Automatic detection of epilepsy from EEGs using a temporal convolutional network with a self-attention layer.

BACKGROUND: Over 60% of epilepsy patients globally are children, whose early diagnosis and treatment are critical for their development and can substantially reduce the disease's burden on both families and society. Numerous algorithms for automated epilepsy detection from EEGs have been proposed. Yet, the occurrence of epileptic seizures during an EEG exam cannot always be guaranteed in clinical practice. Models that exclusively use seizure EEGs for detection risk artificially enhanced performance metrics. Therefore, there is a pressing need for a universally applicable model that can perform automatic epilepsy detection in a variety of complex real-world scenarios. METHOD: To address this problem, we have devised a novel technique employing a temporal convolutional neural network with self-attention (TCN-SA). Our model comprises two primary components: a TCN for extracting time-variant features from EEG signals, followed by a self-attention (SA) layer that assigns importance to these features. By focusing on key features, our model achieves heightened classification accuracy for epilepsy detection. RESULTS: The efficacy of our model was validated on a pediatric epilepsy dataset we collected and on the Bonn dataset, attaining accuracies of 95.50% on our dataset, and 97.37% (A v. E), and 93.50% (B vs E), respectively. When compared with other deep learning architectures (temporal convolutional neural network, self-attention network, and standardized convolutional neural network) using the same datasets, our TCN-SA model demonstrated superior performance in the automated detection of epilepsy. CONCLUSION: The proven effectiveness of the TCN-SA approach substantiates its potential as a valuable tool for the automated detection of epilepsy, offering significant benefits in diverse and complex real-world clinical settings.

Performance investigation of epilepsy detection from noisy EEG signals using base-2-meta stacking classifier.

Epilepsy is a chronic neurological disease, characterized by spontaneous, unprovoked, recurrent seizures that may lead to long-term disability and premature death. Despite significant efforts made to improve epilepsy detection clinically and pre-clinically, the pervasive presence of noise in EEG signals continues to pose substantial challenges to their effective application. In addition, discriminant features for epilepsy detection have not been investigated yet. The objective of this study is to develop a hybrid model for epilepsy detection from noisy and fragmented EEG signals. We hypothesized that a hybrid model could surpass existing single models in epilepsy detection. Our approach involves manual noise rejection and a novel statistical channel selection technique to detect epilepsy even from noisy EEG signals. Our proposed Base-2-Meta stacking classifier achieved notable accuracy (0.98 ± 0.05), precision (0.98 ± 0.07), recall (0.98 ± 0.05), and F1 score (0.98 ± 0.04) even with noisy 5-s segmented EEG signals. Application of our approach to the specific problem like detection of epilepsy from noisy and fragmented EEG data reveals a performance that is not only superior to others, but also is translationally relevant, highlighting its potential application in a clinic setting, where EEG signals are often noisy or scanty. Our proposed metric DF-A (Discriminant feature-accuracy), for the first time, identified the most discriminant feature with models that give A accuracy or above (A = 95 used in this study). This groundbreaking approach allows for detecting discriminant features and can be used as potential electrographic biomarkers in epilepsy detection research. Moreover, our study introduces innovative insights into the understanding of these features, epilepsy detection, and cross-validation, markedly improving epilepsy detection in ways previously unavailable.

PYRIDOXINE-dependent epilepsy (PDE): An observational study of neonatal cases on the role of pyridoxine in patients treated with standard anti-seizure medications.

BACKGROUND: The main objective of this study was to evaluate the neurological consequences of delayed pyridoxine administration in patients diagnosed with Pyridoxin Dependent Epilepsies (PDE). MATERIALS AND METHODS: We reviewed 29 articles, comprising 52 genetically diagnosed PDE cases, ensuring data homogeneity. Three additional cases were included from the General Pediatric Operative Unit of San Marco Hospital. Data collection considered factors like age at the first seizure's onset, EEG reports, genetic analyses, and more. Based on the response to first-line antiseizure medications, patients were categorized into four distinct groups. Follow-up evaluations employed various scales to ascertain neurological, cognitive, and psychomotor developments. RESULTS: Our study includes 55 patients (28 males and 27 females), among whom 15 were excluded for the lack of follow-up data. 21 patients were categorized as "Responder with Relapse", 11 as "Resistant", 6 as "Pyridoxine First Approach", and 2 as "Responders". The neurological outcome revealed 37,5 % with no neurological effects, 37,5 % showed complications in two developmental areas, 15 % in one, and 10 % in all areas. The statistical analysis highlighted a positive correlation between the time elapsed from the administration of pyridoxine after the first seizure and worse neurological outcomes. On the other hand, a significant association was found between an extended latency period (that is, the time that elapsed between the onset of the first seizure and its recurrence) and worse neurological outcomes in patients who received an unfavorable score on the neurological evaluation noted in a subsequent follow-up. CONCLUSIONS: The study highlights the importance of early recognition and intervention in PDE. Existing medical protocols frequently overlook the timely diagnosis of PDE. Immediate administration of pyridoxine, guided by a swift diagnosis in the presence of typical symptoms, might improve long-term neurological outcomes, and further studies should evaluate the outcome of PDE neonates promptly treated with Pyridoxine.

Genetic heterogeneity in epilepsy and comorbidities: insights from Pakistani families.

BACKGROUND: Epilepsy, a challenging neurological condition, is often present with comorbidities that significantly impact diagnosis and management. In the Pakistani population, where financial limitations and geographical challenges hinder access to advanced diagnostic methods, understanding the genetic underpinnings of epilepsy and its associated conditions becomes crucial. METHODS: This study investigated four distinct Pakistani families, each presenting with epilepsy and a spectrum of comorbidities, using a combination of whole exome sequencing (WES) and Sanger sequencing. The epileptic patients were prescribed multiple antiseizure medications (ASMs), yet their seizures persist, indicating the challenging nature of ASM-resistant epilepsy. RESULTS: Identified genetic variants contributed to a diverse range of clinical phenotypes. In the family 1, which presented with epilepsy, developmental delay (DD), sleep disturbance, and aggressive behavior, a homozygous splice site variant, c.1339-6 C > T, in the COL18A1 gene was detected. The family 2 exhibited epilepsy, intellectual disability (ID), DD, and anxiety phenotypes, a homozygous missense variant, c.344T > A (p. Val115Glu), in the UFSP2 gene was identified. In family 3, which displayed epilepsy, ataxia, ID, DD, and speech impediment, a novel homozygous frameshift variant, c.1926_1941del (p. Tyr643MetfsX2), in the ZFYVE26 gene was found. Lastly, family 4 was presented with epilepsy, ID, DD, deafness, drooling, speech impediment, hypotonia, and a weak cry. A homozygous missense variant, c.1208 C > A (p. Ala403Glu), in the ATP13A2 gene was identified. CONCLUSION: This study highlights the genetic heterogeneity in ASM-resistant epilepsy and comorbidities among Pakistani families, emphasizing the importance of genotype-phenotype correlation and the necessity for expanded genetic testing in complex clinical cases.

The evaluation of the training, "the approach to epilepsy and epileptic seizure," which was given to teachers in Türkiye.

INTRODUCTION: Epilepsy is the most common neurological disorder among humans after headaches. According to the World Health Organization, approximately 50-65 million individuals were diagnosed with epilepsy throughout the world, and around two million new cases of epilepsy are added to this figure every year. METHODS: Designed as descriptive and cross-sectional research, this study was performed on 132 elementary school teachers. Training on epilepsy and epileptic seizure was given to teachers. The pretest and posttest research data were collected with the face-to-face interview method. In this process, the epilepsy knowledge scale was used as well as a survey form that had questions designed to find out about teachers' personal characteristics. The Statistical Package for Social Science 25.0 was utilized in the statistical analysis of research data. In the research, the statistical significance was identified if the p-value was below.05 (p < .05). RESULTS: Of all teachers participating in the study, 59.1% were female, 90.2% were married, and 47.7% witnessed an epilepsy seizure before. The mean of teachers' pretest epilepsy knowledge scores was 8.43 ± 4.31 points before the training while the mean of their posttest epilepsy knowledge scores was 12.65 ± 2.48 points after the training. The difference between the means of pretest and posttest scores was statistically significant (p = .000). After the training, there was a statistically significant increase in means of scores obtained by teachers from each item of the epilepsy knowledge scale (p < .05). CONCLUSIONS: As there was a statistically significant improvement in levels of teachers' knowledge about both epilepsy and epileptic seizure after the training, it is recommended that the training about the approach to epilepsy and epileptic seizure be given to all teachers, and additionally, including these topics in the course curricula of universities is recommended.

Differentiating Epileptic and Psychogenic Non-Epileptic Seizures Using Machine Learning Analysis of EEG Plot Images.

The treatment of epilepsy, the second most common chronic neurological disorder, is often complicated by the failure of patients to respond to medication. Treatment failure with anti-seizure medications is often due to the presence of non-epileptic seizures. Distinguishing non-epileptic from epileptic seizures requires an expensive and time-consuming analysis of electroencephalograms (EEGs) recorded in an epilepsy monitoring unit. Machine learning algorithms have been used to detect seizures from EEG, typically using EEG waveform analysis. We employed an alternative approach, using a convolutional neural network (CNN) with transfer learning using MobileNetV2 to emulate the real-world visual analysis of EEG images by epileptologists. A total of 5359 EEG waveform plot images from 107 adult subjects across two epilepsy monitoring units in separate medical facilities were divided into epileptic and non-epileptic groups for training and cross-validation of the CNN. The model achieved an accuracy of 86.9% (Area Under the Curve, AUC 0.92) at the site where training data were extracted and an accuracy of 87.3% (AUC 0.94) at the other site whose data were only used for validation. This investigation demonstrates the high accuracy achievable with CNN analysis of EEG plot images and the robustness of this approach across EEG visualization software, laying the groundwork for further subclassification of seizures using similar approaches in a clinical setting.

Calibrating Deep Learning Classifiers for Patient-Independent Electroencephalogram Seizure Forecasting.

The recent scientific literature abounds in proposals of seizure forecasting methods that exploit machine learning to automatically analyze electroencephalogram (EEG) signals. Deep learning algorithms seem to achieve a particularly remarkable performance, suggesting that the implementation of clinical devices for seizure prediction might be within reach. However, most of the research evaluated the robustness of automatic forecasting methods through randomized cross-validation techniques, while clinical applications require much more stringent validation based on patient-independent testing. In this study, we show that automatic seizure forecasting can be performed, to some extent, even on independent patients who have never been seen during the training phase, thanks to the implementation of a simple calibration pipeline that can fine-tune deep learning models, even on a single epileptic event recorded from a new patient. We evaluate our calibration procedure using two datasets containing EEG signals recorded from a large cohort of epileptic subjects, demonstrating that the forecast accuracy of deep learning methods can increase on average by more than 20%, and that performance improves systematically in all independent patients. We further show that our calibration procedure works best for deep learning models, but can also be successfully applied to machine learning algorithms based on engineered signal features. Although our method still requires at least one epileptic event per patient to calibrate the forecasting model, we conclude that focusing on realistic validation methods allows to more reliably compare different machine learning approaches for seizure prediction, enabling the implementation of robust and effective forecasting systems that can be used in daily healthcare practice.

The value of linear and non-linear quantitative EEG analysis in paediatric epilepsy surgery: a machine learning approach.

Epilepsy surgery is effective for patients with medication-resistant seizures, however 20-40% of them are not seizure free after surgery. Aim of this study is to evaluate the role of linear and non-linear EEG features to predict post-surgical outcome. We included 123 paediatric patients who underwent epilepsy surgery at Bambino Gesù Children Hospital (January 2009-April 2020). All patients had long term video-EEG monitoring. We analysed 1-min scalp interictal EEG (wakefulness and sleep) and extracted 13 linear and non-linear EEG features (power spectral density (PSD), Hjorth, approximate entropy, permutation entropy, Lyapunov and Hurst value). We used a logistic regression (LR) as feature selection process. To quantify the correlation between EEG features and surgical outcome we used an artificial neural network (ANN) model with 18 architectures. LR revealed a significant correlation between PSD of alpha band (sleep), Mobility index (sleep) and the Hurst value (sleep and awake) with outcome. The fifty-four ANN models gave a range of accuracy (46-65%) in predicting outcome. Within the fifty-four ANN models, we found a higher accuracy (64.8% ± 7.6%) in seizure outcome prediction, using features selected by LR. The combination of PSD of alpha band, mobility and the Hurst value positively correlate with good surgical outcome.

Approach to Patients with Seizures and Epilepsy: A Guide for Primary Care Physicians.

Seizures and epilepsy are common neurologic conditions that are frequently encountered in the outpatient primary care setting. An accurate diagnosis relies on a thorough clinical history and evaluation. Understanding seizure semiology and classification is crucial in conducting the initial assessment. Knowledge of common seizure triggers and provoking factors can further guide diagnostic testing and initial management. The pharmacodynamic characteristics and side effect profiles of anti-seizure medications are important considerations when deciding treatment and counseling patients, particularly those with comorbidities and in special populations such as patient of childbearing potential.

PyHFO: lightweight deep learning-powered end-to-end high-frequency oscillations analysis application.

Objective. This study aims to develop and validate an end-to-end software platform, PyHFO, that streamlines the application of deep learning (DL) methodologies in detecting neurophysiological biomarkers for epileptogenic zones from EEG recordings.Approach. We introduced PyHFO, which enables time-efficient high-frequency oscillation (HFO) detection algorithms like short-term energy and Montreal Neurological Institute and Hospital detectors. It incorporates DL models for artifact and HFO with spike classification, designed to operate efficiently on standard computer hardware.Main results. The validation of PyHFO was conducted on three separate datasets: the first comprised solely of grid/strip electrodes, the second a combination of grid/strip and depth electrodes, and the third derived from rodent studies, which sampled the neocortex and hippocampus using depth electrodes. PyHFO demonstrated an ability to handle datasets efficiently, with optimization techniques enabling it to achieve speeds up to 50 times faster than traditional HFO detection applications. Users have the flexibility to employ our pre-trained DL model or use their EEG data for custom model training.Significance. PyHFO successfully bridges the computational challenge faced in applying DL techniques to EEG data analysis in epilepsy studies, presenting a feasible solution for both clinical and research settings. By offering a user-friendly and computationally efficient platform, PyHFO paves the way for broader adoption of advanced EEG data analysis tools in clinical practice and fosters potential for large-scale research collaborations.

Parallel Dual-Branch Fusion Network for Epileptic Seizure Prediction.

Epilepsy is a prevalent chronic disorder of the central nervous system. The timely and accurate seizure prediction using the scalp Electroencephalography (EEG) signal can make patients adopt reasonable preventive measures before seizures occur and thus reduce harm to patients. In recent years, deep learning-based methods have made significant progress in solving the problem of epileptic seizure prediction. However, most current methods mainly focus on modeling short- or long-term dependence in EEG, while neglecting to consider both. In this study, we propose a Parallel Dual-Branch Fusion Network (PDBFusNet) which aims to combine the complementary advantages of Convolutional Neural Network (CNN) and Transformer. Specifically, the features of the EEG signal are first extracted using Mel Frequency Cepstral Coefficients (MFCC). Then, the extracted features are delivered into the parallel dual-branches to simultaneously capture the short- and long-term dependencies of EEG signal. Further, regarding the Transformer branch, a novel feature fusion module is developed to enhance the ability of utilizing time, frequency, and channel information. To evaluate our proposal, we perform sufficient experiments on the public epileptic EEG dataset CHB-MIT, where the accuracy, sensitivity, specificity and precision are 95.76%, 95.81%, 95.71% and 95.71%, respectively. PDBFusNet shows superior performance compared to state-of-the-art competitors, which confirms the effectiveness of our proposal.

Pathophysiology, Diagnosis, Prognosis, and Prevention of Poststroke Epilepsy: Clinical and Research Implications.

Poststroke epilepsy (PSE) is associated with higher mortality and poor functional and cognitive outcomes in patients with stroke. With the remarkable development of acute stroke treatment, there is a growing number of survivors with PSE. Although approximately 10% of patients with stroke develop PSE, given the significant burden of stroke worldwide, PSE is a significant problem in stroke survivors. Therefore, the attention of health policymakers and significant funding are required to promote PSE prevention research. The current PSE definition includes unprovoked seizures occurring more than 7 days after stroke onset, given the high recurrence risks of seizures. However, the pathologic cascade of stroke is not uniform, indicating the need for a tissue-based approach rather than a time-based one to distinguish early seizures from late seizures. EEG is a commonly used tool in the diagnostic work-up of PSE. EEG findings during the acute phase of stroke can potentially stratify the risk of subsequent seizures and predict the development of poststroke epileptogenesis. Recent reports suggest that cortical superficial siderosis, which may be involved in epileptogenesis, is a promising marker for PSE. By incorporating such markers, future risk-scoring models could guide treatment strategies, particularly for the primary prophylaxis of PSE. To date, drugs that prevent poststroke epileptogenesis are lacking. The primary challenge involves the substantial cost burden due to the difficulty of reliably enrolling patients who develop PSE. There is, therefore, a critical need to determine reliable biomarkers for PSE. The goal is to be able to use them for trial enrichment and as a surrogate outcome measure for epileptogenesis. Moreover, seizure prophylaxis is essential to prevent functional and cognitive decline in stroke survivors. Further elucidation of factors that contribute to poststroke epileptogenesis is eagerly awaited. Meanwhile, the regimen of antiseizure medications should be based on individual cardiovascular risk, psychosomatic comorbidities, and concomitant medications. This review summarizes the current understanding of poststroke epileptogenesis, its risks, prognostic models, prophylaxis, and strategies for secondary prevention of seizures and suggests strategies to advance research on PSE.

Diagnostic biomarker discovery from brain EEG data using LSTM, reservoir-SNN, and NeuCube methods in a pilot study comparing epilepsy and migraine.

The study introduces a new online spike encoding algorithm for spiking neural networks (SNN) and suggests new methods for learning and identifying diagnostic biomarkers using three prominent deep learning neural network models: deep BiLSTM, reservoir SNN, and NeuCube. EEG data from datasets related to epilepsy, migraine, and healthy subjects are employed. Results reveal that BiLSTM hidden neurons capture biological significance, while reservoir SNN activities and NeuCube spiking dynamics identify EEG channels as diagnostic biomarkers. BiLSTM and reservoir SNN achieve 90 and 85% classification accuracy, while NeuCube achieves 97%, all methods pinpointing potential biomarkers like T6, F7, C4, and F8. The research bears implications for refining online EEG classification, analysis, and early brain state diagnosis, enhancing AI models with interpretability and discovery. The proposed techniques hold promise for streamlined brain-computer interfaces and clinical applications, representing a significant advancement in pattern discovery across the three most popular neural network methods for addressing a crucial problem. Further research is planned to study how early can these diagnostic biomarkers predict an onset of brain states.

Variantes normales de aspecto epileptiforme en el electroencefalograma. Revisión de la bibliografía e implicaciones clínicas / Normal variants with an epileptiform appearance in electroencephalograms. A literature review and clinical implications

Las variantes normales de aspecto epileptiforme, o variantes epileptiformes benignas, son un reto diagnóstico en la interpretación de los electroencefalogramas que requiere su conocimiento y una amplia experiencia por parte de los responsables del informe electroencefalográfico. Incluyen un grupo heterogéneo de hallazgos, algunos muy infrecuentes, que inicialmente se relacionaron con epilepsia y patologías neurológicas diversas. En la actualidad, la mayoría se consideran variantes sin significado patológico, y su sobreinterpretación habitualmente acarrea diagnósticos erróneos y tratamientos innecesarios. Los datos de prevalencia de estas variantes son muy diversos y proceden habitualmente de poblaciones seleccionadas, por lo que son difícilmente extrapolables a población sana. No obstante, estudios con electrodos invasivos y series más recientes vuelven a asociar algunas de estas variantes con epilepsia. Nuestro objetivo es revisar las características y la prevalencia de las principales variantes epileptiformes benignas y actualizar su significado clínico. (AU)

Automatic Detection of Scalp High-Frequency Oscillations Based on Deep Learning.

Scalp high-frequency oscillations (sHFOs) are a promising non-invasive biomarker of epilepsy. However, the visual marking of sHFOs is a time-consuming and subjective process, existing automatic detectors based on single-dimensional analysis have difficulty with accurately eliminating artifacts and thus do not provide sufficient reliability to meet clinical needs. Therefore, we propose a high-performance sHFOs detector based on a deep learning algorithm. An initial detection module was designed to extract candidate high-frequency oscillations. Then, one-dimensional (1D) and two-dimensional (2D) deep learning models were designed, respectively. Finally, the weighted voting method is used to combine the outputs of the two model. In experiments, the precision, recall, specificity and F1-score were 83.44%, 83.60%, 96.61% and 83.42%, respectively, on average and the kappa coefficient was 80.02%. In addition, the proposed detector showed a stable performance on multi-centre datasets. Our sHFOs detector demonstrated high robustness and generalisation ability, which indicates its potential applicability as a clinical assistance tool. The proposed sHFOs detector achieves an accurate and robust method via deep learning algorithm.

Prognostic Value of Complete Resection of the High-Frequency Oscillation Area in Intracranial EEG: A Systematic Review and Meta-Analysis.

BACKGROUND AND OBJECTIVES: High-frequency oscillations (HFOs; ripples 80-250 Hz; fast ripples [FRs] 250-500 Hz) recorded with intracranial electrodes generated excitement and debate about their potential to localize epileptogenic foci. We performed a systematic review and meta-analysis on the prognostic value of complete resection of the HFOs-area (crHFOs-area) for epilepsy surgical outcome in intracranial EEG (iEEG) accessing multiple subgroups. METHODS: We searched PubMed, Embase, and Web of Science for original research from inception to October 27, 2022. We defined favorable surgical outcome (FSO) as Engel class I, International League Against Epilepsy class 1, or seizure-free status. The prognostic value of crHFOs-area for FSO was assessed by (1) the pooled FSO proportion after crHFOs-area; (2) FSO for crHFOs-area vs without crHFOs-area; and (3) the predictive performance. We defined high combined prognostic value as FSO proportion >80% + FSO crHFOs-area >without crHFOs-area + area under the curve (AUC) >0.75 and examined this for the clinical subgroups (study design, age, diagnostic type, HFOs-identification method, HFOs-rate thresholding, and iEEG state). Temporal lobe epilepsy (TLE) was compared with extra-TLE through dichotomous variable analysis. Individual patient analysis was performed for sex, affected hemisphere, MRI findings, surgery location, and pathology. RESULTS: Of 1,387 studies screened, 31 studies (703 patients) met our eligibility criteria. Twenty-seven studies (602 patients) analyzed FRs and 20 studies (424 patients) ripples. Pooled FSO proportion after crHFOs-area was 81% (95% CI 76%-86%) for FRs and 82% (73%-89%) for ripples. Patients with crHFOs-area achieved more often FSO than those without crHFOs-area (FRs odds ratio [OR] 6.38, 4.03-10.09, p < 0.001; ripples 4.04, 2.32-7.04, p < 0.001). The pooled AUCs were 0.81 (0.77-0.84) for FRs and 0.76 (0.72-0.79) for ripples. Combined prognostic value was high in 10 subgroups: retrospective, children, long-term iEEG, threshold (FRs and ripples) and automated detection and interictal (FRs). FSO after complete resection of FRs-area (crFRs-area) was achieved less often in people with TLE than extra-TLE (OR 0.37, 0.15-0.89, p = 0.006). Individual patient analyses showed that crFRs-area was seen more in patients with FSO with than without MRI lesions (p = 0.02 after multiple correction). DISCUSSION: Complete resection of the brain area with HFOs is associated with good postsurgical outcome. Its prognostic value holds, especially for FRs, for various subgroups. The use of HFOs for extra-TLE patients requires further evidence.

Clinically significant changes in genes and variants associated with epilepsy over time: implications for re-analysis.

Despite the significant advances in understanding the genetic architecture of epilepsy, many patients do not receive a molecular diagnosis after genomic testing. Re-analysing existing genomic data has emerged as a potent method to increase diagnostic yields-providing the benefits of genomic-enabled medicine to more individuals afflicted with a range of different conditions. The primary drivers for these new diagnoses are the discovery of novel gene-disease and variants-disease relationships; however, most decisions to trigger re-analysis are based on the passage of time rather than the accumulation of new knowledge. To explore how our understanding of a specific condition changes and how this impacts re-analysis of genomic data from epilepsy patients, we developed Vigelint. This approach combines the information from PanelApp and ClinVar to characterise how the clinically relevant genes and causative variants available to laboratories change over time, and this approach to five clinical-grade epilepsy panels. Applying the Vigelint pipeline to these panels revealed highly variable patterns in new, clinically relevant knowledge becoming publicly available. This variability indicates that a more dynamic approach to re-analysis may benefit the diagnosis and treatment of epilepsy patients. Moreover, this work suggests that Vigelint can provide empirical data to guide more nuanced, condition-specific approaches to re-analysis.