Identification Of Seizures Research Articles

A Clinical-Electrographic Profile of Neonatal Seizures and Their Etiologies in a Single Level III Neonatal Intensive Care Unit

Background: Seizures are the most frequent neurological emergency in neonatal period and can be associated with significant mortality and subsequent neuro-developmental disability if not recognized and managed early. Repaid identification of neonatal seizures and evaluation is critically required to identify and treat the underlying etiology. Clinicians face a major challenge in diagnosing and treating neonatal seizure because of inconspicuous clinical presentation, variable electro-clinical correlation. Assessing the combination of clinical presentation, etiological factors, different diagnostic tools, and treatments, can broaden the knowledge and understanding towards neonatal seizure providing better management and outcome. Objective: To study the characteristics of clinical and electrographic profile of neonatal seizure and the relations to their etiologies in neonatal intensive care unit. Methods: This is a descriptive cross sectional retrospective study of electronic health records with ICD- 10 diagnosis of neonatal seizure from birth to 28 days, who were admitted to neonatal intensive care unit at Sheikh Shakhbout Medical City between January 2020 to December 2021. Clinical data obtained including basic demographics: gender, gestational age, mode of delivery, birth weight, and Apgar score. Onset and type seizure, type of antiepileptic drugs administered, EEG findings, brain imaging, results of relevant laboratory tests and etiology of seizure were collected. Results: Total 31 neonates included in the study. Majority were male (71%), term (87%), and birth weight >2,5 kg (90%). Seizure within 24 hours was 58% and semiology was focal clonic in 32% of patient. No events in EEG in 81% and 6% had electrographic seizure (n=2). 94 % were treated with anti-convulsant, 86% of them before EEG. The majority (86%) received phenobarbitone as 1st line treatment and 83% received monotherapy. Leading causes of seizure were HIE (48%) followed by Vascular causes (16%). Seizure within 24 hours caused mainly by HIE (61%) and 60% of neonates with vascular and all infectious and genetic causes had seizure after 24 hours. In vascular causes, (60%) presented with focal clonic seizure. 60% of Multifocal epileptiform activity seen in HIE whereas focal presented more in vascular patient (36%). In HIE cases, 53% had normal brain MRI and 47% were abnormal. All cases with vascular causes had diagnostic abnormal MRI. The majority of HIE cases (87%) and all vascular cases received monotherapy. Conclusion: In this descriptive study of neonatal seizure, certain demographic data, clinical and electrographic characteristics had established links to their etiologies. Clinical events captured during EEG with no electrographic seizure are classified as non-epileptic clinical phenomenon. Diagnostic utility of EEG is required in diagnosis of involuntary movements and avoid unnecessary anti-seizure medications. Understanding the clinical-electrographic profile of neonatal seizure helps in the early recognition of specific etiologies, allowing an early diagnosis by organized diagnostic approach and management.

Feasibility Assessment of Rapid Response EEG in the Identification of Nonconvulsive Seizures During Military Medical Air Transport.

Traumatic brain injury often requires neurologic care and specialized equipment, not often found downrange. Nonconvulsive seizures (NCSs) and nonconvulsive status epilepticus (NCSE) occur in up to 30% of patients with moderate or severe traumatic brain injury and is associated with a 39% morbidity and an 18% mortality. It remains difficult to identify at bedside because of the heterogeneous clinical manifestations. The primary diagnostic tool is an electroencephalogram (EEG) which is large, requires an external power source, and requires a specialized technician and neurologist to collect and interpret the data. Rapid response EEG (rr-EEG) is an FDA-approved device that is pocket sized and battery powered and uses a disposable 10-electrode headset. Prior studies have demonstrated the noninferiority of rr-EEG in the identification of NCSE and NCS as compared to conventional EEG in hospitals. An unanswered question is whether rr-EEG could be used in the identification of NCSE and NCS by medics. In conjunction with the Critical Care Air Transport (CCAT) team, a simulation was created and implemented on a CCAT training mission. The simulation team included a neurology resident, who oversaw the simulation, a pulmonary critical care fellow, an intensive care unit nurse, and a respiratory therapy. A survey was provided before and after the simulation. The team was expected to review the rr-EEG to make clinical decisions during ground transport, takeoff, and landing. The neurology resident monitored and recorded the team's ability to distinguish between NCS and a normal EEG. In between, the neurology resident monitored the quality of the EEG for potential interference and loss of quality. The CCAT team was able to efficiently set up the rr-EEG on a patient manikin, correctly identify visual EEG wave forms of a patient in NCS, and utilize the proprietary audio program of a simulated patient in NCS. The team reported that the device was easily set up in the environment, and the data were interpretable despite vibration, aircraft auditory and electrical noise, and the ergonomics of the aircraft medical section. This pilot study has validated a potentially revolutionary technology in medical transport. The rr-EEG technology is measurably user-friendly and will improve patient outcomes. This device and simulation can reduce time to an EEG by hours to days allowing for immediate treatment and intervention, which can significantly reduce morbidity and mortality.

A Comparison of Automatically Extracted Quantitative EEG Features for Seizure Risk Stratification in Neonatal Encephalopathy.

Seizures occur in up to 40% of neonates with neonatal encephalopathy. Earlier identification of seizures leads to more successful seizure treatment, but is often delayed because of limited availability of continuous EEG monitoring. Clinical variables poorly stratify seizure risk, and EEG use to stratify seizure risk has previously been limited by need for manual review and artifact exclusion. The goal of this study is to compare the utility of automatically extracted quantitative EEG (qEEG) features for seizure risk stratification. We conducted a retrospective analysis of neonates with moderate-to-severe neonatal encephalopathy who underwent therapeutic hypothermia at a single center. The first 24 hours of EEG underwent automated artifact removal and qEEG analysis, comparing qEEG features for seizure risk stratification. The study included 150 neonates and compared the 36 (23%) with seizures with those without. Absolute spectral power best stratified seizure risk with area under the curve ranging from 63% to 71%, followed by range EEG lower and upper margin, median and SD of the range EEG lower margin. No features were significantly more predictive in the hour before seizure onset. Clinical examination was not associated with seizure risk. Automatically extracted qEEG features were more predictive than clinical examination in stratifying neonatal seizure risk during therapeutic hypothermia. qEEG represents a potential practical bedside tool to individualize intensity and duration of EEG monitoring and decrease time to seizure recognition. Future work is needed to refine and combine qEEG features to improve risk stratification.

A comprehensive study of machine learning-based methods to predict epileptic seizures

People with epilepsy have many difficulties as a result of this complicated brain condition, which is typified by frequent convulsions. Symptoms of these seizures include bizarre behaviors, odd sensations, and in extreme cases, loss of awareness. These seizures appear as episodes of aberrant electrical impulses in the central nervous system. Successful epilepsy management depends on early seizure detection and identification, which allows for appropriate intervention to minimize risks and improve patient outcomes. Two major reasons have contributed to the extraordinary advancements in the area of epilepsy investigations in the last few years: the explosive development of machine learning techniques and the decreasing cost of non-invasive electroencephalography (EEG) apparatus. The availability of low-cost EEG equipment has made it easier to gather information on brain activity, which has opened up new avenues for monitoring and analyzing episodes of epileptic seizures away from conventional medical settings. The abundance of data and the advancement of machine learning methods have created new opportunities for the early identification and forecasting of seizures. Machine learning algorithms can predict seizures based on EEG data, providing patients with epilepsy with more control and informed decision-making. This paper offers a current review of current methods for treating epileptic seizures. The feature extraction techniques and classification algorithms receive particular focus. The most popular EEG datasets and their accessibility are listed. The approaches that are examined range from those that use more established machine learning techniques, such as naive Bayes models, Support Vector Machines (SVM), and Linear Discriminant Analysis (LDA), to those that take advantage of more recent deep learning techniques, like (Long-Short Term Memory, or LSTM), and deep Convolutional-Neural-Networks (CNN).

Single-channel seizure detection with clinical confirmation of seizure locations using CHB-MIT dataset.

Long-term electroencephalography (EEG) monitoring is advised to patients with refractory epilepsy who have a failure of anti-seizure medication and therapy. However, its real-life application is limited mainly due to the use of multiple EEG channels. We proposed a patient-specific deep learning-based single-channel seizure detection approach using the long-term scalp EEG recordings of the Children's Hospital Boston-Massachusetts Institute of Technology (CHB-MIT) dataset, in conjunction with neurologists' confirmation of spatial seizure characteristics of individual patients. We constructed 18-, 4-, and single-channel seizure detectors for 13 patients. Neurologists selected a specific channel among four channels, two close to the behind-the-ear and two at the forehead for each patient, after reviewing the patient's distinctive seizure locations with seizure re-annotation. Our multi- and single-channel detectors achieved an average sensitivity of 97.05-100%, false alarm rate of 0.22-0.40/h, and latency of 2.1-3.4 s for identification of seizures in continuous EEG recordings. The results demonstrated that seizure detection performance of our single-channel approach was comparable to that of our multi-channel ones. We suggest that our single-channel approach in conjunction with clinical designation of the most prominent seizure locations has a high potential for wearable seizure detection on long-term EEG recordings for patients with refractory epilepsy.

Speeded up robust features trailed GCN for seizure identification during pregnancy

Speeded up robust features trailed GCN for seizure identification during pregnancy

Biological plausible algorithm for seizure detection: Toward AI-enabled electroceuticals at the edge

Nearly 1% of people worldwide suffer from epilepsy. Electroencephalogram (EEG)-based diagnostics and monitoring tools, such as scalp EEG, subscalp EEG, stereo EEG, or sub/epi-dural EEG recordings [also known as electrocorticography (ECoG)], are widely used in different settings as the gold standard techniques to perform seizure identification, localization, and more primarily in epilepsy or suspected epilepsy in patients. Techniques such as subscalp EEG and ECoG offer long-term brain interaction, potentially replacing traditional electroceuticals with smart closed-loop therapies. However, these systems require continuous on-device training due to real-time demands and high power consumption. Inspired by the brain architecture, biologically plausible algorithms, such as some neuromorphic computing, show promise in addressing these challenges. In our research, we utilized liquid time-constant spiking neural networks with forward propagation through time to detect seizures in scalp-EEG. We trained and validated our model on the Temple University Hospital dataset and tested its generalization on out-of-sample data from the Royal Prince Alfred Hospital (RPAH) and EPILEPSIAE datasets. Our model achieved high area under the receiver operating characteristic curve (AUROC) scores of 0.83 in both datasets. We assessed the robustness by decreasing the memory size by 90% and obtained an overall AUROC of 0.82 in the RPAH dataset and 0.83 in the EPILEPSIAE dataset. Our model showed outstanding results of 3.1 μJ power consumption per inference and a 20% firing rate during training. This allows for incorporating bio-inspired efficient algorithms for on-device training, tackling challenges such as memory, power consumption, and efficiency.

Quadrature Response Spectra Deep Neural Based Behavioral Pattern Analytics for Epileptic Seizure Identification

Abstract The brain’s Electroencephalogram (EEG) signals contain essential information about the brain and are widely used to support the analysis of epilepsy. By analyzing brain behavioral patterns, an accurate classification of different epileptic states can be made. The behavioral pattern analysis using EEG signals has become increasingly important in recent years. EEG signals are boisterous and non-linear, and it is a demanding mission to design accurate methods for classifying different epileptic states. In this work, a method called Quadrature Response Spectra-based Gaussian Kullback Deep Neural (QRS-GKDN) Behavioral Pattern Analytics for epileptic seizures is introduced. QRS-GKDN is divided into three processes. First, the EEG signals are preprocessed using the Quadrature Mirror Filter (QMF) and the Power Frequency Spectral (PFS) and Response Spectra (RS)-based Feature Extraction is applied for Behavioral Pattern Analytics. The QMF function is applied to the preprocessed EEG input signals. Then, relevant features for behavioral pattern analysis are extracted from the processed EEG signals using the PFS and RS function. Finally, Gaussian Kullback–Leibler Deep Neural Classification (GKDN) is implemented for epileptic seizure identification. Furthermore, the proposed method is analyzed and compared with dissimilar samples. The results of the Proposed method have superior prediction in a computationally efficient manner for identifying epileptic seizure based on the analyzed behavioral patterns with less error and validation time.

Optimizing EEG monitoring in critically ill children at risk for electroencephalographic seizures

ObjectiveStrategies are needed to optimally deploy continuous EEG monitoring (CEEG) for electroencephalographic seizure (ES) identification and management due to resource limitations. We aimed to construct an efficient multi-stage prediction model guiding CEEG utilization to identify ES in critically ill children using clinical and EEG covariates. MethodsThe largest prospective single-center cohort of 1399 consecutive children undergoing CEEG was analyzed. A four-stage model was developed and trained to predict whether a subject required additional CEEG at the conclusion of each stage given their risk of ES. Logistic regression, elastic net, random forest, and CatBoost served as candidate methods for each stage and were evaluated using cross validation. An optimal multi-stage model consisting of the top-performing stage-specific models was constructed. ResultsWhen evaluated on a test set, the optimal multi-stage model achieved a cumulative specificity of 0.197 and cumulative F1 score of 0.326 while maintaining a high minimum cumulative sensitivity of 0.938. Overall, 11 % of test subjects with ES were removed from the model due to a predicted low risk of ES (falsely negative subjects). CEEG utilization would be reduced by 32 % and 47 % compared to performing 24 and 48 h of CEEG in all test subjects, respectively. We developed a web application called EEGLE (EEG Length Estimator) that enables straightforward implementation of the model. ConclusionsApplication of the optimal multi-stage ES prediction model could either reduce CEEG utilization for patients at lower risk of ES or promote CEEG resource reallocation to patients at higher risk for ES.

Automatic classification of seizure and seizure-free EEG signals based on phase space reconstruction features.

Epilepsy is a type of brain disorder triggered by an abrupt electrical imbalance of neuronal networks. An electroencephalogram (EEG) is a diagnostic tool to capture the underlying brain mechanisms and detect seizure onset in epileptic patients. To detect seizures, neurologists need to manually monitor EEG recordings for long periods, which is challenging and susceptible to errors depending on expertise and experience. Therefore, automatic identification of seizure and seizure-free EEG signals becomes essential. This study introduces a method based on the features extracted from the phase space reconstruction for classifying seizure and seizure-free EEG signals. The computed features are derived from the elliptical area and interquartile range of the Euclidean distance by varying percentage values of data points ranging from 50 to 100%. We consider two public datasets and evaluate these features in each EEG epoch that includes the healthy, interictal, preictal, and ictal stages of epileptic subjects, utilizing the K-nearest neighbor classifier for classification. Results show that the features have higher values during the seizure than the seizure-free EEG signals and healthy subjects. Furthermore, the proposed features can effectively discriminate seizure EEG signals from the seizure-free and normal subjects with 100% accuracy, sensitivity, and specificity in both datasets. Likewise, the classification between the preictal stage and seizure EEG signals attains 98% accuracy. Overall, the reconstructed phase space features significantly enhance the accuracy of detecting epileptic EEG signals compared with existing methods. This advancement holds great potential in assisting neurologists in swiftly and accurately diagnosing epileptic seizures from EEG signals.

Deep Learning for Generalized EEG Seizure Detection after Hypoxia-Ischemia-Preclinical Validation.

Brain maturity and many clinical treatments such as therapeutic hypothermia (TH) can significantly influence the morphology of neonatal EEG seizures after hypoxia-ischemia (HI), and so there is a need for generalized automatic seizure identification. This study validates efficacy of advanced deep-learning pattern classifiers based on a convolutional neural network (CNN) for seizure detection after HI in fetal sheep and determines the effects of maturation and brain cooling on their accuracy. The cohorts included HI-normothermia term (n = 7), HI-hypothermia term (n = 14), sham-normothermia term (n = 5), and HI-normothermia preterm (n = 14) groups, with a total of >17,300 h of recordings. Algorithms were trained and tested using leave-one-out cross-validation and k-fold cross-validation approaches. The accuracy of the term-trained seizure detectors was consistently excellent for HI-normothermia preterm data (accuracy = 99.5%, area under curve (AUC) = 99.2%). Conversely, when the HI-normothermia preterm data were used in training, the performance on HI-normothermia term and HI-hypothermia term data fell (accuracy = 98.6%, AUC = 96.5% and accuracy = 96.9%, AUC = 89.6%, respectively). Findings suggest that HI-normothermia preterm seizures do not contain all the spectral features seen at term. Nevertheless, an average 5-fold cross-validated accuracy of 99.7% (AUC = 99.4%) was achieved from all seizure detectors. This significant advancement highlights the reliability of the proposed deep-learning algorithms in identifying clinically translatable post-HI stereotypic seizures in 256Hz recordings, regardless of maturity and with minimal impact from hypothermia.

Automatic Seizure Detection Using Multi-Input Deep Feature Learning Networks for EEG Signals

Epilepsy, a neurological disease associated with seizures, affects the normal behavior of human beings. The unpredictability of epileptic seizures has caused great obstacles to the treatment of the disease. The automatic seizure detection method based on electroencephalogram (EEG) can assist experts in predicting seizures to improve treatment efficiency. Epileptic seizure detection cannot be achieved accurately using the single-view characteristics of the signals. Moreover, manual feature extraction is a time-consuming task. To design a high-performance seizure identification method, automatic learning of multi-view features becomes an indispensable part for seizure detection. Therefore, the paper proposes a multi-input deep feature learning networks (MDFLN) model, which comprehensively considers the features from the time domain and the time–frequency (TF) domain for EEG signals. The MDFLN model automatically extracts the feature information of the signals through deep learning networks. Then, the bidirectional long short-term memory (BLSTM) network is used to distinguish seizure and nonseizure events. Furthermore, the effectiveness of the proposed network structure is verified in two public datasets. The experimental results demonstrate that the classification accuracy of the proposed method based on multi-view features is at least 2.2% higher than the single-view features. The MDFLN achieves better performance on CHB-MIT and Bonn datasets with accuracy of 98.09% and 98.4%, respectively. The fine-tuned model with the validation set also improves the classification performance. Compare with the state-of-the-art seizure detection methods, the multi-input deep learning network has superior competence with high sensitivity on the CHB-MIT dataset. The proposed automatic seizure detection method can reduce time consumption and effectively assist experts in the clinical diagnosis and treatment.

Enhanced Epileptic Seizure Identification using Sparse ELM-ABO Fusion with Feature Reduction and Multi-class Classification

The interpretation of the electroencephalogram (EEG) signal is one method that can be utilized to diagnose epilepsy, which is one of the most prevalent brain illnesses. The length of an EEG signal is typically quite long, making it difficult to interpret manually. Extreme Learning Machine (ELM) is used to detection of Epilepsy and Seizure. But in ELM Storage space and training time is high. In order to reduce training time and storage space African Buffalo Optimization (ABO) algorithm is used. ABO is combined with Sparse ELM to improve the speed, accuracy of detection and reduce the storage space. First, Wavelet transform is used to extract relevant features. Due to their high dimensionality, these features are then reduced by using linear discriminant analysis (LDA). The proposed Hybrid Sparse ELM technique is successfully implemented for diagnosing epileptic seizure disease. For classification, the Sparse ELM-ABO classifier is applied to the UCI Epileptic Seizure Recognition Data Set training dataset, and the experimental findings are compared to those of the SVM, Sparse ELM, and ELM classifiers applied to the same database. The proposed model was tested in two scenarios: binary classification and multi-label classification. Seizure identification is the only factor in binary classification. Seizure and epilepsy identification are part of multi-label classification. It is observed that the proposed method obtained high accuracy in classification with less execution time along with performance evaluation of parameters such as prediction accuracy, specificity, precision, recall and F-score. Binary classification scores 96.08%, while multi-label classification achieves 90.89%.

Deep-learning-based intelligent neonatal seizure identification using spatial and spectral GNN optimized with the Aquila algorithm

Deep-learning-based intelligent neonatal seizure identification using spatial and spectral GNN optimized with the Aquila algorithm

APPLICATION OF AMPLITUDE-INTEGRATED ELECTROENCEPHALOGRAPHY IN PATIENTS OF NEONATAL INTENSIVE CARE UNITS

Intriduction. Amplitude-integrated electroencephalography is a technique for monitoring continuous cerebral function, when electroencephalographic signal is filtered, scaled and compressed in time.
 Objective of the study is to elucidate peculiarities of interpreting findings of the amplitude-integrated electroencephalography in patients of neonatal intensive care units, and represent a clinical case of establishing diagnosis by using the amplitude-integrated electroencephalography for a critically sick neonate.
 Materials and methods. A comprehensive literature review was conducted across international and national databases, including Elsevier, PubMed, Medline, Web of Science, Scopus, Cochrane Central Register of Controlled Trials, and Google Scholar, covering the period from 2019 to 2023. The search focused on the keywords "amplitude-integrated electroencephalography" and/or "aEEG" and "neonates" and/or "term infants" and/or "preterm infants." The clinical case presented took place at the neonatal intensive care unit of the Maternity Home "Central Municipal Clinical Hospital", Chernivtsi, Ukraine. Permission for publication was obtained from both parents of the child.
 Results. The main indications for conducting the amplitude-integrated electroencephalography in neonates include the assessment of the cerebral function and the degree of cerebral damage with hypoxic-ischemic encephalopathy or asphyxia at birth (often combined with therapeutic hypothermia); assessment of sleep-wake cycle; identification of seizures; assessment of cerebral function maturity in preterm neonates.
 The underlying cerebral activity is estimated according to the amplitude-integrated electroencephalography findings by means of a simple recognition of visual images corresponding to the five main patterns: Continuous Normal Voltage, Discontinuous Normal Voltage, Burst Suppression, Low Voltage, and Flat Trace. A typical neonatal single seizure fit on the amplitude-integrated electroencephalography looks like a “hump” or lower edge elevation interrupting the background recording. Repeated fits (epileptic status) look like a “saw” of repeated “humps”, one of each represents one attack. The article presents a clinical case of the diagnostic search in the neonate with congenital pneumonia and development of multiple organ failure syndrome including seizure syndrome. Clinical tonic-clonic seizures of the infant were associated with electroencephalographic criteria of status epilepticus both on the amplitude-integrated electroencephalography (repeated symmetrical elevations of the lower edge in the left and right) and on the standard electroencephalography (different variations of seizure graphic elements in the right and left). Considering the results of the clinical and instrumental examination, an adequate anticonvulsant therapy was administered.
 Conclusions. Continuous recording of the video-amplitude-integrated electroencephalography and standard electroencephalography in infants from the risk group is a good strategy of the neurological status effective monitoring. It enables to assess the underlying cerebral electric activity and it maturity, diagnose seizures and manage anticonvulsant therapy correctly. An adequate training of the staff who are at the patient’s bedside 24/7 is an important part of the interdisciplinary collaboration which is essential for a safe and effective management of patients in the neonatal intensive care units, prevention of early complications and disability in the future.

Closed‐Loop Optogenetic Modulation of Neural Activities in Freely Moving Mice with Multimodal Fibers

AbstractThe precise manipulation of neural activity is of great significance to reveal the function of complex neural circuits in brain, especially the mechanism of neurological disorders such as epilepsy, Parkinson's, and Alzheimer's disease. In the past decades, optogenetics has become a powerful tool to investigate the function of neural circuits due to its unique advantages of cell specificity and high spatiotemporal resolution. However, to date, most optogenetic manipulation has been conducted in an open‐loop fashion. The closed‐loop neural modulation is still an important task. Here, a closed‐loop optogenetic modulation system is developed for ultra‐fast, ‐accurate, and ‐stable manipulation of neural activities in behaving mice. Specifically, this system is mediated by a functional fiber probe with excellent low optical loss (0.052 dB cm−1 at 589 nm) and electrical impedance (5.40 MΩ µm−2 at 1 kHz). In vivo electrophysiology and behavioral experiments demonstrated that the system can be successfully applied for the identification and intervention of seizures in epilepsy mice with high efficiency. It is envision that the closed‐loop manipulation system has promising applications in brain science, neuroscience, and neuromodulation therapies.

Quantitative EEG in the neonatal intensive care unit: Current application and future promise

AbstractImportanceQuantitative electroencephalography (qEEG) has been used in the neonatal intensive care unit (NICU) for several decades. Recent innovations have led to renewed interest in expanding its role in the NICU with the goal of improving both acute care of neonates in the NICU and longer‐term outcomes.ObservationsEEG in the NICU is primarily used to identify neonatal seizures. Sophisticated analysis of EEG can detect other acute neurological emergencies and provide additional information about short‐ and long‐term neurodevelopmental and epileptic prognosis. Using EEG for these additional findings may be limited by access to EEG resources and a constrained supply of neonatal neurophysiologists who can consistently evaluate unique neonatal EEG patterns.RelevanceQuantitative EEG analysis is a rapidly developing technology with the potential to augment and support the interpretation of neonatal EEGs. This review focuses on the status of qEEG use in the NICU for identification and prediction of seizures and use in neuroprognostication. It also examines areas of promise for bedside qEEG applications.

Detection and Severity Identification of Neonatal Seizure Using Deep Convolutional Neural Networks from Multichannel EEG Signal.

One of the most frequent neurological conditions in newborns is neonatal seizures, which may indicate severe neurological dysfunction. These seizures may have very subtle or very modest clinical indications because patterns like oscillatory (spike) trains begin with relatively low amplitude and gradually increase over time. This becomes very challenging and erroneous if clinical observation is the primary basis for identifying newborn seizures. In this study, a diagnosis system using deep convolutional neural networks is proposed to determine and classify the severity level of neonatal seizures using multichannel neonatal EEG data. Datasets from publicly accessible online sources were used to compile clinical multichannel EEG datasets. Various preprocessing steps were taken, including the conversion of 2D time series data to equivalent waveform pictures. The proposed models have undergone training, and evaluations of their performance were conducted. The proposed CNN was used to perform binary classification with an accuracy of 92.6%, F1-score of 92.7%, specificity of 92.8%, and precision of 92.6%. To detect newborn seizures, this model is utilized. Using the proposed CNN model, multiclassification was performed with accuracy rates of 88.6%, specificity rates of 92.18%, F1-score rates of 85.61%, and precision rates of 88.9%. The results demonstrated that the suggested strategy can assist medical professionals in making accurate diagnoses close to healthcare institutions. The developed system was capable of detecting neonatal seizures and has the potential to be used as a decision-making tool in resource-limited areas with a scarcity of expert neurologists.

A Modified Gated Recurrent Unit Approach for Epileptic Electroencephalography Classification

Epilepsy is one of the most severe non-communicable brain disorders associated with sudden attacks. Electroencephalography (EEG), a non-invasive technique, records brain activities, and these recordings are routinely used for the clinical evaluation of epilepsy. EEG signal analysis for seizure identification relies on expert manual examination, which is labour-intensive, time-consuming, and prone to human error. To overcome these limitations, researchers have proposed machine learning and deep learning approaches. Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) have shown significant results in automating seizure prediction, but due to complex gated mechanisms and the storage of excessive redundant information, these approaches face slow convergence and a low learning rate. The proposed modified GRU approach includes an improved update gate unit that adjusts the update gate based on the output of the reset gate. By decreasing the amount of superfluous data in the reset gate, convergence is speeded, which improves both learning efficiency and the accuracy of epilepsy seizure prediction. The performance of the proposed approach is verified on a publicly available epileptic EEG dataset collected from the University of California, Irvine machine learning repository (UCI) in terms of performance metrics such as accuracy, precision, recall, and F1 score when it comes to diagnosing epileptic seizures. The proposed modified GRU has obtained 98.84% accuracy, 96.9% precision, 97.1 recall, and 97% F1 score. The performance results are significant because they could enhance the diagnosis and treatment of neurological disorders, leading to better patient outcomes.

Nonlinear and chaos features over EMD/VMD decomposition methods for ictal EEG signals detection

The detection and identification of epileptic seizures attracted considerable relevance for the neurophysiologists. In order to accomplish the detection of epileptic seizures or equivalently ictal EEG states, this paper proposes the use of nonlinear and chaos features not computed over the raw EEG signals as it was commonly experienced, but instead over intrinsic mode functions (IMFs) extracted subsequently to the application of newly time-frequency signal decomposition methods on the basis of empirical mode decomposition (EMD) and variational mode decomposition (VMD) methods. The first step within the proposed methodology is to excerpt the various components of the IMFs by EMD and VMD decomposition methods on time EEG segments. The Hjorth parameters, the Hurst exponent, the Recurrence Quantification Analysis (RQA), the detrended fluctuation analysis (DFA), the Largest Lyapunov Exponent (LLE), The Higuchi and Katz fractal dimensions (HFD and KFD), seven nonlinear and chaos features computed over the IMFs were investigated and their classification performances evaluated using the k-nearest neighbor (KNN) and the multilayer perceptron neural network (MLPNN) classifiers. Furthermore, the combination of the best nonlinear features has also been examined in terms of sensitivity, specificity and overall classification accuracy. The publicly available Bonn EEG dataset has been has been employed to validate the efficiency of the proposed method for detecting ictal EEG signals from normal or interictal EEG segments. Among the several experiments involved in the current study, the ultimate results establish that the overall classification accuracy can achieve 100%, 99.45%, 99.8%, 99.8%, 98.6% and 99.1% for six different epileptic seizure detection case problems studied, confirming the ability of the proposed methodology in helping the clinic practitioners in the epilepsy detection care units to classify seizure events with a great confidence.