Seizure Classification Research Articles

Is preserved consciousness during seizures associated with quality of life among patients with drug-resistant epilepsy?

Drug-resistant epilepsy is associated with reduced quality of life (QoL) due to a myriad of disease-related and psychosocial factors. Although consciousness during seizures is a core feature of seizure classification, its impact on QoL in people with epilepsy (PWE) is not well understood. This study aimed to address this gap by comparing QoL between PWE with focal aware (FA) versus impaired awareness (FIA) seizures. Sixty-nine adults with epilepsy completed the Quality of Life in Epilepsy-31 (QoLIE-31) inventory as part of their pre-surgical neuropsychological evaluation (FA: n = 26, FIA: n = 43). There was no group difference in seizure burden as defined by the proportion of comorbid focal to bilateral tonic-clonic seizures (FA:65.4 %; FIA: 79.1 %). People with FA seizures reported lower overall QoL than people with FIA seizures; sub-scale analyses revealed that seizure worry drives this effect. There was no difference in QoL between people with motor and non-motor FA seizures. Results suggest that FA seizures are burdensome on the QoL of PWE. FA seizures may contribute to seizure worry due to preserved awareness of aversive peri-ictal phenomenon. Findings suggest that clinical efforts should continue to be made to optimize seizure control in people with breakthrough FA seizures. Prospective longitudinal monitoring of QoL in trials of consciousness-targeting neurostimulation therapy is needed to determine if QoL changes as a function of improved peri-ictal consciousness following treatment.

Perceptions and metaphors of patients about epileptic seizures and postictal state in Medellín-Colombia: A qualitative study

IntroductionPWE describe epileptic seizures and the postictal state with the description of experienced symptoms or through metaphorical language. For treating physicians, this metaphoric language may go unnoticed. The purpose of the study is to identify both the real and metaphorical descriptions of epileptic seizures and postictal state referred by PWE from Medellín Colombia. MethodsIt is a qualitative study that uses grounded theory applied in ten semi-structured interviews of PWE from the Metropolitan Area of Medellín, Colombia. Descriptions of epileptic seizures and the postictal state were identified. For their classification into metaphorical and literal characteristics, the texts of “The Living Metaphor” by Paul Riccoeur, “The Illness and its Metaphors – AIDS and its Metaphors” by Susan Sontag, and “Metaphors of Everyday Life” by Lakoff and Johnson were used as references. ResultsTen clinical and fourteen metaphorical descriptions of epileptic seizures were identified. Regarding the postictal state, eight clinical and six metaphorical descriptions were identified. The metaphors were classified into three categories: a. external force b. depreciation and division and c. the absence of continuity (slowness, disconnection). ConclusionMetaphors are frequent in the description of epileptic seizures and can be useful in seizure classification, neuroanatomical localization, and therapeutic approach. Metaphors can be an initial stage in the construction of otherness as a form of identity.

Epileptic seizure classification using fuzzy lattices and Neural Reinforcement Learning

ABSTRACT This work uses Fuzzy Lattices and Neural Reinforcement Learning techniques for seizure classification. EEG database of Bonn University and CHB-MIT has been used for the evaluation of the proposed method. Here, features are represented in the form of fuzzy lattices, and feature vectors are created in the form of Kinetic Energy (K.E.) using Schrödinger equation. Then, the highest K.E.-based seven fuzzy lattices have been used for classification using Neural Reinforcement Learning classifier. Neural Reinforcement Learning classifier is a self-learner method that classifies different seizure sub-classes (healthy eyes open, healthy eye closed, Epileptogenic Zone, hippocampal formation of opposite hemisphere, epileptic seizure). The effectiveness of the proposed method has been tested on two different public datasets. The average classification accuracy achieved is 97.6% and 97.5% for Bonn and CHB-MIT datasets, respectively. Results are compared with existing techniques to show the precedence of proposed approach. Also, computation speed of proposed classifier is more than 1.5 times compared to Fuzzy Q Learning classifier. The objective is to develop a hybrid model integrating fuzzy lattices and neural reinforcement learning (adaptive methods) for accurate classification, aiming to enhance and speeding up seizure detection and diagnosis to improve patient care through advanced computational techniques.

Updated international guidelines for classification of neonatal seizures

Updated international guidelines for classification of neonatal seizures

Hybrid WCA–PSO Optimized Ensemble Extreme Learning Machine and Wavelet Transform for Detection and Classification of Epileptic Seizure from EEG Signals

Hybrid WCA–PSO Optimized Ensemble Extreme Learning Machine and Wavelet Transform for Detection and Classification of Epileptic Seizure from EEG Signals

Impact of EEG sampling frequency on the accuracy of automatic seizure detection and classification with DL algorithms

Impact of EEG sampling frequency on the accuracy of automatic seizure detection and classification with DL algorithms

Application of interpretable machine learning techniques to automatic seizure detection and classification

Application of interpretable machine learning techniques to automatic seizure detection and classification

Architecture of a model for epileptic seizure detection and classification from EEG recordings

Architecture of a model for epileptic seizure detection and classification from EEG recordings

Retracted: Automatic Detection and Classification of Epileptic Seizures in Patients with Liver Cirrhosis and Overlapping Hev Infection Based on Deep Multimodal Fusion Technology

Retracted: Automatic Detection and Classification of Epileptic Seizures in Patients with Liver Cirrhosis and Overlapping Hev Infection Based on Deep Multimodal Fusion Technology

Adherence to antiseizure medications in an underserved population with epilepsy

Background and purposeAntiseizure medications (ASM) effectively prevent seizures in about 70% of adult epilepsy patients, but nonadherence to medication is the primary cause of breakthrough seizures, accounting for 26% to 79% of cases. Factors such as age, education, dosing frequency, forgetfulness, fear of side effects, and socioeconomic status contribute to poor adherence, especially among underserved populations. This study aimed to assess medication adherence during routine follow-up visits and identify the role of education in reducing non adherence in an underserved patient population. MethodsThe study involved a retrospective chart review of adult epilepsy patients seen at the University of Illinois Hospital between December 2016 and April 2020. Data on patient demographics, epilepsy and seizure classification, medication details, emergency visits, and adherence were collected from electronic medical records using the RedCap system. Descriptive statistics and statistical tests were conducted using STATA 17.0 for data analysis, including chi-squared analysis for categorical data and t-tests for continuous data. ResultsThe study enrolled a total of 286 adult epilepsy patients who met the eligibility criteria. Among them, 111 patients (38.81 %) were classified as nonadherent based on ASM levels. Caucasian/white race and income > $50,000 per year, were significantly associated with adherence (p = 0.009 and p = 0.006 respectively). Moreover, patients with weekly seizures were more likely to be adherent (p = 0.042). No significant differences were found regarding medication adherence and sex, education, employment, epilepsy type, age at diagnosis, seizure type or number of current ASM medications. Even though not significant, a trend towards college educated patients being more adherent was observed (70.37 %). Of self-reported adherent patients, 33.33 % were found to be nonadherent based on ASM levels. Nurse phone calls reminding 70 non adherent patients about adherence increased the chances of becoming adherent by 80.39 %. Finally, although not statistically significant, the majority of adherent patients had no history of hospitalizations for breakthrough seizures (73.89 %). ConclusionMore than a third of our patients were found to be non-adherent during routine follow-up visits. Lower socio-economic status and lower education were associated with increased chances of being non adherent. Rates of adherence were improved by nurse’s phone calls discussing the importance of adherence and risks of SUDEP. The findings emphasize the importance of education in improving medication adherence among these populations, suggesting the need for social interventions, community outreach programs, and targeted educational initiatives.

Unsupervised domain adaptation for cross-patient seizure classification

Objective. Epileptic seizure is a chronic neurological disease affecting millions of patients. Electroencephalogram (EEG) is the gold standard in epileptic seizure classification. However, its low signal-to-noise ratio, strong non-stationarity, and large individual difference nature make it difficult to directly extend the seizure classification model from one patient to another. This paper considers multi-source unsupervised domain adaptation for cross-patient EEG-based seizure classification, i.e. there are multiple source patients with labeled EEG data, which are used to label the EEG trials of a new patient. Approach. We propose an source domain selection (SDS)-global domain adaptation (GDA)-target agent subdomain adaptation (TASA) approach, which includes SDS to filter out dissimilar source domains, GDA to align the overall distributions of the selected source domains and the target domain, and TASA to identify the most similar source domain to the target domain so that its labels can be utilized. Main results. Experiments on two public seizure datasets demonstrated that SDS-GDA-TASA outperformed 13 existing approaches in unsupervised cross-patient seizure classification. Significance. Our approach could save clinicians plenty of time in labeling EEG data for epilepsy patients, greatly increasing the efficiency of seizure diagnostics.

Time and frequency domain pre-processing for epileptic seizure classification of epileptic EEG signals

Although epilepsy is one of the most prevalent and ancient neurological disorder, but, still difficult to identify the specific type of seizure, due to artefacts, noise, and other disturbances, because of acquisition of Scalp EEG. It necessitating the use of skilled medical professionals as incorrect diagnosis lead to wrong Anti Seizure Drug (ASDs) and face it’s side effects. On the other hand machine learning plays a crucial role in seizure detection by analyzing and identifying patterns in brain activity data that are indicative of seizures. It can be used to develop predictive models that can detect the onset of seizures in real-time, allowing for early intervention and improved patient outcomes. Most of the research work focuses on seizure detection using various machine learning techniques pre-processed by different mathematical models. But, very less attention is paid towards seizure type detection. In this study, multiple Machine and Deep Learning algorithms were used in conjunction with time-domain and frequency-domain pre-processing to classify epileptic seizures into multiple types. The ictal period of various seizure types were extracted from Temple University Hospital EEG (TUHEEG) and the pre-processed data was tried out with multiple classifiers, including support vector classifiers (SVC), K- Nearest Neighbor (KNN), and Long short term memory (LSTM), among others. By using SVM, KNN, and LSTM, multiclass classification of seven types of epileptic seizures with 19 channels were considered for each EEG data and a 75–25 train–test ratio was accomplished with 90.41%, 94.46%, and 86.2% accuracy respectively. Epileptic seizure’s ictal phase EEG signals are categorized using a variety of machine learning(ML) and deep learning(DL) methods after being pre-processed using time domain and frequency domain approaches. The KNN yields the best results of all.

Automatic classification of hyperkinetic, tonic, and tonic-clonic seizures using unsupervised clustering of video signals.

This study evaluated the accuracy of motion signals extracted from video monitoring data to differentiate epileptic motor seizures in patients with drug-resistant epilepsy. 3D near-infrared video was recorded by the Nelli® seizure monitoring system (Tampere, Finland). 10 patients with 130 seizures were included in the training dataset, and 17 different patients with 98 seizures formed the testing dataset. Only seizures with unequivocal hyperkinetic, tonic, and tonic-clonic semiology were included. Motion features from the catch22 feature collection extracted from video were explored to transform the patients' videos into numerical time series for clustering and visualization. Changes in feature generation provided incremental discrimination power to differentiate between hyperkinetic, tonic, and tonic-clonic seizures. Temporal motion features showed the best results in the unsupervised clustering analysis. Using these features, the system differentiated hyperkinetic, tonic and tonic-clonic seizures with 91, 88, and 45% accuracy after 100 cross-validation runs, respectively. F1-scores were 93, 90, and 37%, respectively. Overall accuracy and f1-score were 74%. The selected features of motion distinguished semiological differences within epileptic seizure types, enabling seizure classification to distinct motor seizure types. Further studies are needed with a larger dataset and additional seizure types. These results indicate the potential of video-based hybrid seizure monitoring systems to facilitate seizure classification improving the algorithmic processing and thus streamlining the clinical workflow for human annotators in hybrid (algorithmic-human) seizure monitoring systems.

Limited clinical validity of univariate resting-state EEG markers for classifying seizure disorders.

Differentiating between epilepsy and psychogenic non-epileptic seizures presents a considerable challenge in clinical practice, resulting in frequent misdiagnosis, unnecessary treatment and long diagnostic delays. Quantitative markers extracted from resting-state EEG may reveal subtle neurophysiological differences that are diagnostically relevant. Two observational, retrospective diagnostic accuracy studies were performed to test the clinical validity of univariate resting-state EEG markers for the differential diagnosis of epilepsy and psychogenic non-epileptic seizures. Clinical EEG data were collected for 179 quasi-consecutive patients (age > 18) with a suspected diagnosis of epilepsy or psychogenic non-epileptic seizures who were medication-naïve at the time of EEG; 148 age- and gender-matched patients subsequently received a diagnosis from specialist clinicians and were included in the analyses. Study 1 is a hypothesis-driven study testing the ability of theta power and peak alpha frequency to classify people with epilepsy and people with psychogenic non-epileptic seizures, with an advanced machine learning pipeline. The next study (Study 2) is data-driven; a high number of quantitative EEG features are extracted and a similar machine learning approach as Study 1 assesses whether previously unexplored univariate EEG measures show promise as diagnostic markers. The results of Study 1 suggest that EEG markers that were previously identified as promising diagnostic indicators (i.e. theta power and peak alpha frequency) have limited clinical validity for the classification of epilepsy and psychogenic non-epileptic seizures (mean accuracy: 48%). The results of Study 2 indicate that identifying univariate markers that show good correlation with a categorical diagnostic label is challenging (mean accuracy: 45-60%). This is due to a considerable overlap in neurophysiological features between the diagnostic classes considered in this study, and to the presence of more dominant EEG dynamics such as alterations due to temporal proximity to epileptiform discharges. Markers that were identified in the context of previous epilepsy research using visually normal resting-state EEG were found to have limited clinical validity for the classification task of distinguishing between people with epilepsy and people with psychogenic non-epileptic seizures. A search for alternative diagnostic markers uncovered the challenges involved and generated recommendations for further research.

Improving Seizure Frequency Documentation and Classification.

Accurate and reliable seizure data are essential for evaluating treatment strategies and tracking the quality of care in epilepsy clinics. This quality improvement project aimed to increase seizure documentation (i.e., documentation of seizure frequency from 80% to 100%, date of last seizure from 35% to 50%, and International League Against Epilepsy (ILAE) seizure classification from 35% to at least 50%) over 6 months. We surveyed 7 epileptologists to determine their perceived seizure frequency, ILAE classification, and date of last seizure documentation habits. Baseline data were collected weekly from September to December 2021. Subsequently, we implemented a newly created flowsheet in our Electronic Health Record (EHR) based on the Epilepsy Learning Healthcare System (ELHS) Case Report Forms to increase seizure documentation in a standardized way. Two epileptologists tested this flowsheet tool in their epilepsy clinics between February 2022 and July 2022. Data were collected weekly and compared with documentation from other epileptologists within the same group. Epileptologists at our center believed they documented seizure frequency for 84%-87% of clinic visits, which aligned with baseline data collection, showing they recorded seizure frequency for 83% of clinic visits. Epileptologists believed they documented ILAE classification for 47%-52% of clinic visits, and baseline data showed this was documented in 33% of clinic visits. They also reported documenting the date of the last seizure for 52%-63% of clinic visits, but this occurred in only 35% of clinic visits. After implementing the new flowsheet, documentation increased to nearly 100% for all fields being completed by the providers who tested the flowsheet. We demonstrated that by implementing an easy-to-use standardized EHR documentation tool, our documentation of critical metrics, as defined by the ELHS, improved dramatically. This shows that simple and practical interventions can substantially improve clinically meaningful documentation.

Detection and classification of adult epilepsy using hybrid deep learning approach

The electroencephalogram (EEG) has emerged over the past few decades as one of the key tools used by clinicians to detect seizures and other neurological abnormalities of the human brain. The proper diagnosis of epilepsy is crucial due to its distinctive nature and the subsequent negative effects of epileptic seizures on patients. The classification of minimally pre-processed, raw multichannel EEG signal recordings is the foundation of this article’s unique method for identifying seizures in pre-adult patients. The new method makes use of the automatic feature learning capabilities of a three-dimensional deep convolution auto-encoder (3D-DCAE) associated with a neural network-based classifier to build an integrated framework that endures training in a supervised manner to attain the highest level of classification precision among brain state signals, both ictal and interictal. A pair of models were created and evaluated for testing and assessing our method, utilizing three distinct EEG data section lengths, and a tenfold cross-validation procedure. Based on five evaluation criteria, the labelled hybrid convolutional auto-encoder (LHCAE) model, which utilizes a classifier based on bidirectional long short-term memory (Bi-LSTM) and an EEG segment length of 4 s, had the best efficiency. This proposed model has 99.08 ± 0.54% accuracy, 99.21 ± 0.50% sensitivity, 99.11 ± 0.57% specificity, 99.09 ± 0.55% precision, and an F1-score of 99.16 ± 0.58%, according to the publicly available Children’s Hospital Boston (CHB) dataset. Based on the obtained outcomes, the proposed seizure classification model outperforms the other state-of-the-art method’s performance in the same dataset.

Automatic epileptic seizure detection using MSA-DCNN and LSTM techniques with EEG signals

To identify epilepsy, Electroencephalography (EEG) is an important and common tool used to study the electrical activity of the human brain. The machine learning-based classifier is utilized to detect the seizure by manually extracting the features from the EEG signals in previous works. Though, these effective benefits have been proved already with automatic feature extraction, they are unable to achieve the classification of multiple classes. Meanwhile, real-time epileptic seizure detection is unable to keep the capacity because the identifiable EGG is too long. Hence, this paper is decided to develop an enhanced deep learning architecture with EEG signal for performing automatic epileptic seizure detection. The EEG signal is collected from the standard datasets. The Fourier-Bessel Series Expansion-Based Empirical Wavelet Transform (FBSE-EWT) method is used to decompose the signal from the gathered data. In feature extraction, the decomposed signals are used and while extracting the signal features, the autoencoder is involved in that process. To reduce the computational overload, the relief-F feature ranking method is used for choosing the important signal features. The Long Short Term Memory (LSTM) and Multi-Scale Atrous-based Deep Convolutional Neural Networks (MSA-DCNN) are used that is named as Hybrid Deep Scheme (HDS) to detect epileptic seizures with the top-ranked features for epileptic seizure classification. The Black Widow Optimization (BWO) and the Spider Monkey Optimization (SMO) are combined to generate Adaptive Spider Monkey Black Widow Optimization (ASMBWO) that is employed to perform the parameter tuning into a classification technique. Using different measures, the experimental analysis is done between the conventional epileptic seizure detection and the proposed model to establish an enhanced performance of the proposed model.

Comprehensive Evaluation of Inflammatory Biomarkers and Osmolarity to Distinguish Simple and Complex Febrile Seizures in Children.

With limited sample sizes and varying study outcomes regarding complete blood count (CBC)-associated biomarkers and their febrile seizure (FS) classification, along with limited research on osmolarity, this study aims to evaluate CBC-associated biomarkers, including osmolarity, for a comprehensive view of their diagnostic value. This single-center retrospective study used data from 364 children (aged 5-60 months) diagnosed with FS. The patients were categorized into simple FS (n = 221) and complex FS (n = 143) groups. CBC and biochemical tests, including sodium, potassium, chloride, glucose, blood urea nitrogen, and C-reactive protein levels, were evaluated. The neutrophil-to-lymphocyte ratio (NLR), mean platelet volume-to-lymphocyte ratio, and osmolarity were calculated and compared between FS types and the number of seizures. Receiver operating characteristic (ROC) curve analysis was conducted to assess the predictive utility of these markers. Inflammatory markers, including NLR, were ineffective in predicting FS types. Complex FS cases exhibited a significantly lower osmolarity than simple FS cases. The area under the ROC curve for osmolarity to distinguish complex FS was 0.754, while other markers did not reach the desired threshold of 0.700. Including osmolarity in the classification of FS has clinical applicability. Physicians may consider osmolarity as an additional tool to aid in clinical decision-making.

Development of tuned hybrid fuzzy and BiLSTM-based epileptic seizure classification model with stacked 1D-CNN-fisher discriminant feature selection

ABSTRACT Electroencephalogram (EEG) is a signal which consists of different sinusoidal components with a dense frequency spectrum. The existing methods are time-consumingand includes inconsistencies in judgment among seizure classification. Therefore, it is very difficult to accurately detect epileptic seizures from the recorded EEG. Therefore, a new epileptic seizure detection model is developed with hybrid deep-structured technology. The EEG signal data obtained from the standard online resources which are given into the pre-processing phase with the help of band pass filtering and smoothing techniques. Then, the 5-level Discrete Wavelet Transform (5-level DWT) is used for signal decomposition to get the decomposed signals. 1-D stacked Convolutional Neural Network (1-D stacked CNN) is utilized for the extraction of features. After, the feature selection process is executed by utilizing the Fisher Discriminant Analysis (FDA). The selected features are subjected to the classification phase by Tuned Hybrid Fuzzy Bi-directional Long Short-Term Memory (THFBi-LSTM). Here, the parameter optimization takes place with hybridized optimization algorithm of Probability-based Dingo Coyote Optimization (P-DCO). In the overall simulation estimation, the offered approach achieves a 97% accuracy rate and also a 92% F1-score rate. Thus, the experimental results are reveled that it is better than the other baseline approaches.

A novel end-to-end approach for epileptic seizure classification from scalp EEG data using deep learning technique

A novel end-to-end approach for epileptic seizure classification from scalp EEG data using deep learning technique