A method for detecting epileptic spikes in EEG recordings that leverages additional EMG channels to identify and remove muscle artifacts is presented. Unlike conventional approaches, our method models the uneven propagation of muscle artifacts by applying a filter bank and linear regression to clean the EEG signal. Spike detection is then performed using template matching with user-defined parameters, such as amplitude and duration, designed for neurophysiological interpretability. To validate our approach, we developed a dedicated database comprising EEG and EMG recordings from 20 participants. Artificial triangular spikes were added to EEG segments contaminated with muscle artifacts, creating numerous examples of spikes masked by artifacts. This dataset enabled a systematic evaluation of both preprocessing and spike detection techniques. Our method achieved a sensitivity of 0.88, specificity of 1.00, and precision of 0.79 in the detection of simulated spikes. Further testing on real EEG data with interictal spikes and added muscle artifacts yielded a sensitivity of 0.83, specificity of 0.99, and precision of 0.71, demonstrating robust performance even under challenging conditions. These results indicate that incorporating EMG channels to account for muscle activity substantially improves the effectiveness of EEG signal analysis. The proposed approach facilitates reliable detection of epileptic spikes, even when masked by muscle artifacts, and allows neurophysiologists to tailor detection criteria to specific amplitude and temporal features.

Objectives:Mesial temporal lobe epilepsy (MTLE) is a common neurological disorder, with memory impairment being one of its typical symptoms. Most previous studies have focused on assessing declarative memory directly related to hippocampal functions, but emerging data suggest a decline in the efficiency of other types of memory as well. The aim of this study was to comprehensively assess various types of memory and analyze the relationship between memory performance and the volume of selected gray matter structures. Methods:In total, 21 patients with left-MTLE and 28 age- and education-matched healthy individuals underwent neuropsychological assessment using the Wechsler Memory Scale IV (WMS-IV) to evaluate memory functioning. Magnetic resonance imaging was also conducted to assess gray matter volume and structure in all participants. Results:Compared with healthy controls, patients with left-MTLE showed significantly reduced performance in short-term verbal and visual memory, long-term verbal and visual memory, and working memory. Volumetric analysis revealed differences in gray matter volume between groups, with some structures being smaller and others larger in the patient group. Numerous correlations were found between WMS-IV scores and the volume of specific brain regions. Significant associations were observed both ipsilateral and contralateral to the epileptic focus, involving regions such as the cerebellar cortex, cingulate gyrus, insula, thalamus, and pallidum. Conclusion:This study expands our understanding of the memory profile in patients with MTLE. Neuropsychological testing showed that patients performed worse than controls across all assessed memory domains. Additionally, the study identified a distinct pattern of neuronal abnormalities and brain-behavior correlations. These findings suggest that the extent of structural brain anomalies may be linked to the severity of memory impairment in MTLE, underscoring the complex relationship between neuroanatomy and cognitive function in this population.

Removing artifacts from electroencephalography (EEG) signals is a common technique. Although numerous algorithms have been proposed, most rely solely on EEG data. In this study, we introduce a novel approach utilizing a hybrid convolutional neural network–long short-term memory (CNN-LSTM) architecture alongside simultaneous recording of facial and neck EMG signals. This setup enables the precise elimination of artifacts from the EEG signal. To validate the method, we collected a dataset from 24 participants who were presented with a light-emitting diode (LED) stimulus that elicited steady-state visual evoked potentials (SSVEPs) while they performed strong jaw clenching, an action known to induce significant artifacts. We then assessed the algorithm’s ability to remove artifacts while preserving SSVEP responses. The results were compared against other commonly used algorithms, such as independent component analysis and linear regression. The findings demonstrate that the proposed method exhibits excellent performance, effectively removing artifacts while retaining the EEG signal’s useful components.

The aim of this study was to implement and evaluate a simplified convolutional neural network (CNN) architecture for the automatic detection of interictal epileptiform discharges (IEDs) in EEG signals. In recent years, deep learning techniques have become the dominant approach in supporting epilepsy diagnosis; however, many proposed models are characterized by high architectural complexity and significant computational cost. In response to these limitations, a lightweight, three-layer CNN was designed and evaluated using data from 60 patients diagnosed with epilepsy. The model achieved strong classification performance, with an accuracy of 94.44%, precision of 70.83%, sensitivity of 74.50%, specificity of 96.63%, F1-score of 72.62%, and an AUC of 95.26%. These results demonstrate that even shallow and parameter-efficient networks can achieve performance comparable to much more complex architectures, while offering advantages such as lower hardware requirements and shorter training times. The conducted analysis indicates that the proposed solution can be effectively used as a component of clinical decision support systems for epilepsy diagnosis, providing a balance between simplicity and classification effectiveness.

Background: Temporal lobe epilepsy is a common neurological disease that affects many areas of patients’ lives, including social competence. The aim of the study was to assess theory of mind in patients with temporal lobe epilepsy and to investigate the demographic and clinical factors associated with this function. Methods: A total of 65 participants took part in the study, which included 44 patients with epilepsy and 21 demographically matched healthy individuals. The following neuropsychological tests were used to examine theory of mind: the Faux Pas Test, the Hinting Task, the Emotion Comprehension Test, and a cognitive function screen, the Montreal Cognitive Assessment. Results: Patients with epilepsy scored lower on all measures of the theory-of-mind tests. Moreover, in the clinical group, numerous moderate and strong correlations were found between the theory-of-mind tests and education, age at onset of epilepsy, lateralization of epileptic focus, cognitive status, and, to a lesser degree, number of anti-epileptic drugs, frequency of seizures, and age. In contrast, in the control group, significant correlations were found mostly between the theory-of-mind tests and sex, and, to a lesser degree, age. Education and cognitive functioning were not associated. Conclusions: Patients with epilepsy experience difficulties in theory of mind, which may have a negative impact on the quality of their social relationships. The level of theory-of-mind abilities correlates with particular clinical and demographic indicators. Recognizing these issues allows clinicians to implement tailored interventions, potentially improving patients’ quality of life.

The aim of the study was a comprehensive assessment of the profile of executive dysfunctions in patients with MTLE and the search for associations between the results of neuropsychological tests and individual clinical variables.We examined 25 patients with MTLE and 25 healthy controls using the Montreal Cognitive Assessment (MoCA), Color Trails Test (CTT), Tower of London (ToL), Victoria Stroop Test (VLT) and Wisconsin Card Sorting Test (WCST).We considered the possible effects of seizure frequency and lateralization of the epileptogenic zone on various aspects of cognitive functioning. MTLE group scored significantly lower than controls in MoCA (p = 0.000) and needed significantly more time (p=0.000) in CTT-2. They also had lower scores in several parts of ToL (total correct, p=0.004; additional moves, p=0.038; execution time, p=0.001; problem-solving time, p=0.003) and WCST (error responses, p=0.003; conceptual level responses, p=0.000; com - pleted categories, p=0.007; perseverative responses, p=0.004; perseverative errors, p=0.009). There were no significant dif- ferences between the clinical and control group in VST and in other indicators of CTT, ToL and WCST. Neither the laterality of the epileptogenic focus nor the seizure frequency were sig- nificantly correlated with the results.Patients with MTLE exhibit a wide range of executive dysfunctions. Importantly, the disorders were present only in some aspects of functioning, such as: logical reasoning, planning, switching between tasks, cognitive flexibility and problem-solving, while others e.g. inhibition, remained normal. Our results constitute a significant enrichment of knowledge concerning the specificity of functioning of this group of patients which may help clinicians to introduce solutions to improve the functioning of these patients.

Drug-resistant temporal lobe epilepsy is associated with a reduction in the quality of life of patients. The aim of this study was to compare the quality of life before and after the surgical treatment of epilepsy and to assess factors that may affect the well-being of patients after surgery. The study involved 168 patients with drug-resistant temporal lobe epilepsy. All of them were examined twice: once before and again one year after surgery. Two questionnaires were used in the study: the Quality of Life in Epilepsy Inventory-Patient-Weighted and Hospital Anxiety and Depression Scale and one that collected data on selected demographic and clinical variables. The results showed that patients scored significantly higher in quality of life and lower in depression and anxiety after surgery; however, this only applied to patients with a good outcome of treatment (Engel Class I and Class II). Patients with an unfavorable outcome of surgical treatment (Engel Class III and Class IV) achieved significantly worse results in all examined variables. Correlational analysis showed a relationship between select aspects of quality of life and the level of depression and anxiety, as well as the frequency of seizures and age at epilepsy onset. There was no significant relationship with age, sex, education, or number of prescribed antiepileptic drugs. The study confirms the significant relationship between the quality of life and the effectiveness of surgical treatment, indicating the relationship between patients' well-being and selected clinical indicators.

The purpose of the article is to investigate whether the implementation of a CNN consisting of several layers will allow the effective detection of epileptic seizures. For the research, a publicly available database registered for 4 dogs and 8 people was used. The 1-second iEEG recordings were marked by a neurophysiologist as interictal, early seizure, and seizure. A CNN was trained for each patient individually. Coefficients such as precision, AUC, sensitivity, and specificity were calculated, and the results were compared with the best algorithms published in one of the contests on the Kaggle platform. The average accuracy for the recognition of seizures using CNN is 0.921, the sensitivity is 0.850, and the specificity is 0.927. For early seizures these values are 0.825, 0.782, and 0.828, respectively.

AimsEpilepsy is one of the most common chronic neurological disorders, affecting around 50 million people worldwide, but its underlying cellular and molecular events are not fully understood. The Golgi is a highly dynamic cellular organelle and can be fragmented into ministacks under both physiological and pathological conditions. This phenomenon has also been observed in several neurodegenerative disorders; however, the structure of the Golgi apparatus (GA) in human patients suffering from epilepsy has not been described so far. The aim of this study was to assess the changes in GA architecture in epilepsy.MethodsGolgi visualisation with immunohistochemical staining in the neocortex of adult patients who underwent epilepsy surgery; 3D reconstruction and quantitative morphometric analysis of GA structure in the rat hippocampi upon kainic acid (KA) induced seizures, as well as in vitro studies with the use of Ca2+ chelator BAPTA-AM in primary hippocampal neurons upon activation were performed.ResultsWe observed GA dispersion in neurons of the human neocortex of patients with epilepsy and hippocampal neurons in rats upon KA-induced seizures. The structural changes of GA were reversible, as GA morphology returned to normal within 24 h of KA treatment. KA-induced Golgi fragmentation observed in primary hippocampal neurons cultured in vitro was largely abolished by the addition of BAPTA-AM.ConclusionsIn our study, we have shown for the first time that the neuronal GA is fragmented in the human brain of patients with epilepsy and rat brain upon seizures. We have shown that seizure-induced GA dispersion can be reversible, suggesting that enhanced neuronal activity induces Golgi reorganisation that is involved in aberrant neuronal plasticity processes that underlie epilepsy. Moreover, our results revealed that elevated cytosolic Ca2+ is indispensable for these KA-induced morphological alterations of GA in vitro. The neuronal Golgi apparatus is fragmented in the human brain of patients with epilepsy and rat brain upon seizures. Seizure-induced GA dispersion can be reversible, suggesting that enhanced neuronal activity induces Golgi reorganization that is involved in aberrant neuronal plasticity processes that underlie epilepsy. The driving force behind KA-induced Golgi fragmentation is the elevated cytosolic Ca2+.image

This chapter investigates the effects of monotherapy with carbamazepine (CBZ) or phenytoin (PHT) on the visual evoked potentials (VEPs), brainstem evoked potentials (BAEPs) and somatosensory evoked potentials. Patients with brain pathology upon CT scan or progressive neurologic disease and patients likely to be noncompliant were excluded. Serum drug levels were measured for CBZ or PHT and were within therapeutic range in all subjects. Electrophysiologic studies included VEPs after monooculs full-field pattern-reversal stimulation, click-stimulus BAEPs, and median nerve short-latency somatosensory evoked potentials, which were recorded before the treatment, according to American Electroencephalographic Society guidelines for clinical EPs studies. Electrophysiologic evaluation was repeated after at least 2 to 3 months of monotherapy. The results on the same group of patients before and after treatment were compared. Little information is available on the effects of PHT or CBZ on EPs. It concerns mainly patients receiving chronic anticonvulsant therapy.

This paper presents a system for locating the epileptogenic zone (EZ) using an automated analysis of electrocorticography (ECoG) signal recorded with 20 electrodes placed on the brain surface. The developed system enables automatic determination of places where anomalies connected with epilepsy are observed. The developed algorithm was tested on signals recorded for 33 patients who, after a prior neurological analysis, underwent the brain resection surgery. The results obtained with the algorithm were compared with those of medical analyses performed by the neurologist. The proposed system has a satisfactory accuracy 87.8% - and can be used as a decision-supporting tool by the neurosurgeon during brain resection.

The diagnosis of epilepsy primarily relies on the visual and subjective assessment of the patient's electroencephalographic (EEG) or intracranial electroencephalographic (iEEG) signals. Neurophysiologists, based on their experience, look for characteristic discharges such as spikes and multi-spikes. One of the main challenges in epilepsy research is developing an automated system capable of detecting epileptic seizures with high sensitivity and precision. Moreover, there is an ongoing search for universal features in iEEG signals that can be easily interpreted by neurophysiologists. This article explores the possibilities, issues, and challenges associated with utilizing artificial intelligence for seizure detection using the publicly available iEEG database. The study presents standard approaches for analyzing iEEG signals, including chaos theory, energy in different frequency bands (alpha, beta, gamma, theta, and delta), wavelet transform, empirical mode decomposition, and machine learning techniques such as support vector machines. It also discusses modern deep learning algorithms such as convolutional neural networks (CNN) and long short-term memory (LSTM) networks. Our goal was to gather and comprehensively compare various artificial intelligence techniques, including both traditional machine learning methods and deep learning techniques, which are most commonly used in the field of seizure detection. Detection results were tested on a separate dataset, demonstrating classification accuracy, sensitivity, precision, and specificity of seizure detection. The best results for seizure detection were obtained with features related to iEEG signal energy (accuracy of 0.97, precision of 0.96, sensitivity of 0.99, and specificity of 0.96), as well as features related to chaos, Lyapunov exponents, and fractal dimension (accuracy, precision, sensitivity, and specificity all equal to 0.95). The application of CNN and LSTM networks yielded significantly better results (CNN: Accuracy of 0.99, precision of 0.98, sensitivity of 1, and specificity of 0.99; LSTM: Accuracy of 0.98, precision of 0.96, sensitivity of 1, and specificity of 0.99). Additionally, the use of the gradient-weighted class activation mapping algorithm identified iEEG signal fragments that played a significant role in seizure detection.

Epilepsy is a neurological disorder that causes seizures of many different types. The article presents an analysis of heart rate variability (HRV) for epileptic seizure prediction. Considering that HRV is nonstationary, our research focused on the quantitative analysis of a Poincare plot feature, i.e. cardiac sympathetic index (CSI). It is reported that the CSI value increases before the epileptic seizure. An algorithm using a 1D-convolutional neural network (1D-CNN) was proposed for CSI estimation. The usability of this method was checked for 40 epilepsy patients. Our algorithm was compared with the method proposed by Toichi et al. The mean squared error (MSE) for testing data was 0.046 and the mean absolute percentage error (MAPE) amounted to 0.097. The 1D-CNN algorithm was also compared with regression methods. For this purpose, a classical type of neural network (MLP), as well as linear regression and SVM regression, were tested. In the study, typical artifacts occurring in ECG signals before and during an epileptic seizure were simulated. The proposed 1D-CNN algorithm estimates CSI well and is resistant to noise and artifacts in the ECG signal.

W ostatnich latach opublikowano wiele rekomendacji oraz standardów diagnostyki i leczenia chorych z padaczką. Mimo różnic między przedstawionymi zaleceniami podstawowe zasady dotyczące stosowania leków przeciwpadaczkowych są wspólne i dokładnie określone. W Polsce w ostatnich kilku latach zasady refundacji istotnie się zmieniły. Wprowadzone zmiany umożliwiają wybór terapii zgodnie z dostępną wiedzą wynikającą z przeprowadzonych badań klinicznych oraz doświadczenia nagromadzonego w praktyce klinicznej. Podstawowe znaczenie dla uzyskania pozytywnego efektu stosowanej terapii ma prawidłowo przeprowadzona diagnostyka. Właściwe rozpoznanie odpowiedniego typu napadów padaczkowych lub określonego zespołu padaczkowego warunkuje skuteczność terapii. W artykule przedstawiono aktualne zalecenia dotyczące diagnozowania i leczenia padaczki zarówno na etapie wstępnym, jak i u osób z podejrzeniem padaczki lekoopornej. Dokonano również adaptacji rekomendacji międzynarodowych do warunków systemu opieki neurologicznej funkcjonującego w Polsce. Sekcja Padaczki Polskiego Towarzystwa Neurologicznego opracowała niniejsze rekomendacje na podstawie dostępnych danych naukowych oraz uwarunkowań refundacyjnych obowiązujących w Polsce na 2022 rok.