller craniotomy sizes and shorter operation durations, without compromising safety or efficacy. These results support the trend towards minimally invasive, patient-tailored surgical approaches in epilepsy treatment.

Determinants of successful ictal SPECT injection in phase 1 epilepsy presurgical evaluation: Findings from the pediatric epilepsy research consortium surgery database project.

The main goal of presurgical evaluation in drug-resistant focal epilepsy is to identify a seizure onset zone (SOZ). Of the noninvasive, yet resource-intensive tests available, ictal single-photon emission computed tomography (SPECT) aids SOZ localization by measuring focal increases in blood flow within the SOZ via intravenous peri-ictal radionuclide administration. Recent studies indicate that geographic and center-specific factors impact utilization of these diagnostic procedures. Our study analyzed successful ictal SPECT acquisition (defined as peri-ictal injection during inpatient admission) using surgery-related data from the Pediatric Epilepsy Research Consortium (PERC) surgery database. We hypothesized that a high seizure burden, longer duration of video EEG monitoring (VEEG), and more center-specific hours of SPECT availability would increase the likelihood of successful ictal SPECT. We identified study participants (≤18 years of age) who underwent SPECT as part of their phase 1 VEEG from January 2018 to June 2022. We assessed association between ictal SPECT outcomes (success vs. failure) and variables including patient demographics, epilepsy history, and center-specific SPECT practices. Phase 1 VEEG monitoring with ictal SPECT injection was planned in 297 participants and successful in 255 participants (85.86%). On multivariable analysis, the likelihood of a successful SPECT injection was higher in patients of non-Hispanic ethnicity (p = 0.040), shorter duration VEEG (p = 0.004), and higher hours of available SPECT services (p < 0.001). Higher seizure frequency (p = 0.033) was significant only in bivariate analysis. Patients treated at centers with more operational hours were more likely to experience pre-admission protocols prior to VEEG (p = 0.002). There is inter-center variability in protocols and SPECT acquisition capabilities. Shorter duration of EEG monitoring, non-Hispanic ethnicity (when on private insurance), extended operational hours of nuclear medicine as noted on multivariate analysis and higher seizure frequency in bivariate analysis are strongly associated with successful ictal SPECT injection. In pediatric patients with drug-resistant epilepsy, single-photon emission computed tomography (SPECT) scans can be helpful in localizing seizure onset zone. However, due to many logistical challenges described below, which include not only the half-life of the technetium isotope used to inject intravenously during a seizure (called the ictal SPECT scan) but also available nuclear scanner time in addition to the unpredictability of seizures, obtaining an ictal SPECT during a planned elective inpatient hospital stay is not guaranteed. Thus, as healthcare costs increase, planning a prolonged hospital stay during which an ictal SPECT scan is not feasible is not optimal. We leveraged our prospective surgery database to look at center-specific factors and patient-specific factors associated with an ictal SPECT injection in the first, pediatric-focussed, large-scale, multicenter, prospective, SPECT feasibility study. We found that longer availability of the scanner is the most important center-specific factor in assuring ictal SPECT injection. Although seizure frequency is an important patient-specific factor on bivariate analysis, this factor lost statistical significance when other factors like patient insurance status and video EEG duration were also considered in our multivariable logistical model.

Continuous Electroencephalogram (cEEG) Findings and Neurodevelopmental Outcomes in Neonates with Congenital Heart Disease (CHD) at 12-24 Months of Age.

This study aims to assess the role of continuous EEG (cEEG) background patterns and duration of cross-clamp time and cardiopulmonary bypass (CPB) in children with congenital heart disease (CHD) undergoing cardiac surgery and its correlation with abnormal neurodevelopmental outcomes at 12-24 months on Bayley Scales of Infant and Toddler Development (BSID-III). This retrospective cohort study included infants with CHD and cEEG monitoring, who underwent surgery by 44 weeks gestational age. 34 patients were included, who were operated at median age - 7 days. Longer duration of cross- camp time was associated with poor language composite scores (LCS) (p value = 0.036). A significant association existed between severity of encephalopathy in 24-hour post-operative period and poor LCS (p value = 0.026). Majority of neonates with CHD have below average cognitive, language and motor composite scores on BSID-III. Longer duration of cross-clamp time and severity of encephalopathy during 24-hour post-operative EEG monitoring are associated with poor LCS.

Clinical observation: Rhythmic and periodic EEG patterns in postanoxic coma can possibly be related to propofol discontinuation

ObjectivesTo investigate whether rhythmic/periodic EEG patterns (RPP) appearing after propofol discontinuation are more likely to be related to the elimination phase of propofol, or are an expression of severe brain damage. MethodsIn a retrospective cohort of comatose postanoxic patients, EEG was assessed one hour before (baseline) and on hour after discontinuation of propofol. Presence and duration of RPP were related to (changes in) EEG background pattern and duration of sedation. ResultsIn eleven (of 36 eligible) patients RPP appeared after propofol discontinuation and disappeared in seven of these patients within one hour. A continuous background pattern at baseline and shorter duration of propofol infusion seemed associated with (earlier) spontaneous disappearance of RPP. In ten patients with RPP at baseline, the EEG did not change, and in one patient it changed into burst-suppression. ConclusionOur findings suggest that RPP after propofol discontinuation could be propofol-related. DiscussionRPP might be related to propofol discontinuation rather than an expression of severe brain damage, especially in case of, and congruent with, a continuous pattern at the time of propofol discontinuation. This opens a new insight in this phenomenon and its transient nature. In clinical practice, we suggest to consider the timing of propofol discontinuation when assessing the EEG signal in postanoxic patients.

Individualized Care Delivery for Children With Autism and Related Disabilities Undergoing Overnight Video Electroencephalography (EEG): One Hospital's Experience With a Coordinated Team Approach.

Background and Purpose: Children with developmental disabilities have increased risk of epilepsy and need for overnight video electroencephalographic (EEG) monitoring. However, video EEGs have historically been considered difficult to complete for this population. An autism support service at a pediatric tertiary care hospital implemented a coordinated team approach to help children with developmental disability tolerate overnight video EEGs. The project included completion of a caregiver-report preprocedure questionnaire that then was shared with the multidisciplinary team and used to create individualized care plans. The current study aims to describe rates of video EEG completion and need for lead placement under general anesthesia among children with autism and related disabilities who received these supports. Methods: Rates of video EEG completion and general anesthesia use were analyzed for children referred to the support service between April 2019 and November 2021. Results: A total of 182 children with developmental disability (mean age = 10.3 years, 54.9% diagnosed with autism) met inclusion criteria. 92.9% (n = 169) of children successfully completed EEG (leads on ≥12 hours). Only 19.2% (n = 35) required general anesthesia for video EEG lead placement. The majority (80.2%) of parents (n = 146) completed the preprocedure questionnaire. Video EEG outcomes did not differ based on completion of the questionnaire. Parent-reported challenges with communication and cooperation were associated with shorter video EEG duration and greater use of general anesthesia. Conclusions: These findings suggest that most children with developmental disability can complete video EEG with sufficient support. Preprocedure planning can identify children who would benefit from additional accommodations. Further research is necessary to clarify which supports are most helpful.

Effect of remimazolam on electroencephalogram burst suppression in elderly patients undergoing cardiac surgery: Protocol for a randomized controlled noninferiority trial

BackgroundPostoperative delirium (POD) is a common complication following cardiac surgery and increases postoperative morbidity and mortality. Intraoperative electroencephalogram (EEG) burst suppression suggests excessively deep anesthesia and predicts POD. Use of remimazolam provides a stable hemodynamic status and an appropriate depth of anesthesia. We aim to assess remimazolam administered for anesthesia and sedation in elderly patients having cardiac surgery. MethodsThis is a randomized controlled clinical trial with noninferiority design. A total of 260 elderly patients aged equal to or greater than 60 years undergoing cardiac surgery will be randomly allocated to receive remimazolam or propofol (1:1) for general anesthesia and postoperative sedation until extubation. The primary outcome is the cumulative time with EEG burst suppression which is obtained from the SedLine system. The noninferiority margin is 2.0 min. The secondary outcomes include the POD occurrence within the first 5 days postoperatively and the duration of perioperative hypotension. DiscussionThis noninferiority trial is the first to evaluate the effect of perioperative remimazolam administration on EEG burst suppression, POD occurrence, and duration of hypotension in elderly patients who undergo cardiac surgery. Trial registrationChinese Clinical Trial Registry (ChiCTR2200056353).

Developing customized NIRS-EEG for infant sleep research: methodological considerations.

Studies using simultaneous functional near-infrared spectroscopy (fNIRS)-electroencephalography (EEG) during natural sleep in infancy are rare. Developments for combined fNIRS-EEG for sleep research that ensure optimal comfort as well as good coupling and data quality are needed. We describe the steps toward developing a comfortable, wearable NIRS-EEG headgear adapted specifically for sleeping infants ages 5 to 9 months and present the experimental procedures and data quality to conduct infant sleep research using combined fNIRS-EEG. 5- to 9-month-old infants participated. In phase 1, (10 = slept) participated using the non-wearable version of the NIRS-EEG headgear with 13-channel-wearable EEG and 39-channel fiber-based NIRS. In phase 2, infants (21 = slept) participated with the wireless version of the headgear with 20-channel-wearable EEG and 47-channel wearable NIRS. We used QT-NIRS to assess the NIRS data quality based on the good time window percentage, included channels, nap duration, and valid EEG percentage. The infant nap rate during phase 1 was (45% valid EEG data) and increased to 90% during phase 2 (100% valid EEG data). Infants slept significantly longer with the wearable system than the non-wearable system. However, there were more included good channels based on QT-NIRS in study phase 1 (61%) than phase 2 (50%), though this difference was not statistically significant. We demonstrated the usability of an integrated NIRS-EEG headgear during natural infant sleep with both non-wearable and wearable NIRS systems. The wearable NIRS-EEG headgear represents a good compromise between data quality, opportunities of applications (home visits and toddlers), and experiment success (infants' comfort, longer sleep duration, and opportunities for caregiver-child interaction).

Continuous Electroencephalography (EEG) Protocol Improves Seizure Detection in Children on Extracorporeal Membrane Oxygenation.

Seizures are a complication for pediatric patients requiring extracorporeal membrane oxygenation (ECMO). There are no standardized guidelines regarding continuous electroencephalography (EEG) monitoring to detect seizures in these patients, and the impact of protocolized monitoring has not been evaluated. Here we examined the effects of continuous EEG protocol implementation in our pediatric ECMO population. Retrospective chart reviews were conducted on 57 patients who underwent extracorporeal membrane oxygenation and concurrent continuous EEG out of 165 patients supported on extracorporeal membrane oxygenation. Timing of continuous EEG initiation and seizures detected by continuous EEG was determined for 5 years prior to and 15 months after protocol implementation. Protocol implementation was associated with increased ECMO-supported patients who were concurrently monitored by continuous EEG. Time from ECMO cannulation to continuous EEG initiation was shorter (median 7 hours after versus 16.2 hours before; P < .001). Patients who had ongoing seizures at the start of continuous EEG recording decreased from 64% preprotocol to 0% postprotocol (P < .001), and there was an associated earlier time to break in status epilepticus postprotocol. Seizures were detected past 48 hours after cannulation in 50% of patients in the postprotocol group. Protocol implementation resulted in earlier continuous EEG initiation and more EEGs initiated before seizure onset with evidence of altered seizure dynamics. Although current recommendations suggest that continuous EEG duration of 24-48 hours results in seizure detection for >90% of critically ill adults, longer monitoring may be needed to reliably detect seizures in children supported with ECMO, particularly if monitoring is initiated earlier in the post-cannulation period.

Automated diagnosis of epileptic seizures using EEG image representations and deep learning

BackgroundThe identification of seizure and its complex waveforms in electroencephalography (EEG) through manual examination is time consuming, tedious, and susceptible to human mistakes. These issues have prompted the design of an automated seizure detection system that can assist the neurophysiologists by providing a fast and accurate analysis. MethodsExisting automated seizure detection systems are either machine learning based or deep learning based. Machine learning based algorithms employ handcrafted features with sophisticated feature selection approaches. As a result of which their performance varies with the choice of the feature extraction and selection techniques employed. On the other hand, deep learning-based methods automatically deduce the best subset of features required for the categorization task but they are computationally expensive and lacks generalization on clinical EEG datasets. To address the above stated limitations and motivated by the advantage of continuous wavelet transform's (CWT) in elucidating the non-stationary nature of the EEG signals in a better way, we propose an approach based on EEG image representations (constructed via applying WT at different scale and time intervals) and transfer learning for seizure detection. Firstly, the pre-trained model is fine-tuned on the EEG image representations and thereafter features are extracted from the trained model by performing activations on different layers of the network. Subsequently, the features are passed through a Support Vector Machine (SVM) for categorization using a 10-fold data partitioning scheme. Results and comparison with existing methodsThe proposed mechanism results in a ceiling level of classification performance (accuracy=99.50/98.67, sensitivity=100/100 & specificity=99/96) for both the standard and the clinical dataset that are better than the existing state-of-the art works. ConclusionThe rapid advancement in the field of deep learning has created a paradigm shift in automated diagnosis of epilepsy. The proposed tool has effectually marked the relevant EEG segments for the clinician to review thereby reducing the time burden in scanning the long duration EEG records.

A Standardized, 3-Tiered, Seizure Burden-Based Protocol for the Treatment of Neonatal Seizures.

To evaluate use of a standardized, 3-tiered, seizure burden-based protocol for treatment of all electroencephalography (EEG)-confirmed seizures in a level IV neonatal intensive care unit (NICU). All infants admitted to the NICU with EEG-confirmed seizures over a 25-month period were enrolled in the study. We compared short-term outcomes before and after implementation of a standardized, 3-tiered protocol. A total of 107 infants were enrolled in the study. Use of midazolam infusions was reduced by 53.7% (p = 0.02). Midazolam infusion duration increased from 4 to 7.5 days (p = 0.003); however, when excluding 3 outliers, there was no significant difference between groups (-p = 0.67). Duration of EEG monitoring decreased from 5 to 3 days (p = 0.005). Hospital length of stay was unchanged. Implementation of a standardized, 3-tiered protocol for treatment of neonatal seizures improved short-term outcomes. Although not measured directly, reductions in EEG duration and midazolam use are promising indicators of overall seizure burden. More research is needed to evaluate impact on long-term neurodevelopmental outcomes.

Computer-aided diagnosis of autism spectrum disorder from EEG signals using deep learning with FAWT and multiscale permutation entropy features.

Autism spectrum disorder (ASD), a neurodevelopment disorder, is characterized by significant difficulties in social interaction and emerges as a major threat to children. Its computer-aided diagnosis used by neurologists improves the detection process and has a favorable impact on patients' health. Currently, a biomarker termed electroencephalography (EEG) is considered as vital tool to detect abnormal electrical activity in the brain. In this context, the present paper brings forth a novel approach for automated diagnosis of ASD from multichannel EEG signals using flexible analytic wavelet transform (FAWT). Firstly, this approach processes the acquired EEG signals with filtering and segmentation into short-duration EEG segments in the range of 5-20 s. These segmented EEG signals are decomposed into five levels using FAWT technique to obtain various sub-bands. Further, multiscale permutation entropy values are extracted from decomposed sub-bands which are used as feature vectors in the present work. Afterwards, these feature vectors are evaluated by traditional machine learning algorithms viz., k-nearest neighbor, logistic regression, support vector machine, and random forest, as well as convolutional neural network (CNN) as deep learning algorithm with different segment durations. The analysis of results reveals that CNN provides maximum accuracy, sensitivity, specificity, and area under the curve of 99.19%, 99.34%, 99.21%, and 0.9997, respectively, for 10 s duration EEG segment to identify ASD patients among healthy individuals. Thus, the proposed CNN architecture would be extremely helpful during diagnostic process of autism disease for neurologists.

Assessment of Electroencephalographic Changes and Clinical Characteristics Among Patients with Substance-Related Disorder

Background: Substance abuse is defined as the hazardous use of psychoactive substances such as alcohol and illegal narcotics. It is a significant global public health concern. Chronic relapsing diseases, defined by compulsive use of drugs despite negative health effects, were substantial contributors to the illness burden in the USA and all over the world. Objective: The objectives were as follows: (a) to determine the presence of electroencephalographic (EEG) changes and their types among patients with substance-related disorders and (b) to evaluate the sociodemographic and clinical characteristics of patients with substance-related disorder. Materials and Methods: It was a cross-sectional study conducted from September 1, 2021 to August 1, 2022. It was performed on 112 patients (104 males and 8 females) in the Neurophysiology Department of Al Imam Al Sadiq Teaching Hospital in Al-Hilla Governorate. The patients were diagnosed by psychiatrists, according to the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition. All patients were assessed by history, physical examination, and EEG test. Results: The study showed that the frequency of EEG changes was 57.1%, whereas those without any changes was 42.9%. Those with score 2 or moderate severity were 53.6%. Severe abnormalities were found in 3.5% of the patients. There was a significant association between the EEG change and the type of substance taken, with a P-value of 0.008. The study showed the association between the EEG change and duration of substance taken, with a P-value of 0.0001, which was significant. There was a significant association between the type of substance taken and age (P = 0.002). The association between the type of substance taken and gender, residence, and occupation was non-significant. Conclusion: The study concluded that the EEG changes were of high prevalence in patients with substance-related disorder. The most common abnormality was score 2 (moderate severity). The most common substance with an abnormal EEG change was amphetamine.

Characterizing TMS-EEG perturbation indexes using signal energy: initial study on Alzheimer's Disease classification.

Transcranial Magnetic Stimulation (TMS) combined with EEG recordings (TMS-EEG) has shown great potential in the study of the brain and in particular of Alzheimer's Disease (AD). In this study, we propose an automatic method of determining the duration of TMS-induced perturbation of the EEG signal as a potential metric reflecting the brain's functional alterations. A preliminary study is conducted in patients with Alzheimer's disease (AD). Three metrics for characterizing the strength and duration of TMS-evoked EEG (TEP) activity are proposed and their potential in identifying AD patients from healthy controls was investigated. A dataset of TMS-EEG recordings from 17 AD and 17 healthy controls (HC) was used in our analysis. A Random Forest classification algorithm was trained on the extracted TEP metrics and its performance is evaluated in a leave-one-subject-out cross-validation. The created model showed promising results in identifying AD patients from HC with an accuracy, sensitivity and specificity of 69.32%, 72.23% and 66.41%, respectively. Clinical relevance- Three preliminary metrics were proposed to quantify the strength and duration of the response to TMS on EEG data. The proposed metrics were successfully used to identify Alzheimer's disease patients from healthy controls. These results proved the potential of this approach which will provide additional diagnostic value.

High incidence of epileptiform activity in adults undergoing extracorporeal membrane oxygenation

ObjectiveThe prevalence of seizures and other types of epileptiform brain activity in patients undergoing extracorporeal membrane oxygenation (ECMO) is unknown. We aimed to estimate the prevalence of seizures and ictal-interictal continuum patterns in patients undergoing electroencephalography (EEG) during ECMO. MethodsRetrospective review of a prospective ECMO registry from 2011-2018 in a university-affiliated academic hospital. Adult subjects who had decreased level of consciousness and underwent EEG monitoring for seizure screening were included. EEG classification followed the American Clinical Neurophysiology Society criteria. Poor neurological outcome was defined as a Cerebral Performance Category of 3–5 at hospital discharge. ResultsThree hundred and ninety-five subjects had ECMO, and one hundred and thirteen (28.6%) had EEG monitoring. Ninety-two (23.3%) subjects had EEG performed during ECMO and were included in the study (average EEG duration 54 h). Veno-arterial ECMO was the most common cannulation strategy (83%) and 26 (28%) subjects had extracorporeal cardiopulmonary resuscitation. Fifty-eight subjects (63%) had epileptiform activity or ictal-interictal continuum patterns on EEG, including three (3%) subjects with nonconvulsive status epilepticus, 33 (36%) generalized periodic discharges, and 4 (5%) lateralized periodic discharges. Comparison between subjects with or without epileptiform activity showed comparable in-hospital mortality (57% vs. 47%, p = 0.38) and poor neurological outcome (and 56% and 36%, p = 0.23). Twenty-seven subjects (33%) had acute neuroimaging abnormalities (stroke N = 21). ConclusionsSeizures and ictal-interictal continuum patterns are commonly observed in patients managed with ECMO. Further studies are needed to evaluate whether epileptiform activity is an actionable target for interventions. SignificanceEpileptiform and ictal-interictal continuum abnormalities are frequently observed in patients supported with ECMO undergoing EEG monitoring.

Modeling phasmophobia (fear of ghosts) using electroencephalogram

&lt;span&gt;Extreme fears towards ghosts and entities are defined as phasmaphobia. Those diagnosed with phasmophobia symptoms should control their own fears to avoid phasmaphobia attack. In this work, we present the development of phasmophobia detection electroencephalogram database (PDED).&lt;/span&gt;&lt;span&gt;PDED&lt;/span&gt;&lt;span&gt;consists&lt;/span&gt;&lt;span&gt;of&lt;/span&gt;&lt;span&gt;an&lt;/span&gt;&lt;span&gt;average&lt;/span&gt;&lt;span&gt;of&lt;/span&gt;&lt;span&gt;45&lt;/span&gt;&lt;span&gt;minutes electroencephalography (EEG) recordings from eight electrodes situated on the frontal lobe of the brain area. A real-time fear assessment was conducted simultaneously with the EEG recording by the participant. Five different stimuli were used to induce fear in our experiment. 599 EEG epochs related to fear were extracted based on the timestamp recorded by each individual. Asymmetry relation ratio (ARR) techniques were used on these EEG to detect the presence of fear. The quality of long duration of EEG recording from PDED in recognizing fear was thoroughly presented based on ARR. In this study, 91.5% of fear emotion managed to be detected from these epochs. Using PDED, it is also proven that the changes of ARR reflected positive correlation towards the changes of the level of fear. Analysis using emotion recognition rate (ERR) curves indicated that, two electrodes, namely F7 and F8, were sufficient to recognized 88% of fear from the recordings.&lt;/span&gt;

Evolutionary inspired approach for mental stress detection using EEG signal

Stress is a pensive issue in our competitive world and it has a huge impact on physical and mental health. Severe health issues may arise due to long exposure of stress. Hence, its timed detection can be helpful in managing stress periods. In this regard, electroencephalogram (EEG) based techniques have been widely explored, as stress severely impact the functioning and structure of brain. These non-invasive methods for stress detection need improvement in terms of predictive accuracy and reliability. In this work, a novel approach for stress detection has been presented using short duration of EEG signal. Entropy based features were extracted from EEG signal decomposed using stationary wavelet transform. Selected features were used for classification using different supervised machine learning algorithms. Further, different evolutionary inspired approaches were deployed to optimize the parameters of support vector machines (SVM) and perform feature weighting, simultaneously. SVM optimized using whale optimization algorithm resulted in an accuracy of 97.2559%. Accurate detection using short duration EEG signal shows potential of this technique for timed and reliable detection of stress.

Two-layer LSTM network-based prediction of epileptic seizures using EEG spectral features

Epilepsy is a chronic nervous disorder, which disturbs the normal daily routine of an epileptic patient due to sudden seizure onset. In this era of smart healthcare, automated seizure prediction techniques could assist the patients, their family, and medical personnel to control and manage these seizures. This paper proposes a spectral feature-based two-layer LSTM network model for automatic prediction of epileptic seizures using long-term multichannel EEG signals. This model makes use of spectral power and mean spectrum amplitude features of delta, theta, alpha, beta, and gamma bands of 23-channel EEG spectrum for this task. Initially, the proposed single-layer and two-layer LSTM models have been evaluated for EEG segments having durations in the range of 5–50 s for 24 epileptic subjects, out of which EEG segments of 30 s duration are found to be useful for accurate seizure prediction using two-layer LSTM model. Afterwards, to validate the performance of this classifier, the spectral features of 30 s duration EEG segments are fed to random forest, decision tree, k-nearest neighbour, support vector machine, and naive Bayes classifiers, which are empowered with grid search-based parameter estimation. Finally, the iterative simulation results and comparison with recently published existing techniques firmly reveal that the proposed two-layer LSTM model with EEG spectral features is an effective technique for accurately predicting seizures in real time with an average classification accuracy of 98.14%, average sensitivity of 98.51%, and average specificity of 97.78%, thereby enabling the epileptic patients to have a better quality of life.

Author Response: Clinical Reasoning: A 70-Year-Old Man With Right Arm and Leg Shaking.

We appreciate the comments from Drs. Freund and Tatum and agree that frontal lobe seizures are an important consideration.1 In small studies of patients with frontal lobe epilepsy, the ictal EEG was obscured by an artifact or seemed normal in only 1.5% of cases localized to the dorsolateral frontal cortex. However, up to 50% of cases were localized to the medial frontal cortex.2 Our patient had bilateral symptoms of increased muscle tone and an impaired ability to speak upon presentation, which persisted throughout the duration of continuous EEG.1 The EEG demonstrated generalized slowing without evidence of epileptiform abnormality. The patient gradually improved in the timeline expected after acute stroke, without intervention of antiepileptic treatment.1 For this reason and those outlined in our article, we believe stroke is the most likely cause of the patient's symptomology. The co-occurrence of acute stroke and seizure has previously been reported to be as high as 9%, with most cases representing nonconvulsive status epilepticus (NCSE), as opposed to convulsive seizures.3 Although it is unclear whether the co-occurrence of acute stroke and status epilepticus leads to higher mortality rates, there is evidence that this incidence leads to higher rates of functional disability.4 Therefore, we agree it is important to consider seizure in the differential diagnosis of a patient presenting with acute stroke, despite a negative surface EEG.