Residual and bidirectional LSTM for epileptic seizure detection.

Electroencephalogram (EEG) plays a pivotal role in the detection and analysis of epileptic seizures, which affects over 70 million people in the world. Nonetheless, the visual interpretation of EEG signals for epilepsy detection is laborious and time-consuming. To tackle this open challenge, we introduce a straightforward yet efficient hybrid deep learning approach, named ResBiLSTM, for detecting epileptic seizures using EEG signals. Firstly, a one-dimensional residual neural network (ResNet) is tailored to adeptly extract the local spatial features of EEG signals. Subsequently, the acquired features are input into a bidirectional long short-term memory (BiLSTM) layer to model temporal dependencies. These output features are further processed through two fully connected layers to achieve the final epileptic seizure detection. The performance of ResBiLSTM is assessed on the epileptic seizure datasets provided by the University of Bonn and Temple University Hospital (TUH). The ResBiLSTM model achieves epileptic seizure detection accuracy rates of 98.88-100% in binary and ternary classifications on the Bonn dataset. Experimental outcomes for seizure recognition across seven epilepsy seizure types on the TUH seizure corpus (TUSZ) dataset indicate that the ResBiLSTM model attains a classification accuracy of 95.03% and a weighted F1 score of 95.03% with 10-fold cross-validation. These findings illustrate that ResBiLSTM outperforms several recent deep learning state-of-the-art approaches.

Threshold of somatic mosaicism leading to brain dysfunction with focal epilepsy.

Somatic mosaicism in a fraction of brain cells causes neurodevelopmental disorders, including childhood intractable epilepsy. However, the threshold for somatic mosaicism leading to brain dysfunction is unknown. In this study, we induced various mosaic burdens in focal cortical dysplasia type II (FCD II) mice, featuring mTOR somatic mosaicism and spontaneous behavioral seizures. The mosaic burdens ranged from approximately 1,000 to 40,000 neurons expressing the mTOR mutant in the somatosensory (SSC) or medial prefrontal (PFC) cortex. Surprisingly, approximately 8,000 to 9,000 neurons expressing the MTOR mutant, which are extrapolated to constitute 0.08-0.09% of total cells or roughly 0.04% of variant allele frequency (VAF) in the mouse hemicortex, were sufficient to trigger epileptic seizures. The mutational burden was correlated with seizure frequency and onset, with a higher tendency for electrographic inter-ictal spikes and beta- and gamma-frequency oscillations in FCD II mice exceeding the threshold. Moreover, mutation-negative FCD II patients in deep sequencing of their bulky brain tissues revealed somatic mosaicism of the mTOR pathway genes as low as 0.07% in resected brain tissues through ultra-deep targeted sequencing (up to 20 million reads). Thus, our study suggests that extremely low levels of somatic mosaicism can contribute to brain dysfunction.

AI in ECG: Validating an ambulatory semiology labeller and predictor.

OBJECTIVES: Early prediction of epileptic seizures can help reduce morbidity and mortality. In this work, we explore using electrocardiographic (ECG) signal as input to a seizure prediction system and note that the performance can be improved by using selected signal processing techniques. METHODS: We used frequency domain analysis with a deep neural network backend for all our experiments in this work. We further analysed the effect of the proposed system for different seizure semiologies and prediction horizons. We explored refining the signal using signal processing to enhance the system's performance. RESULTS: Our final system using the Temple University Hospital's Seizure (TUHSZ) corpus gave an overall prediction accuracy of 84.02 %, sensitivity of 87.59 %, specificity of 81.9 %, and an area under the receiver operating characteristic curve (AUROC) of 0.9112. Notably, these results surpassed the state-of-the-art outcomes reported using the TUHSZ database; all findings are statistically significant. We also validated our study using the Siena scalp EEG database. Using the frequency domain data, our baseline system gave a performance of 75.17 %, 79.17 %, 70.04 % and 0.82 for prediction accuracy, sensitivity, specificity and AUROC, respectively. After selecting the optimal frequency band of 0.8-15 Hz, we obtained a performance of 80.49 %, 89.51 %, 75.23 % and 0.89 for prediction accuracy, sensitivity, specificity and AUROC, respectively which is an improvement of 5.32 %, 10.34 %, 5.19 % and 0.08 for prediction accuracy, sensitivity, specificity and AUROC, respectively. CONCLUSIONS: The seizure information in ECG is concentrated in a narrow frequency band. Identifying and selecting that band can help improve the performance of seizure detection and prediction. SIGNIFICANCE: EEG is susceptible to artefacts and is not preferred in a low-cost ambulatory device. ECG can be used in wearable devices (like chest bands) and is feasible for developing a low-cost ambulatory device for seizure prediction. Early seizure prediction can provide patients and clinicians with the required alert to take necessary precautions and prevent a fatality, significantly improving the patient's quality of life.

Cervical spinal cord stimulation exerts anti-epileptic effects in a rat model of epileptic seizure through the suppression of CCL2-mediated cascades.

Epidural spinal cord stimulation (SCS) is indicated for the treatment of intractable pain and is widely used in clinical practice. In previous basic research, the therapeutic effects of SCS have been demonstrated for epileptic seizure. However, the mechanism has not yet been elucidated. In this study, we investigated the therapeutic effect of SCS and the influence of epileptic seizure. First, SCS in the cervical spine was performed. The rats were divided into four groups: control group and treatment groups with SCS conducted at 2, 50, and 300 Hz frequency. Two days later, convulsions were induced by the intraperitoneal administration of kainic acid, followed by video monitoring to assess seizures. We also evaluated glial cells in the hippocampus by fluorescent immunostaining, electroencephalogram measurements, and inflammatory cytokines such as C-C motif chemokine ligand 2 (CCL2) by quantitative real-time polymerase chain reaction. Seizure frequency and the number of glial cells were significantly lower in the 300 Hz group than in the control group. SCS at 300 Hz decreased gene expression level of CCL2, which induces monocyte migration. SCS has anti-seizure effects by inhibiting CCL2-mediated cascades. The suppression of CCL2 and glial cells may be associated with the suppression of epileptic seizure.

Short-term epileptic seizures prediction based on cepstrum analysis and signal morphology.

This article aims to provide and implement a patient-specific seizure (for Intervention Time (IT) detection) prediction algorithm using non-invasive data to develop warning devices to prevent further patient injury and reduce stress. Employing algorithms with high initial data volume and computations time to increase the accuracy is an important problem in prediction issues. Consequently, reduction of calculations is met by applying only two effective EEG signal channels without manual removal of artifacts by visual inspection as the algorithm's input. Autoregression (AR) modeling and Cepstrum detect changes due to IT period. We carry out the goal of higher accuracy by increasing sensitivity to interictal epileptiform discharges or artifacts and reduce errors caused by them, taking advantage of the discrete wavelet transform and the comparison of two channels epochs by applying the median filter. Averaging and positive envelope methods are introduced to patient-specific thresholds become more differentiated as soon as possible and can be lead to sooner prediction. We examined this method on a mathematical model of adult epilepsy as well as on 10 patients with EEG data. The results of our experiments confirm that performance of the proposed approach in accuracy and average false prediction rate is superior to other algorithms. Simulation results have been shown the robustness of our proposed method to artifacts and errors, which is a step towards the development of real-time alarm devices by non-invasive techniques.

Post-epileptic seizure posttraumatic stress Disorder: A mediation analysis.

OBJECTIVE: Previous studies investigated the varying prevalence of post-epileptic seizure posttraumatic stress disorder (PS-PTSD). The current study aimed first to compare the profiles of patients with and without PS-PTSD and, second, to study the interaction between other past traumatic experiences, subjective ictal anxiety, psychiatric comorbidities, and PS-PTSD in people with epilepsy (PWE). METHODS: We conducted an observational study, investigating past traumatic experiences and PS-PTSD through standardized scales (CTQ-28, LEC-5 and PCL-5). We used semi-structured interviews and validated psychometric scales (NDDIE for depression and GAD-7 for anxiety) to collect data on general psychiatric comorbidities. We also assessed epilepsy specific psychiatric symptoms (interictal and peri-ictal). We performed a mediation analysis through PROCESS for SPSS to evaluate the effect of history of past trauma and subjective ictal anxiety on PS-PTSD through interictal depression and anxiety symptoms. RESULTS: We enrolled 135 PWE, including 35 patients with PS-PTSD (29.5 %). Patients with PS-PTSD had significantly higher depression (12.87 vs 10; p = 0.005) and anxiety (7.74 vs 5.01; p = 0.027) scores and higher prevalence of peri-ictal psychiatric symptoms, compared to patients without PS-PTSD. The relationship between other past traumatic experiences and PS-PTSD was totally mediated by interictal depression and anxiety. We found a significant indirect effect of interictal anxiety symptoms on the path between subjective ictal anxiety and PS-PTSD. SIGNIFICANCE: Our results showed that patients with PS-PTSD have a more severe psychopathological profile (more peri ictal and inter ictal depressive and anxiety symptoms). Both inter ictal and subjective ictal anxiety appear to have a significant role in PS-PTSD.

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.

Exploration of interictal to ictal transition in epileptic seizures using a neural mass model.

An epileptic seizure can usually be divided into three stages: interictal, preictal, and ictal. However, the seizure underlying the transition from interictal to ictal activities in the brain involves complex interactions between inhibition and excitation in groups of neurons. To explore this mechanism at the level of a single population, this paper employed a neural mass model, named the complete physiology-based model (cPBM), to reconstruct electroencephalographic (EEG) signals and to infer the changes in excitatory/inhibitory connections related to excitation-inhibition (E-I) balance based on an open dataset recorded for ten epileptic patients. Since epileptic signals display spectral characteristics, spectral dynamic causal modelling (DCM) was applied to quantify these frequency characteristics by maximizing the free energy in the framework of power spectral density (PSD) and estimating the cPBM parameters. In addition, to address the local maximum problem that DCM may suffer from, a hybrid deterministic DCM (H-DCM) approach was proposed, with a deterministic annealing-based scheme applied in two directions. The H-DCM approach adjusts the temperature introduced in the objective function by gradually decreasing the temperature to obtain relatively good initialization and then gradually increasing the temperature to search for a better estimation after each maximization. The results showed that (i) reconstructed EEG signals belonging to the three stages together with their PSDs can be reproduced from the estimated parameters of the cPBM; (ii) compared to DCM, traditional D-DCM and anti D-DCM, the proposed H-DCM shows higher free energies and lower root mean square error (RMSE), and it provides the best performance for all stages (e.g., the RMSEs between the reconstructed PSD computed from the reconstructed EEG signal and the sample PSD obtained from the real EEG signal are 0.33 ± 0.08, 0.67 ± 0.37 and 0.78 ± 0.57 in the interictal, preictal and ictal stages, respectively); and (iii) the transition from interictal to ictal activity can be explained by an increase in the connections between pyramidal cells and excitatory interneurons and between pyramidal cells and fast inhibitory interneurons, as well as a decrease in the self-loop connection of the fast inhibitory interneurons in the cPBM. Moreover, the E-I balance, defined as the ratio between the excitatory connection from pyramidal cells to fast inhibitory interneurons and the inhibitory connection with the self-loop of fast inhibitory interneurons, is also significantly increased during the epileptic seizure transition. Supplementary Information: The online version contains supplementary material available at 10.1007/s11571-023-09976-6.

Relationship between Anaplastic Lymphoma Kinase Inhibitors and Epileptic Seizure Disorder: A Post-Marketing Surveillance Study.

INTRODUCTION: Anaplastic lymphoma kinase (ALK) has been to be involved in the uptake and regulation of dopamine 2 receptor (D2R), a G protein-coupled receptor expressed in various brain regions. Therefore, it is crucial to understand the relationship between ALK inhibitors and seizures is an important issue. This study investigated the relationship between ALK inhibitors and seizures. METHODS: This study investigated the relationship between ALK inhibitors and seizures through a disproportionality analysis using the US Food and Drug Administration (FDA) Adverse Event Reporting System (FAERS). The target drugs were the ALK inhibitors crizotinib, ceritinib, alectinib, brigatinib, and lorlatinib. The seizures covered were defined high-level group term (HLGT): "Seizures (incl. subtype)" including high-level term (HLT): "seizures and seizure disorders NEC." This study used the information component (IC), a signal score, as a Bayesian statistical method for disproportionality analysis. The signal detection criteria used in this study were the same as those reported previously: a lower limit of 95% credible interval (CrI) for IC >0. RESULTS: The signal scores of '"seizures and seizure disorders not elsewhere classified (NEC)" "for each ALK inhibitor were crizotinib (IC: -0.00052, 95% CrI: -0.38-0.27), ceritinib (IC: 1.18, 95% CrI: 0.68-1.54), alectinib (IC: 0.68, 95% CrI: 0.19-1.02), brigatinib (IC: 1.04, 95% CrI: 0.32-1.54), and lorlatinib (IC: 0.82, 95% CrI: 0.11-1.32). On the other hand, "generalized tonic-clonic seizures," "partial simple seizures NEC," "absence seizures," and "partial complex seizures" had no or few reported cases, and no signal was detected. CONCLUSION: To our knowledge, this is the first report to evaluate the relationship between ALK inhibitors and seizures using post-marketing surveillance data. These results suggest that ceritinib, alectinib, brigatinib, and lorlatinib, which are highly brain-migrating drugs, are associated with seizures.

Effect of virtual reality-based seizure management education program for parents (VR-ESMEPP) on seizure management: A randomized controlled trial.

OBJECTIVE: This study evaluated the efficacy of Virtual Reality-Based Seizure Management Education Program for Parents (VR-ESMEPP) that was designed to improve parents' knowledge-skill percentage about epileptic seizure, and motivation levels about educational material. METHODS: The study was conducted at a university hospital's pediatric neurology clinic in Turkey and involved both a VR-trained group and a control group. The parents' knowledge-skill percentage about epileptic seizure, and motivation levels about educational material were assessed before, after, and at 15 days after participating in VR-ESMEPP. RESULTS: The parents' knowledge-skill percentage about epileptic seizure increased in the group that participated in the VR-ESMEPP. There was no such increase in the control group. Examination of the scores of the Instructional Materials Motivation Survey (IMMS) for the parents showed that while there was a significant increase between the pre-test and post-test within the group that participated in the VR-ESMEPP, there was no significant difference in the scores of the control group. However, the high IMMS scores obtained by all parents indicate the motivating nature of the education material. SIGNIFICANCE: The study established the efficacy of VR-ESMEPP and demonstrated its ability to enhance parents' knowledge-skill percentage about epileptic seizure. Despite the absence of a difference in motivation levels between the groups, the high scores obtained by all participants indicate that the program was indeed motivating.

Effects of baicalin pre-treatment on pentylenetetrazole-induced seizures: Insights from zebrafish larvae locomotor behavior and neuronal calcium imaging.

Natural compounds are increasingly being studied for their potential neuroprotective effects against inflammatory neurological diseases. Epilepsy is a common neurological disease associated with inflammatory processes, and around 30% of people with epilepsy do not respond to traditional treatments. Some flavonoids, when taken along with antiseizure medications can help reduce the likelihood of drug-resistant epilepsy. Baicalin, a plant-based compound, has been shown to possess pharmacological properties such as anti-inflammatory, neuroprotective, anticonvulsant, and antioxidant activities. In this study, we tested the effect of baicalin on an established model of pharmacologically induced seizure in zebrafish using measures of both locomotor behavior and calcium imaging of neuronal activity. The results of our study showed that, at the tested concentration, and contrary to other studies in rodents, baicalin did not have an anti-seizure effect in zebrafish larvae. However, given its known properties, other concentrations and approaches should be explored to determine if it could potentially have other beneficial effects, either alone or when administered in combination with classic antiseizure medications.

EEG power spectra parameterization and adaptive channel selection towards semi-supervised seizure prediction.

BACKGROUND: The seizure prediction algorithms have demonstrated their potential in mitigating epilepsy risks by detecting the pre-ictal state using ongoing electroencephalogram (EEG) signals. However, most of them require high-density EEG, which is burdensome to the patients for daily monitoring. Moreover, prevailing seizure models require extensive training with significant labeled data which is very time-consuming and demanding for the epileptologists. METHOD: To address these challenges, here we propose an adaptive channel selection strategy and a semi-supervised deep learning model respectively to reduce the number of EEG channels and to limit the amount of labeled data required for accurate seizure prediction. Our channel selection module is centered on features from EEG power spectra parameterization that precisely characterize the epileptic activities to identify the seizure-associated channels for each patient. The semi-supervised model integrates generative adversarial networks and bidirectional long short-term memory networks to enhance seizure prediction. RESULTS: Our approach is evaluated on the CHB-MIT and Siena epilepsy datasets. With utilizing only 4 channels, the method demonstrates outstanding performance with an AUC of 93.15% on the CHB-MIT dataset and an AUC of 88.98% on the Siena dataset. Experimental results also demonstrate that our selection approach reduces the model parameters and training time. CONCLUSIONS: Adaptive channel selection coupled with semi-supervised learning can offer the possible bases for a light weight and computationally efficient seizure prediction system, making the daily monitoring practical to improve patients' quality of life.

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.

Therapeutic value of patent foramen ovale closure for drug-resistant epilepsy: A case series report.

OBJECTIVE: Closure surgery of patent foramen ovale (PFO) has been found to effectively control cryptogenic stroke and migraine, but it is uncertain whether PFO closure could also alleviate epileptic seizures. This study aims to observe the therapeutic effect of PFO closure on epileptic seizures. METHODS: Since July 11th, 2017, in the neurology department of West China Hospital, Sichuan University, Chengdu, we have been regularly monitoring patients with epilepsy who have undergone PFO closure. The patient's clinical information, such as frequency, duration, and severity of seizures, before and after surgery was recorded in detail as well as postoperative safety events. RESULTS: Of the 31 epilepsy patients who confirmed PFO observed (27 cases were drug-resistant epilepsy, 87.10%), average age of surgery was 23.74 years, and 12 cases were female (38.71%). After one-year follow-up, 26 patients (83.87%) achieved remission of seizure frequency, and 22 of whom (70.97%) experienced a remission of more than 50%. Additionally, compared to before surgery, 22 cases (70.97%) reported a decrease in the average seizure duration, and 20 cases (64.52%) reported a reduction in seizure severity. In the seizure indicators of frequency, average duration and severity, significant differences were identified between preoperative and postoperative comparisons with all test p values were <0.05. Furthermore, no serious safety events were reported except for one patient who briefly reported chest pain, and all patients expressed effective PFO closure. SIGNIFICANCE: The PFO closure has been shown for the first time to result in a significant reduction in the frequency, duration, and severity of seizures. Patients with drug-resistant epilepsy and PFO with a large shunt are ideal candidates for undergoing PFO closure. PLAIN LANGUAGE SUMMARY: Since PFO closure was found to have a good therapeutic effect on cryptogenic stroke and migraine, it has become a credible complementary therapy for the treatment of neurological diseases, and drug-resistant epilepsy with PFO is expected to become the next target disease that PFO closure could significantly improve.

Do we intervene less and slower in the epilepsy monitoring unit for psychogenic seizures?

PURPOSE: Individuals with psychogenic non-epileptic seizures (PNES) can be stigmatized in healthcare settings. We aimed to compare intervention rate (IR), intervention time (IT), and adverse event (AE) rate between PNES and epileptic seizures (ES) in the epilepsy monitoring unit (EMU). METHODS: We used a prospective database of consecutive admissions to our centre's EMU between August 2021 and September 2022. We excluded purely electric seizures and vague, minor spells with no EEG correlate. We therefore only included electroclinical seizures and PNES. We compared the IR, IT, and AE rate between PNES and ES, as diagnosed by an epileptologist during EEG monitoring. We performed the same comparisons between spells occurring in people admitted with a high vs low suspicion of PNES (HSP vs LSP). We also verified if ITs became longer with repeated PNES. RESULTS: We analyzed 586 spells: 43 PNES vs 543 ES, or 133 HSP vs 453 LSP. Our univariate analyses showed that IR was higher for PNES than for ES (93 % vs 61 %, p <.001) but that IT and AE rate were similar across groups. This higher IR was only apparent outside weekday daytime hours, when EEG technologists were not present. HSP did not differ from LSP in terms of IR, IT, and AE rate. As PNES accumulated in individual patients, IT tended to be longer (Spearman's correlation = 0.42; p =.012). SIGNIFICANCE: Our EMU staff did not intervene less or slower for PNES. Rather, IR was higher for PNES than for ES, but IT tended to be longer with repeat PNES.

An epilepsy detection method based on multi-dimensional feature extraction and dual-branch hypergraph convolutional network.

Epilepsy is a disease caused by abnormal neural discharge, which severely harms the health of patients. Its pathogenesis is complex and variable with various forms of seizures, leading to significant differences in epilepsy manifestations among different patients. The changes of brain network are strongly correlated with related pathologies. Therefore, it is crucial to effectively and deeply explore the intrinsic features of epilepsy signals to reveal the rules of epilepsy occurrence and achieve accurate detection. Existing methods have faced the following issues: 1) single approach for feature extraction, resulting in insufficient classification information due to the lack of rich dimensions in captured features; 2) inability to deeply analyze the essential commonality of epilepsy signal after feature extraction, making the model susceptible to data distribution and noise interference. Thus, we proposed a high-precision and robust model for epileptic seizure detection, which, for the first time, applies hypergraph convolution to the field of epilepsy detection. Through a hypergraph network structure constructed based on relationships between channels in electroencephalogram (EEG) signals, the model explores higher-order characteristics of epilepsy EEG data. Specifically, we use the Conv-LSTM module and Power spectral density (PSD), a two-branch parallel method, to extract channel features from space-time and frequency domains to solve the problem of insufficient feature extraction, and can adequately describe the data structure and distribution from multiple perspectives through double-branch parallel feature extraction. In addition, we construct a hypergraph on the captured features to explore the intrinsic features in the high-dimensional space in an attempt to reveal the essential commonality of epileptic signal feature extraction. Finally, using the ensemble learning concept, we accomplished epilepsy detection on the dual-branch hypergraph convolution. The model underwent leave-one-out cross-validation on the TUH dataset, achieving an average accuracy of 96.9%, F1 score of 97.3%, Pre of 98.2% and Re of 96.7%. In addition, the model was generalized performance tested on CHB-MIT scalp EEG dataset with leave-one-out cross-validation, and the average ACC, F1 score, Pre and Re were 94.4%, 95.1%, 95.8%, and 93.9% respectively. Experimental results indicate that the model outperforms related literature, providing valuable reference for the clinical application of epilepsy detection.

Pentylenetetrazole kindling induces dynamic changes in GAD65 expression in hippocampal somatostatin interneurons.

INTRODUCTION: One of the mechanisms of epileptgenesis is impairment of inhibitory neural circuits. Several studies have compared neural changes among subtypes of gamma-aminobutyric acid-related (GABAergic) neurons after acquired epileptic seizure. However, it is unclear that GABAergic neural modifications that occur during acquisition process of epileptic seizure. METHODS: Male rats were injected with pentylenetetrazole (PTZ kindling: n = 30) or saline (control: n = 15) every other day to observe the development of epileptic seizure stages. Two time points were identified: the point at which seizures were most difficult to induce, and the point at which seizures were most easy to induce. The expression of GABAergic neuron-related proteins in the hippocampus was immunohistochemically compared among GABAergic subtypes at each of these time points. RESULTS: Bimodal changes in seizure stages were observed in response to PTZ kindling. The increase of seizure stage was transiently suppressed after 8 or 10 injections, and then progressed again by the 16th injection. Based on these results, we defined 10 injections as a short-term injection period during which seizures are less likely to occur, and 20 injections as a long-term injection period during which continuous seizures are likely to occur. The immunohistochemical analysis showed that hippocampal glutamic acid decarboxylase 65 (GAD65) expression was increased after short-term kindling but unchanged after long-term kindling. Increased GAD65 expression was limited to somatostatin-positive (SOM+) cells among several GABAergic subtypes. By contrast, GAD, GABA, GABAAR α1, GABABR1, and VGAT cells showed no change following short- or long-term PTZ kindling. CONCLUSION: PTZ kindling induces bimodal changes in the epileptic seizure stage. Seizure stage is transiently suppressed after short-term PTZ injection with GAD65 upregulation in SOM+ cells. The seizure stage is progressed again after long-term PTZ injection with GAD65 reduction to baseline level.

Emergency medical service response for cases of stroke-suspected seizure: A population-based study.

OBJECTIVES: We evaluated the on-scene time of emergency medical services (EMS) for cases where discrimination between acute stroke and epileptic seizures at the initial examination was difficult and identified factors linked to delays in such scenarios. MATERIALS AND METHODS: A retrospective review of cases with suspected seizure using the EMS database of fire departments across six Japanese cities between 2016 and 2021 was conducted. Patient classification was based on transport codes. We defined cases with stroke-suspected seizure as those in whom epileptic seizure was difficult to differentiate from stroke and evaluated their EMS on-scene time compared to those with epileptic seizures. RESULTS: Among 30,439 cases with any seizures, 292 cases of stroke-suspected seizure and 8,737 cases of epileptic seizure were included. EMS on-scene time in cases of stroke-suspected seizure was shorter than in those with epileptic seizure after propensity score matching (15.1±7.2 min vs. 17.0±9.0 min; p = 0.007). Factors associated with delays included transport during nighttime (odds ratio [OR], 1.73, 95 % confidence interval [CI] 1.02-2.93, p = 0.041) and transport during the 2020-2021 pandemic (OR, 1.77, 95 % CI 1.08-2.90, p = 0.022). CONCLUSION: This study highlighted the difference between the characteristics in EMS for stroke and epileptic seizure by evaluating the response to cases with stroke-suspected seizure. Facilitating prompt and smooth transfers of such cases to an appropriate medical facility after admission could optimize the operation of specialized medical resources.

First seizure in elderly patients: Need to treat? Evidence from a retrospective study.

BACKGROUND: The risk of seizure recurrence after a first unprovoked epileptic seizure is reported to be approximately 40%. Little is known about the recurrence risk after a first seizure in elderly patients, who may be at higher risk due to an increased rate of structural lesions, encephalopathy, subcortical arteriosclerotic encephalopathy or brain atrophy. METHODS: In a retrospective approach, the recurrence rate in 304 patients aged 60 years and above who presented with a first seizure between 2004 and 2017 was analyzed. Hierarchical Cox regression was used to investigate the impact of EEG and neuroimaging results, age or the prescription of anti-seizure medication (ASM) on seizure recurrence. RESULTS: Seizure recurrence rates were 24.5% and 34.4% after one and two years, respectively. Anti-seizure medication was started in 87.8% of patients, in 28.8% despite the absence of clear epileptogenic lesions on neuroimaging or epileptiform potentials in the EEG. Medical treatment significantly reduced the risk of recurrence (hazard ratio = 0.47). Epileptiform potentials in the EEG, epileptogenic lesions in neuroimaging and age had no significant effect on seizure recurrence. Age and the presence of neurodegenerative and psychiatric comorbidities showed a significant association with ASM prescription. CONCLUSIONS: The present data show a strong protective effect of ASM on seizure recurrence in patients above the age of 60, even in the absence of pathologic neuroimaging or EEG results needed for the diagnosis of epilepsy. Treatment with ASM therefore seems beneficial for reducing the recurrence risk in elderly patients. The lack of a significant association between seizure recurrence and epileptogenic lesions might be related to other confounding factors like encephalopathy, subcortical arteriosclerotic encephalopathy, neurodegenerative diseases or brain atrophy.