Identification Of Seizures Research Articles

A machine learning approach to seizure detection in a rat model of post-traumatic epilepsy

Epilepsy is a common neurologic condition frequently investigated using rodent models, with seizures identified by electroencephalography (EEG). Given technological advances, large datasets of EEG are widespread and amenable to machine learning approaches for identification of seizures. While such approaches have been explored for human EEGs, machine learning approaches to identifying seizures in rodent EEG are limited. We utilized a predesigned deep convolutional neural network (DCNN), GoogLeNet, to classify images for seizure identification. Training images were generated through multiplexing spectral content (scalograms), kurtosis, and entropy for two-second EEG segments. Over 2200 h of EEG data were scored for the presence of seizures, with 95.6% of seizures identified by the DCNN and a false positive rate of 34.2% (1.52/h), as compared to visual scoring. Multiplexed images were superior to scalograms alone (scalogram-kurtosis-entropy 0.956 ± 0.010, scalogram 0.890 ± 0.028, t(7) = 3.54, p < 0.01) and a DCNN trained specifically for the individual animal was superior to using DCNNs across animals (intra-animal 0.960 ± 0.0094, inter-animal 0.811 ± 0.015, t(30) = 5.54, p < 0.01). For this dataset the DCNN approach is superior to a previously described algorithm utilizing longer local line lengths, calculated from wavelet-decomposition of EEG, to identify seizures. We demonstrate the novel use of a predesigned DCNN constructed to classify images, utilizing multiplexed images of EEG spectral content, kurtosis, and entropy, to rapidly and objectively identifies seizures in a large dataset of rat EEG with high sensitivity.

Study of etiological factors and immediate outcomes of neonatal seizure among preterm and term neonate in a tertiary health centre of Northern India

Background: Neonatal seizures result due to altered neurological functions like motor, behavioural and autonomic function. We conducted this study to assess the incidence, etiological factors, and immediate outcomes of neonatal seizures in term and preterm neonates. Methods: This prospective observational study included all neonates delivered in a tertiary health centre of New Delhi from Nov 2015 to Oct 2016 and admitted in Neonatal Intensive Care Unit with clinically identified seizures up to 28 days of postnatal age. Results: Out of 11,109 live births during the study period, 302 developed neonatal seizures with overall incidence of 2.71%. The early preterm (12.05%), very low birth weight babies (56.30%), and neonates in first 24 hrs of life (68.9%) had the highest incidence of neonatal seizures. The commonest seizure type was subtle seizures (52.3%). In early preterm commonest etiology was infection (31.3%) while in late preterm and term neonates most common etiology was Hypoxic ischaemic encephalopathy 59% and 72% respectively. Overall, HIE was the most common etiology (57%). Out of 302 cases, 81 (26.8%) cases have died. HIE was found to be the most common cause for mortality. Mortality was highest in early preterms (49.3%) and very low birth weight neonates (52.3%). Also, mortality was maximum among neonates having subtle seizures (29.1%) and seizures occurring within 24 hrs of life (30.8%). Conclusions: Persistently high incidence of neonatal seizures requires further strengthening of antenatal, natal, and post-natal health services. Early identification of neonatal seizures and timely intervention are very important for better outcomes.

Amplitude Integrated Electroencephalography: Simulated Assessment of Neonatal Seizure Detection in PICU Patients.

Amplitude integrated electroencephalography (aEEG) is a mainstay of care in neonatal ICUs; however, knowledge gaps exist in relation to its accuracy for identifying seizures in older children. We aimed to review the diagnostic accuracy of existing neonatal seizure detection criteria for seizure detection in older children in hospital. Retrospective study. PICU/Neurophysiology Department in Dublin. One hundred twenty patients (2 mo to 16 yr old) were chosen from a database of formal 10-20 system, 21-lead electroencephalography recordings (2012-2020), comprising 30 studies with seizures, 90 without. None. Electroencephalography studies containing electrographic seizures (ESzs) were annotated to describe number, duration, distribution, and spread. Two-channel aEEG (using leads C3-P3, C4-P4) recordings were generated and independently reviewed by a professional specialist in clinical neurophysiology blinded to outcome and without reference to the raw electroencephalography trace. Logistic regression was used to identify factors associated with correct seizure identification on aEEG. Median patient age was 6.1 years. Abnormal recordings featured 123 seizures. Status epilepticus (SE) was evident by electroencephalography in 10 cases. Using neonatal criteria, aEEG had a sensitivity of 70% and negative predictive value of 90% for identifying any ESz. Accurate detection of individual seizures was diminished when seizures were very short or occurred during waking. Sensitivity for individual seizures was 81% when seizures less than 1 minute were excluded. aEEG correctly identified SE in 70% of the 10 cases, although ESz were confirmed to be present in 80% of this subpopulation. aEEG criteria for neonatal seizure identification can be applied with caution to older children and should be supplemented by formal electroencephalography. Seizure identification is better for longer seizures and those arising from sleep. SE is not always recognized by aEEG among older children.

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.

Expert and deep learning model identification of iEEG seizures and seizure onset times.

Hundreds of 90-s iEEG records are typically captured from each NeuroPace RNS System patient between clinic visits. While these records provide invaluable information about the patient's electrographic seizure and interictal activity patterns, manually classifying them into electrographic seizure/non-seizure activity, and manually identifying the seizure onset channels and times is an extremely time-consuming process. A convolutional neural network based Electrographic Seizure Classifier (ESC) model was developed in an earlier study. In this study, the classification model is tested against iEEG annotations provided by three expert reviewers board certified in epilepsy. The three experts individually annotated 3,874 iEEG channels from 36, 29, and 35 patients with leads in the mesiotemporal (MTL), neocortical (NEO), and MTL + NEO regions, respectively. The ESC model's seizure/non-seizure classification scores agreed with the three reviewers at 88.7%, 89.6%, and 84.3% which was similar to how reviewers agreed with each other (92.9%-86.4%). On iEEG channels with all 3 experts in agreement (83.2%), the ESC model had an agreement score of 93.2%. Additionally, the ESC model's certainty scores reflected combined reviewer certainty scores. When 0, 1, 2 and 3 (out of 3) reviewers annotated iEEG channels as electrographic seizures, the ESC model's seizure certainty scores were in the range: [0.12-0.19], [0.32-0.42], [0.61-0.70], and [0.92-0.95] respectively. The ESC model was used as a starting-point model for training a second Seizure Onset Detection (SOD) model. For this task, seizure onset times were manually annotated on a relatively small number of iEEG channels (4,859 from 50 patients). Experiments showed that fine-tuning the ESC models with augmented data (30,768 iEEG channels) resulted in a better validation performance (on 20% of the manually annotated data) compared to training with only the original data (3.1s vs 4.4s median absolute error). Similarly, using the ESC model weights as the starting point for fine-tuning instead of other model weight initialization methods provided significant advantage in SOD model validation performance (3.1s vs 4.7s and 3.5s median absolute error). Finally, on iEEG channels where three expert annotations of seizure onset times were within 1.5 s, the SOD model's seizure onset time prediction was within 1.7 s of expert annotation.

Improving Deep Learning for Seizure Detection using GAN with Cramer Distance and a Temporal-Spatial-Frequency Loss Function

The signals of EEG are analyzed in the identification of seizure and diagnosis of epilepsy. The visual examination process of EEG data by skilled physician is huge time-utilization and the judgemental process is complicated, which may vary or show inconsistency among the physician. Hence, an automatic process in diagnosis and detection was initiated by the Deep Learning (DL) approaches. Time Aware Convolutional Neural Network with Recurrent Neural Network (TA-CNN-RNN) was one among them. Deep neural networks trained on large labels performed well on many supervised learning tasks. Creating such massive databases takes time, resources, and effort. In many circumstances, such resources are unavailable, restricting DL adoption and use. In this manuscript, Generative Adversarial Networks with the Cramer distance (CGAN) is proposed to generate an accurate data for each lable. A spatiotemporal error factor is introduced to differentiate actual and genetrated data. The discriminator is learned to differentiate the created data from the actual ones, while the generator is learned to create counterfeit data, which are not estimated as false by the discriminator. The classical GANs have a complex learning because of the nonlinear and non-stationary features of EEG data which is solved by Carmer Distance in the proposed method. Finally, the sample generated by CGAN is given as input for the Time Aware Convolutional Neural Network with Recurrent Neural Network (TA-CNN-RNN) classifier to investigate experimental seizure Prediction outcome of the proposed CGAN. From the investigational outcomes, the proposed CGAN- TA-CNN-RNN model attained classification accuracy of 94.6%, 94.8% and 95.2% on CHB-MIT-EEG, Bonn-iEEG and VIRGO-EEG than other existing EEG classification schemes and also provides great potentials in real-time applications.

Study on characteristic of epileptic multi-electroencephalograph base on Hilbert-Huang transform and brain network dynamics.

Lots of studies have been carried out on characteristic of epileptic Electroencephalograph (EEG). However, traditional EEG characteristic research methods lack exploration of spatial information. To study the characteristics of epileptic EEG signals from the perspective of the whole brain，this paper proposed combination methods of multi-channel characteristics from time-frequency and spatial domains. This paper was from two aspects: Firstly, signals were converted into 2D Hilbert Spectrum (HS) images which reflected the time-frequency characteristics by Hilbert-Huang Transform (HHT). These images were identified by Convolutional Neural Network (CNN) model whose sensitivity was 99.8%, accuracy was 98.7%, specificity was 97.4%, F1-score was 98.7%, and AUC-ROC was 99.9%. Secondly, the multi-channel signals were converted into brain networks which reflected the spatial characteristics by Symbolic Transfer Entropy (STE) among different channels EEG. And the results show that there are different network properties between ictal and interictal phase and the signals during the ictal enter the synchronization state more quickly, which was verified by Kuramoto model. To summarize, our results show that there was different characteristics among channels for the ictal and interictal phase, which can provide effective physical non-invasive indicators for the identification and prediction of epileptic seizures.

Narrative Review of Non-Convulsive Status Epilepticus in Adults in Intensive Care

ABSTRACT Background Seizures are common in the Neurocritical Intensive Care Unit. Early identification and treatment of clinical and sub-clinical seizures remain important in managing the neurologically critically ill patient. Aim The aim of this narrative review is to provide an overview of the different types of sub-clinical seizures, diagnosis and detection, correlative physiology, and the importance of prompt treatment. Methods A group of physicians, advanced practice providers, and pharmacists performed a literature search based on their area of expertise and provided the most relevant evidence for the narrative review. Findings There are many types of subclinical seizures and pharmaceutical interventions. Seizures can be complex and early treatment is crucial to good outcomes. Conclusions This review is a narrative overview of sub-clinical seizures seen in the Neurocritical care unit. It is written for all practicing providers to describe the physiology, identification, and treatment of sub-clinical seizures to facilitate improved patient outcomes.

Newer indications for neuromonitoring in critically ill neonates.

Continuous neuromonitoring in the neonatal intensive care unit allows for bedside assessment of brain oxygenation and perfusion as well as cerebral function and seizure identification. Near-infrared spectroscopy (NIRS) reflects the balance between oxygen delivery and consumption, and use of multisite monitoring of regional oxygenation provides organ-specific assessment of perfusion. With understanding of the underlying principles of NIRS as well as the physiologic factors which impact oxygenation and perfusion of the brain, kidneys and bowel, changes in neonatal physiology can be more easily recognized by bedside providers, allowing for appropriate, targeted interventions. Amplitude-integrated electroencephalography (aEEG) allows continuous bedside evaluation of cerebral background activity patterns indicative of the level of cerebral function as well as identification of seizure activity. Normal background patterns are reassuring while abnormal background patterns indicate abnormal brain function. Combining brain monitoring information together with continuous vital sign monitoring (blood pressure, pulse oximetry, heart rate and temperature) at the bedside may be described as multi-modality monitoring and facilitates understanding of physiology. We describe 10 cases in critically ill neonates that demonstrate how comprehensive multimodal monitoring provided greater recognition of the hemodynamic status and its impact on cerebral oxygenation and cerebral function thereby informing treatment decisions. We anticipate that there are numerous other uses of NIRS as well as NIRS in conjunction with aEEG which are yet to be reported.

Seizures in Dementia are Associated with Worse Clinical Outcomes, Higher Mortality and Shorter Lifespans (P3-1.001)

<h3>Objective:</h3> To study impact of seizures on clinical and mortality outcomes in dementia patients. <h3>Background:</h3> Dementia and seizures are both public health imperatives. Seizures occur in 10–64% of those with dementia and accelerate cognitive decline. However, the impact of seizures on clinical and mortality outcomes in dementia patients has not been studied. <h3>Design/Methods:</h3> We analyzed longitudinal data from 39 Alzheimer’s disease Centers from 9/2005–12/2021, maintained by National Alzheimer’s Coordinating Center. We included patients with cognitive impairment at initial visit. We compared cognitive, functional and mortality outcomes among those with and without seizures. <h3>Results:</h3> At the initial visit, among 26,425 cognitively impaired patients, 374(1.4% point prevalence) had seizures. Seizure patients were significantly younger (62.91 vs 68.4 years, p&lt;0.001) at onset of cognitive decline. In multivariate regression analysis, dominant Alzheimer’s disease(AD) mutation(OR: 5.55, CI: 2.39–12.89, p &lt; 0.001), stroke (OR: 3.17, CI: 2.35–4.27, p &lt; 0.001), transient ischemic attack[TIA] (OR: 1.72, CI: 1.21–2.46, p = 0.003), traumatic brain injury[TBI] (OR: 1.92, CI: 1.48–2.50, p &lt; 0.001), Parkinson’s disease [PD] (OR: 1.79, CI: 1.07–2.98, p = 0.025), depression (OR: 1.61, CI: 1.30–1.99, p &lt; 0.001) and lower education (OR: 0.97, CI: 0.95–0.99, p = 0.043) were associated with seizures. Patients with seizures performed worse on mini-mental-status examination(18.50 vs 22.88, <i>p</i> &lt; 0.001) and Clinical-Dementia-Rating Sum-of-boxes(7.95 vs 4.28, p &lt; 0.001); and had more physical dependence(OR: 2.52, CI: 1.99–3.19, p &lt; 0.001) compared to those without seizures after adjusting for age and dementia duration using generalized linear model. Analysis of longitudinal mortality data showed that a higher proportion of seizure patients had died (OR: 1.56, CI: 1.27–1.91, p &lt; 0.0001),and they were younger at death(72.99 vs 79.72years, p &lt; 0.001). Multivariate survival analysis using Cox regression was conducted to study age at death and seizure status. We adjusted the model for sex, disease duration, stroke, TIA, TBI, depression, education and dominant AD mutation. Despite adjustment, patients with seizures were at a higher risk of dying at a younger age(hazard ratio: 1.76, CI: 1.49–2.08, p&lt;0.001). <h3>Conclusions:</h3> Our study shows that dementia patients with seizures have worse cognition and higher mortality rates at a younger age compared to dementia patients without seizures. Dementia patients with early onset of dementia, dominant AD mutation, stroke, TIA, TBI, PD, depression, and/or lower education are more likely to have seizures. Dementia patient with these risk factors may be routinely considered for EEG for early identification and treatment of seizures to improve outcomes. <b>Disclosure:</b> Dr. Zawar has nothing to disclose. Dr. Quigg has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Cerebral Therapeutics. Dr. Quigg has received personal compensation in the range of $500-$4,999 for serving on a Scientific Advisory or Data Safety Monitoring board for Cerebral Therapeutics. Dr. Quigg has received personal compensation in the range of $500-$4,999 for serving as an Expert Witness for Finnigen and Harrison. Dr. Quigg has received research support from NIH. Dr. Quigg has received publishing royalties from a publication relating to health care. The institution of Dr. Manning has received research support from Department of Defense. The institution of Dr. Kapur has received personal compensation in the range of $500-$4,999 for serving on a Scientific Advisory or Data Safety Monitoring board for Marinus. Dr. Kapur has received personal compensation in the range of $5,000-$9,999 for serving as an officer or member of the Board of Directors for Robert Wood Johnson Foundation . Dr. Kapur has received personal compensation in the range of $500-$4,999 for serving as an Editor, Associate Editor, or Editorial Advisory Board Member for Elsevier. The institution of Dr. Kapur has received research support from NIH. Dr. Kapur has received intellectual property interests from a discovery or technology relating to health care. Dr. Kapur has a non-compensated relationship as a Chair, Board North America with International League against Epilepsy that is relevant to AAN interests or activities. Dr. Kapur has a non-compensated relationship as a Board of Directors with American Epilepsy Society that is relevant to AAN interests or activities.

Modernizing Identification of Non-Convulsive Seizures and Status Epilepticus: Neurologists’ Experience at a Level 1 Trauma Center (P9-1.007)

<h3>Objective:</h3> We hypothesized that utilization of the Ceribell Rapid Response EEG (RR-EEG) can reduce time to diagnosis in a level one trauma center in the Department of Defense. A secondary aim was to evaluate utilization practices and cost savings. <h3>Background:</h3> Non-convulsive seizures (NCS) and non-convulsive status epilepticus (NCSE) have been found in up to 27% of patients that are critically ill and often go unrecognized or have delays in recognition. Electroencephalography (EEG) is the gold standard diagnostic tool but is a limited resource, requires trained technicians and specialized neurologists, thereby potentially leading to delays in diagnosis and treatment. <h3>Design/Methods:</h3> We obtained 50 rr-EEG headsets from the manufacturer Ceribell Inc as part of quality improvement effort. From September 2021 through April 2022, Neurology residents triaged consults concerning for NCS or NCSE and based on clinical suspicion performed rr-EEG or ordered conventional EEG. Data was collected to include time of consult, time of initiation, time of interpretation, provider’s clinical impressions, and final diagnosis of seizure or not. <h3>Results:</h3> Average time to initiation of data collection for rr-EEG was 48.94 minutes compared to 128.05 minutes for conventional EEG (<i>p</i>-value &lt;0.001). Average time to interpretation of rr-EEG was 58.59 minutes compared to 246.29 minutes time of interpretation after downloading the conventional EEG. We compared time of interpretation of the rr-EEG (58.59 minutes) to the initiation of the conventional EEG (128.05 minutes) due to delays associated with work-flow and formal reading of the EEGs. This yielded a <i>p</i>-value of &lt;0.001. <h3>Conclusions:</h3> rr-EEG reduced time to initiation and interpretation by over 50% compared to conventional EEG as utilized by neurologists at a busy Level 1 trauma center. rr-EEG also reduced cost per EEG while increasing utilization and availability of EEG technology. <b>Disclosure:</b> Dr. Luster has nothing to disclose. Dr. Tchopev has nothing to disclose. The institution of Dr. Hoffman has received research support from United States Air Force. Dr. Jacobus has nothing to disclose. The institution of Dr. Willis has received research support from Air Force. Dr. Willis has received intellectual property interests from a discovery or technology relating to health care.

Detect, predict, and prevent acute seizures and status epilepticus

Status epilepticus is one of the most frequent pediatric neurological emergencies. While etiology is often influencing the outcome, more easily modifiable risk factors of outcome include detection of prolonged convulsive seizures and status epilepticus and appropriately dosed and timely applied medication treatment. Unpredictability and delayed or incomplete treatment may at times lead to longer seizures, thereby affecting outcomes.Barriers in the care of acute seizures and status epilepticus include the identification of patients at greatest risk of convulsive status epilepticus, potential stigma, distrust, and uncertainties in acute seizure care, including caregivers, physicians, and patients. Furthermore, unpredictability, detection capability, and identification of acute seizures and status epilepticus, limitations in access to obtaining and maintaining appropriate treatment, and rescue treatment options pose challenges. Additionally, timing and dosing of treatment and related acute management algorithms, potential variations in care due to healthcare and physician culture and preference, and factors related to access, equity, diversity, and inclusion of care.We outline strategies for the identification of patients at risk of acute seizures and status epilepticus, improved status epilepticus detection and prediction, and acute closed-loop treatment and status epilepticus prevention. This paper was presented at the 8th London-Innsbruck Colloquium on Status Epilepticus and Acute Seizures held in September 2022.

Computer-assisted analysis of routine electroencephalogram to identify hidden biomarkers of epilepsy: protocol for a systematic review

IntroductionThe diagnosis of epilepsy frequently relies on the visual interpretation of the electroencephalogram (EEG) by a neurologist. The hallmark of epilepsy on EEG is the interictal epileptiform discharge (IED). This...

Feature Selection with Deep Belief Network for Epileptic Seizure Detection on EEG Signals

The term Epilepsy refers to a most commonly occurring brain disorder after a migraine. Early identification of incoming seizures significantly impacts the lives of people with Epilepsy. Automated detection of epileptic seizures (ES) has dramatically improved the life quality of the patients. Recent Electroencephalogram (EEG) related seizure detection mechanisms encountered several difficulties in real-time. The EEGs are the non-stationary signal, and seizure patterns would change with patients and recording sessions. Further, EEG data were disposed to wide noise varieties that adversely moved the recognition accuracy of ESs. Artificial intelligence (AI) methods in the domain of ES analysis use traditional deep learning (DL), and machine learning (ML) approaches. This article introduces an Oppositional Aquila Optimizer-based Feature Selection with Deep Belief Network for Epileptic Seizure Detection (OAOFS-DBNECD) technique using EEG signals. The primary aim of the presented OAOFS-DBNECD system is to categorize and classify the presence of ESs. The suggested OAOFS-DBNECD technique transforms the EEG signals into .csv format at the initial stage. Next, the OAOFS technique selects an optimal subset of features using the pre-processed data. For seizure classification, the presented OAOFS-DBNECD technique applies Artificial Ecosystem Optimizer (AEO) with a deep belief network (DBN) model. An extensive range of simulations was performed on the benchmark dataset to ensure the enhanced performance of the presented OAOFS-DBNECD algorithm. The comparison study shows the significant outcomes of the OAOFS-DBNECD approach over other methodologies. In addition, the result of the suggested approach has been evaluated using the CHB-MIT database, and the findings demonstrate accuracy of 97.81%. These findings confirmed the best seizure categorization accuracy on the EEG data considered.

Generalized Epileptic Seizure Prediction using Machine Learning Method

In recent years, the electroencephalography (EEG) signal identification of epileptic seizures has developed into a routine procedure to determine epilepsy. Since physically identifying epileptic seizures by expert neurologists becomes a labor-intensive, time-consuming procedure that also produces several errors. Thus, efficient, and computerized detection of epileptic seizures is required. The disordered brain function that causes epileptic seizures can have an impact on a patient's condition. Epileptic seizures can be prevented by medicine with great success if they are predicted before they start. Electroencephalogram (EEG) signals are utilized to predict epileptic seizures by using machine learning algorithms and complex computational methodologies. Furthermore, two significant challenges that affect both expectancy time and genuine positive forecast rate are feature extraction from EEG signals and noise removal from EEG signals. As a result, we suggest a model that offers trustworthy preprocessing and feature extraction techniques. To automatically identify epileptic seizures, a variety of ensemble learning-based classifiers were utilized to extract frequency-based features from the EEG signal. Our algorithm offers a higher true positive rate and diagnoses epileptic episodes with enough foresight before they begin. On the scalp EEG CHB-MIT dataset on 24 subjects, this suggested framework detects the beginning of the preictal state, the state that occurs before a few minutes of the onset of the detention, resulting in an elevated true positive rate of (91%) than conventional methods and an optimum estimation time of 33 minutes and an average time of prediction is 23 minutes and 36 seconds. Depending on the experimental findings’ The maximum accuracy, sensitivity, and specificity rates in this research were 91 %, 98%, and 84%.

Clinical seizure semiology is subtle and identification of seizures by parents is unreliable in infants with tuberous sclerosis complex.

The objectives of this study were to assess the accuracy of parental seizure detection in infants with antenatally diagnosed tuberous sclerosis complex (TSC), and to document the total seizure burden (clinical and subclinical) in those patients who met criteria for prolonged electroencephalography (EEG) recording. Consecutive infants at a single institution with antenatally diagnosed TSC who met criteria for prolonged video-EEG (vEEG) were recruited to this study. The vEEG data were reviewed and when a seizure was identified on EEG, the video and audio recording was assessed for evidence of clinical seizure and, if present, whether there was evidence of parent seizure identification. Nine infants were enrolled, for whom 674 focal seizures were identified in eight of nine patients across 24 prolonged vEEG recordings, with vEEG total duration of 634 h 49 min (average seizure frequency of 1 focal seizure/h). Only 220 of 674 (32.6%) were clinical seizures, 395 of 674 (58.6%) were subclinical seizures, and 59 of 674 seizures could not be classified. Only 63 of 220 clinical seizures (28.6%) were identified by parents, with 157 of 220 (71.4%) not identified. Thirty clusters of epileptic spasms were detected in one patient. At least one clinical epileptic spasm occurred in 2 of 30 clusters (6.7%), 24 of 30 clusters of epileptic spasms (80%) were electrographic only, and classification was uncertain for 4 of 30 clusters (13.3%). No clinical epileptic spasms were detected by parents. Clinical seizure frequency was significantly underestimated by parents for all patients. This study demonstrates that in infants with TSC who met criteria for prolonged vEEG, (1) parents significantly under recognize total clinical seizure count, (2) parents fail to identify epileptic spasms, and (3) seizure frequency is high. This highlights that epilepsy treatment decisions should not be based solely on parental clinical seizure identification. Prolonged vEEG monitoring may have an important role in the routine epilepsy care of infants with TSC, as demonstrating undetected high clinical seizure frequency may allow improved epilepsy management decisions.

RNN and BiLSTM Fusion for Accurate Automatic Epileptic Seizure Diagnosis Using EEG Signals.

Epilepsy is a common neurological condition. The effects of epilepsy are not restricted to seizures alone. They comprise a wide spectrum of problems that might impair and reduce quality of life. Even with medication, 30% of epilepsy patients still have recurring seizures. An epileptic seizure is caused by significant neuronal electrical activity, which affects brain activity. EEG shows these changes as high-amplitude spiky and sluggish waves. Recognizing seizures on an electroencephalogram (EEG) manually by a professional neurologist is a time-consuming and labor-intensive process, hence an efficient automated approach is necessary for the identification of epileptic seizure. One technique to increase the speed and accuracy with which a diagnosis of epileptic seizures could be made is by utilizing computer-aided diagnosis systems that are built on deep neural networks, or DNN. This study introduces a fusion of recurrent neural networks (RNNs) and bi-directional long short-term memories (BiLSTMs) for automatic epileptic seizure identification via EEG signal processing in order to tackle the aforementioned informational challenges. An electroencephalogram's (EEG) raw data were first normalized after undergoing pre-processing. A RNN model was fed the normalized EEG sequence data and trained to accurately extract features from the data. Afterwards, the features were passed to the BiLSTM layers for processing so that further temporal information could be retrieved. In addition, the proposed RNN-BiLSTM model was tested in an experimental setting using the freely accessible UCI epileptic seizure dataset. Experimental findings of the suggested model have achieved avg values of 98.90%, 98.50%, 98. 20%, and 98.60%, respectively, for accuracy, sensitivity, precision, and specificity. To further verify the new model's efficacy, it is compared to other models, such as the RNN-LSTM and the RNN-GRU learning models, and is shown to have improved the same metrics by 1.8%, 1.69%, 1.95%, and 2.2% on using 5-fold. Additionally, the proposed method was compared to state-of-the-art approaches and proved to be a more accurate categorization of such techniques.

Identification and management of seizures in children

Estimates from epidemiological studies indicate the high global prevalence of seizures in children. They can be associated with different complications that might even be life-threatening. Different risk factors have been reported to increase the risk and severity of seizures, like metabolic disorders, infections, and reduced access to needed care. Therefore, providing appropriate management is essential to enhance the prognosis of these cases. In the present article, we conducted a literature review to shed more light on identifying, diagnosing, and managing seizures in children. The identification process depends on different factors, including obtaining an adequate history from the patient or their caregivers, performing a thorough general and neurological examination, and conducting appropriate investigations whenever needed. It should be noted that in severe cases, these approaches should be made promptly not to delay the management approaches, which can be life-saving. Reassuring family attendants is also recommended. Besides, increasing awareness among these families about the diagnosis, identification, prognosis, reporting, and responding to seizures might reduce the risk of recurrence and enhance the prognosis of seizures. Choosing a treatment strategy is usually based on different factors, including the child's age, epilepsy type, family preferences, the presence of comorbidities, and ability to administer medications. For recurrent seizures, home-based medications, like rectal diazepam or buccal midazolam, might also be used to lower the risk of recurrence and reduce the intensity of seizures.

Epileptic Seizure Detection Using Geometric Features Extracted from SODP Shape of EEG Signals and AsyLnCPSO-GA.

Epilepsy is a neurological disorder that is characterized by transient and unexpected electrical disturbance of the brain. Seizure detection by electroencephalogram (EEG) is associated with the primary interest of the evaluation and auxiliary diagnosis of epileptic patients. The aim of this study is to establish a hybrid model with improved particle swarm optimization (PSO) and a genetic algorithm (GA) to determine the optimal combination of features for epileptic seizure detection. First, the second-order difference plot (SODP) method was applied, and ten geometric features of epileptic EEG signals were derived in each frequency band (δ, θ, α and β), forming a high-dimensional feature vector. Secondly, an optimization algorithm, AsyLnCPSO-GA, combining a modified PSO with asynchronous learning factor (AsyLnCPSO) and the genetic algorithm (GA) was proposed for feature selection. Finally, the feature combinations were fed to a naïve Bayesian classifier for epileptic seizure and seizure-free identification. The method proposed in this paper achieved 95.35% classification accuracy with a tenfold cross-validation strategy when the interfrequency bands were crossed, serving as an effective method for epilepsy detection, which could help clinicians to expeditiously diagnose epilepsy based on SODP analysis and an optimization algorithm for feature selection.

Koolen-de Vries syndrome associated with continuous spike-wave in sleep

Koolen-de Vries syndrome (KdVS) is a genetic condition caused by 17q21.31 microdeletions or pathogenic variants in KANSL1. Affected patients most commonly exhibit some or all of the following: neonatal hypotonia, developmental impairment, facial dysmorphic features, and congenital malformations. Epilepsy occurs in approximately half, often with phenotypes on the epilepsyaphasia spectrum. We describe six children with KdVS found to have continuous spike-wave in sleep (CSWS) on EEG, four of whom were diagnosed with epileptic encephalopathy with CSWS and two with Landau-Kleffner syndrome. When compared with other children with CSWS on EEG, patients with KdVS may present at slightly later ages and with a longer interval between seizure diagnosis and identification of CSWS. There is no clear best treatment for children with CSWS, but two patients in our cohort were trialed on a variation of the ketogenic diet, and both reported clinical improvement. In one of the patients, the response was dramatic, and CSWS recurred when weaning of the ketogenic diet was attempted. Based on our findings, an EEG capturing a prolonged period of sleep should be arranged in any child with KdVS presenting with developmental regression or plateau, particularly if they have a preceding history of seizures.