Brain connectivity analysis in preictal phases of seizure induced by pentylenetetrazol in rats.

Abnormal patterns of brain connectivity characterize epilepsy. However, little is known about these patterns during the stages preceding a seizure induced by pentylenetetrazol (PTZ). To investigate brain connectivity in male Wistar rats during the preictal phase of PTZ-induced seizures (60 mg/kg), we recorded local field potentials in the primary motor (M1) cortex, the ventral anterior (VA) nucleus of the thalamus, the hippocampal CA1 area, and the dentate gyrus (DG) during the baseline period and after PTZ administration. While there were no changes in power density between the baseline and preictal periods, we observed an increase in directional functional connectivity in theta from the hippocampal formation to M1 and VA, as well as in middle gamma from DG to CA1 and from CA1 to M1, and also in slow gamma from M1 to CA1. These findings are supported by increased phase coherence between DG-M1 in theta and CA1-M1 in middle gamma, as well as enhanced phase-amplitude coupling of delta-middle gamma in M1 and delta-fast gamma in CA1. Interestingly, we also noted a slight decrease in phase synchrony between CA1 and VA in slow gamma. Together, these results demonstrate increased functional connectivity between brain regions during the PTZ-induced preictal period, with this increase being particularly driven by the hippocampal formation.

EpilepIndex: A novel feature engineering tool to detect epilepsy using EEG signals.

Epilepsy is a common neurological disease characterized by seizures. A person with a seizure onset can lose consciousness which in turn can lead to fatal accidents. Electroencephalogram (EEG) is a recording of the electrical signals from the brain which is used to analyse the epileptic seizures. Physical visual examination of the EEG by trained neurologists is subjective and highly difficult due to the non-linear complex nature of the EEG. This opens a window for automatic detection of epileptic seizures using machine learning methods. In this work, we have used a standard database that consists of five different sets of EEG data including the epileptic EEG. Using this data, we have devised a novel 22 possible clinically significant cases with the combination of binary and multi class type of classification problem to automatically classify epileptic EEG. As the EEG is non-linear, we have devised 11 statistically significant non-linear entropy features to extract from this database. These features are fed to 10 different classifiers of various types for each of the 22 clinically significant cases and their classification accuracy is reported for 10-fold cross validation. Random Forest and Optimized Forest classifiers reported accuracies above 90% for all 22 cases considered in this study. Such vast possible clinically significant 22 cases from the combination of the data from the database considered has not been in the literature with the best of the knowledge of the authors. Comparing with the literature, several studies have presented one or few combinations of these 22 cases in this work. In comparison to similar works, the accuracies obtained by the classifiers were highly competitive. In addition, a novel integrated epilepsy detection index named EpilepIndex (IED) is able to differentiate between epileptic EEG and a normal EEG with 100% accuracy.

Peri-ictal heart rate changes in patients with epilepsy.

Background: Heart rate (HR) changes associated with seizures are promising biomarkers in epilepsy. Aims: The aim of our study is to reveal possible HR changes in the peri-ictal period. Methods: Long-term video-EEG monitorization records of generalized and focal epilepsy patients were reviewed. HRs were calculated in the pre-ictal (2 min before the first seizure activity in EEG), ictal (the time from the first seizure activity on the EEG to the end of the seizure), and in the interictal period (at least 2 h before or 12 h after the seizure). Interictal, pre-ictal, and ictal HRs were compared with each other. In addition, it was investigated whether peri-ictal HR changes differ between generalized and focal seizure patients. Results: Focal motor seizures were observed in 21, and generalized tonic-clonic seizures were observed in 18 of 39 (22 female and 17 male) patients studied. HRs in the pre-ictal and ictal periods were significantly higher than in the interictal period. This significant increase in HR was validated separately in both focal and generalized seizure groups and was not different between the two groups. Conclusion: Our study supports previous studies showing the presence of increased peri-ictal HR and also provides new insights by comparing focal and generalized motor seizures. We think that our findings may contribute to the development of early warning signs in epilepsy patients.

Ipsilateral preictal alpha rhythm attenuation (IPARA): An EEG sign of side of seizure onset in temporal lobe epilepsy.

PURPOSE: Identification of the seizure onset zone is critically important for outlining the surgical plan in the treatment of pharmacoresistant focal epilepsy. In patients with temporal lobe epilepsy (TLE), bilateral ictal scalp EEG changes frequently occur and can make lateralization of the seizure onset zone difficult. We investigated the incidence and clinical utility of unilateral preictal alpha rhythm attenuation as a lateralizing sign of seizure onset in TLE. METHODS: Scalp EEG recordings of the seizures acquired during presurgical video-EEG monitoring of 57 consecutive patients with TLE were reviewed retrospectively. Included patients had interictal baseline recordings demonstrating symmetrical posterior alpha rhythm and seizures occurring during wakefulness. RESULTS: We identified a total of 649 seizures in the 57 patients, of which 448 seizures in 53 patients fulfilled the inclusion criteria. Among the 53 included patients, 7 patients (13.2%) exhibited a distinct attenuation of the posterior alpha rhythm prior to the first ictal EEG changes, in 26 of 112 (23.2%) included seizures. Preictal alpha rhythm attenuation in these seizures was ipsilateral to the ultimately determined side of seizure onset (based on video-EEG or intracranial EEG findings) in 22 (84.6%) of these seizures and bilateral in 4 (15.4%), and occurred on average 5.9 ± 2.6 s prior to ictal EEG onsets. CONCLUSION: Our findings suggest that in some patients with TLE lateralized preictal attenuation of the posterior alpha rhythm may be a useful indicator of side of seizure onset, presumably due to early disruption of thalamo-temporo-occipital network function, likely mediated through the thalamus.

Patient-Specific Preictal Pattern-Aware Epileptic Seizure Prediction with Federated Learning.

Electroencephalography (EEG) signals are the primary source for discriminating the preictal from the interictal stage, enabling early warnings before the seizure onset. Epileptic siezure prediction systems face significant challenges due to data scarcity, diversity, and privacy. This paper proposes a three-tier architecture for epileptic seizure prediction associated with the Federated Learning (FL) model, which is able to achieve enhanced capability by utilizing a significant number of seizure patterns from globally distributed patients while maintaining data privacy. The determination of the preictal state is influenced by global and local model-assisted decision making by modeling the two-level edge layer. The Spiking Encoder (SE), integrated with the Graph Convolutional Neural Network (Spiking-GCNN), works as the local model trained using a bi-timescale approach. Each local model utilizes the aggregated seizure knowledge obtained from the different medical centers through FL and determines the preictal probability in the coarse-grained personalization. The Adaptive Neuro-Fuzzy Inference System (ANFIS) is utilized in fine-grained personalization to recognize epileptic seizure patients by examining the outcomes of the FL model, heart rate variability features, and patient-specific clinical features. Thus, the proposed approach achieved 96.33% sensitivity and 96.14% specificity when tested on the CHB-MIT EEG dataset when modeling was performed using the bi-timescale approach and Spiking-GCNN-based epileptic pattern learning. Moreover, the adoption of federated learning greatly assists the proposed system, yielding a 96.28% higher accuracy as a result of addressing data scarcity.

Pre-ictal fluctuation of EEG functional connectivity discriminates seizure phenotypes in mesial temporal lobe epilepsy.

OBJECTIVE: We explored whether quantifiable differences between clinical seizures (CSs) and subclinical seizures (SCSs) occur in the pre-ictal state. METHODS: We analyzed pre-ictal stereo-electroencephalography (SEEG) retrospectively across mesial temporal lobe epilepsy patients with recorded CSs and SCSs. Power spectral density and functional connectivity (FC) were quantified within and between the seizure onset zone (SOZ) and the early propagation zone (PZ), respectively. To evaluate the fluctuation of neural connectivity, FC variability was computed. Measures were further verified by a logistic regression model to evaluate their classification potentiality through the area under the receiver-operating-characteristics curve (AUC). RESULTS: Fifty-four pre-ictal SEEG epochs (27 CSs and 27 SCSs) were selected among 14 patients. Within the SOZ, pre-ictal FC variability of CSs was larger than SCSs in 1-45 Hz during 30 seconds before seizure onset. Pre-ictal FC variability between the SOZ and PZ was larger in SCSs than CSs in 55-80 Hz within 1 minute before onset. Using these two variables, the logistic regression model achieved an AUC of 0.79 when classifying CSs and SCSs. CONCLUSIONS: Pre-ictal FC variability within/between epileptic zones, not signal power or FC value, distinguished SCSs from CSs. SIGNIFICANCE: Pre-ictal epileptic network stability possibly marks seizure phenotypes, contributing insights into ictogenesis and potentially helping seizure prediction.

Insufficient sleep may alter cortical excitability near the migraine attack: A blinded TMS crossover study.

BACKGROUND: Migraine is a brain disorder with a multifaceted and unexplained association to sleep. Brain excitability likely changes periodically throughout the migraine cycle. In this study we examine the effect of insufficient sleep on neuronal excitability during the course of the migraine cycle. METHODS: We examined 54 migraine patients after two nights of eight-hour habitual sleep and two nights of four-hour restricted sleep in a randomised, blinded crossover study. We performed transcranial magnetic stimulation and measured cortical silent period, short- and long-interval intracortical inhibition, intracortical facilitation and short-latency afferent inhibition. We analysed how responses changed before and after attacks with linear mixed models. RESULTS: Short- interval intracortical inhibition was more reduced after sleep restriction compared to habitual sleep the shorter the time that had elapsed since the attack (p = 0.041), and specifically in the postictal phase (p = 0.013). Long-interval intracortical inhibition was more increased after sleep restriction with time closer before the attack (p = 0.006), and specifically in the preictal phase (p = 0.034). Short-latency afferent inhibition was more decreased after sleep restriction with time closer to the start of the attack (p = 0.026). CONCLUSION: Insufficient sleep in the period leading up to a migraine attack may cause dysfunction in cortical GABAergic inhibition. The results also suggest that migraine patients may have increased need for sufficient sleep during a migraine attack to maintain normal neurological function after the attack.

Effects of insufficient sleep on sensorimotor processing in migraine: A randomised, blinded crossover study of event related beta oscillations.

BACKGROUND: Migraine has a largely unexplained connection with sleep and is possibly related to a dysfunction of thalamocortical systems and cortical inhibition. In this study we investigate the effect of insufficient sleep on cortical sensorimotor processing in migraine. METHODS: We recorded electroencephalography during a sensorimotor task from 46 interictal migraineurs and 28 controls after two nights of eight-hour habitual sleep and after two nights of four-hour restricted sleep. We compared changes in beta oscillations of the sensorimotor cortex after the two sleep conditions between migraineurs, controls and subgroups differentiating migraine subjects usually having attacks starting during sleep and not during sleep. We included preictal and postictal recordings in a secondary analysis of temporal changes in relation to attacks. RESULTS: Interictally, we discovered lower beta synchronisation after sleep restriction in sleep related migraine compared to non-sleep related migraine (p=0.006) and controls (p=0.01). No differences were seen between controls and the total migraine group in the interictal phase. After migraine attacks, we observed lower beta synchronisation (p<0.001) and higher beta desynchronisation (p=0.002) after sleep restriction closer to the end of the attack compared to later after the attack. CONCLUSION: The subgroup with sleep related migraine had lower sensorimotor beta synchronisation after sleep restriction, possibly related to dysfunctional GABAergic inhibitory systems. Sufficient sleep during or immediately after migraine attacks may be of importance for maintaining normal cortical excitability.

Prostaglandin-E2 levels over the course of glyceryl trinitrate provoked migraine attacks.

Administration of glyceryl trinitrate (GTN), a donor of nitric oxide, can induce migraine-like attacks in subjects with migraine. Provocation with GTN typically follows a biphasic pattern; it induces immediate headache in subjects with migraine, as well as in healthy controls, whereafter only subjects with migraine may develop a migraine-like headache several hours later. Interestingly, intravenous infusion with prostaglandin-E2 (PGE2) can also provoke a migraine-like headache, but seems to have a more rapid onset compared to GTN. The aim of the study was to shed light on the mechanistic aspect PGE2 has in migraine attack development. Therefore, PGE2 plasma levels were measured towards the (pre)ictal state of an attack, which we provoked with GTN. Blood samples from women with migraine (n = 37) and age-matched female controls (n = 25) were obtained before and âˆ¼ 140 min and âˆ¼ 320 min after GTN infusion. PGE2 levels were measured using liquid chromatography tandem mass spectrometry (LC-MS/MS) analysis. Data was analyzed using a generalized linear mixed-effect model. Immediate headache after GTN infusion occurred in 85 % of migraine participants and in 75 % of controls. A delayed onset migraine-like attack was observed in 82 % of migraine subjects and in none of the controls. PGE2 levels were not different between the interictal and preictal state (P = 0.527) nor between interictal and ictal state (defined as having migraine-like headache) (P = 0.141). Hence, no evidence was found that a rise in PGE2 is an essential step in the initiation of GTN-induced migraine-like attacks.

A multi-frame network model for predicting seizure based on sEEG and iEEG data.

Introduction: Analysis and prediction of seizures by processing the EEG signals could assist doctors in accurate diagnosis and improve the quality of the patient's life with epilepsy. Nowadays, seizure prediction models based on deep learning have become one of the most popular topics in seizure studies, and many models have been presented. However, the prediction results are strongly related to the various complicated pre-processing strategies of models, and cannot be directly applied to raw data in real-time applications. Moreover, due to the inherent deficiencies in single-frame models and the non-stationary nature of EEG signals, the generalization ability of the existing model frameworks is generally poor. Methods: Therefore, we proposed an end-to-end seizure prediction model in this paper, where we designed a multi-frame network for automatic feature extraction and classification. Instance and sequence-based frames are proposed in our approach, which can help us simultaneously extract features of different modes for further classification. Moreover, complicated pre-processing steps are not included in our model, and the novel frames can be directly applied to the raw data. It should be noted that the approaches proposed in the paper can be easily used as the general model which has been validated and compared with existing model frames. Results: The experimental results showed that the multi-frame network proposed in this paper was superior to the existing model frame in accuracy, sensitivity, specificity, F1-score, and AUC in the classification performance of EEG signals. Discussion: Our results provided a new research idea for this field. Researchers can further integrate the idea of the multi-frame network into the state-of-the-art single-frame seizure prediction models and then achieve better results.

Reduction of Hippocampal High-Frequency Activity in Wag/Rij Rats with a Genetic Predisposition to Absence Epilepsy.

In temporal lobe epilepsy, high frequency oscillations serve as electroencephalographic (EEG) markers of epileptic hippocampal tissue. In contrast, absence epilepsy and other idiopathic epilepsies are known to result from thalamo-cortical abnormalities, with the hippocampus involvement considered to be only indirect. We aimed to uncover the role of the hippocampus in absence epilepsy using a genetic rat model of absence epilepsy (WAG/Rij rats), in which spike-wave discharges (SWDs) appear spontaneously in cortical EEG. We performed simultaneous recordings of local field potential from the hippocampal dentate gyrus using pairs of depth electrodes and epidural cortical EEG in freely moving rats. Hippocampal ripples (100-200 Hz) and high frequency oscillations (HFO, 50-70 Hz) were detected using GUI RIPPLELAB in MatLab (Navarrete et al., 2016). Based on the dynamics of hippocampal ripples, SWDs were divided into three clusters, which might represent different seizure types in reference to the involvement of hippocampal processes. This might underlie impairment of hippocampus-related cognitive processes in some patients with absence epilepsy. A significant reduction to nearly zero-ripple-density was found 4-8 s prior to SWD onset and during 4 s immediately after SWD onset. It follows that hippocampal ripples were not just passively blocked by the onset of SWDs, but they were affected by spike-wave seizure initiation mechanisms. Hippocampal HFO were reduced during the preictal, ictal and postictal periods in comparison to the baseline. Therefore, hippocampal HFO seemed to be blocked with spike-wave seizures. All together, this might underlie impairment of hippocampus-related cognitive processes in some patients with absence epilepsy. Further investigation of processes underlying SWD-related reduction of hippocampal ripples and HFO oscillations may help to predict epileptic attacks and explain cognitive comorbidities in patients with absence epilepsy.

Quantitative Analysis of Inter- and Intrahemispheric Coherence on Epileptic Electroencephalography Signal.

When an epileptic seizure occurs, the neuron's activity of the brain is dynamically changed, which affects the connectivity between brain regions. The connectivity of each brain region can be quantified by electroencephalography (EEG) coherence, which measures the statistical correlation between electrodes spatially separated on the scalp. Previous studies conducted a coherence analysis of all EEG electrodes covering all parts of the brain. However, in an epileptic condition, seizures occur in a specific region of the brain then spreading to other areas. Therefore, this study applies an energy-based channel selection process to determine the coherence analysis in the most active brain regions during the seizure. This paper presents a quantitative analysis of inter- and intrahemispheric coherence in epileptic EEG signals and the correlation with the channel activity to glean insights about brain area connectivity changes during epileptic seizures. The EEG signals are obtained from ten patients' data from the CHB-MIT dataset. Pair-wise electrode spectral coherence is calculated in the full band and five sub-bands of EEG signals. The channel activity level is determined by calculating the energy of each channel in all patients. The EEG coherence observation in the preictal (Cohpre ) and ictal (Cohictal ) conditions showed a significant decrease of Cohictal in the most active channel, especially in the lower EEG sub-bands. This finding indicates that there is a strong correlation between the decrease of mean spectral coherence and channel activity. The decrease of coherence in epileptic conditions (Cohictal

Hyperventilation in functional seizures: Evidence for subtypes.

PURPOSE: Functional seizures (FS) are heterogenous, with no agreed way to subdivide them. One FS subtype frequently observed during EEG is those whose seizures are provoked by hyperventilation. We wished to see whether this subtype might reflect a different seizure mechanism. METHODS: We analysed the video-EEG/ECGs of all patients with FS from two hospitals in Melbourne from 2010-6. RESULTS: We identified 120 patients during the study period, 107 of whom had usable recordings. Examining those 11 (10%) whose seizures had been induced by hyperventilation, we compared the heart rates of those where the seizure occurred during the hyperventilation, and those where they occurred afterwards. The during-hyperventilation group had a higher baseline heart rate which increased prior to their seizure; the after-hyperventilation group had a lower baseline heart rate and no pre-ictal increase. In those patients whose seizures were not hyperventilation-induced, the same two heart rate patterns could be found: those with a higher baseline heart rate showed increasing heart rate prior to seizure onset, while those with a lower baseline heart rate did not. Cluster analysis showed the sample was optimally divided into these two groups based on their pre-onset heart rate alone. CONCLUSION: Patients with FS show two distinct patterns of pre-ictal heart rate, which may reflect two distinct seizure mechanisms.

Silencing of Hippocampal Somatostatin Interneurons Induces Recurrent Spontaneous Limbic Seizures in Mice.

The hippocampus proper and the subiculum contain two major populations of somatostatin (SST)-containing interneurons, oriens-lacunosum moleculare (O-LM) cells projecting from the stratum oriens to the stratum lacunosum moleculare and bistratified cells with their cell bodies close to the pyramidal cell layer and axons terminating in the strata radiatum and oriens. Both types of interneurons innervate pyramidal cell dendrites and exert prominent feedback inhibition. We now investigated whether impairing this type of feed-back inhibition by selectively inhibiting GABA release from SST expressing interneurons in hippocampal sector CA1 and subiculum may be sufficient to induce spontaneous recurrent seizures. We injected transgenic mice expressing Cre-recombinase on the SST promoter unilaterally into the ventral CA1 sector and subiculum with an adeno-associated viral (AAV) vector expressing tetanus toxin light chain (TeLC) with its reading frame inverted in a flip-excision (FLEX) cassette. This treatment resulted in specific expression of TeLC and silencing of SST-containing interneurons. We continuously monitored the EEG and behavior of the mice for six weeks. Nine out of eleven mice within 10 days developed series of pre- or interictal spikes (IS, 21.4 ± 6.83 per week) and four mice exposed recurrent spontaneous seizures (SRS, 1.5 ± 0.29 per week). All 23 SRS observed were preceded by IS series. Our data demonstrate a critical role of feed-forward inhibition mediated by SST-containing interneurons suggesting that their sustained malfunctioning can be causatively involved in the development of TLE.

Peri-Ictal and Para-Ictal Psychiatric Phenomena: A Relatively Common Yet Unrecognized Disorder.

Patients with epilepsy can experience different neuropsychiatric symptoms related (peri-ictal) or not (interictal) with seizures. Peri-ictal symptoms can precede (pre-ictal) or follow (post-ictal) the seizure, or even be the expression of the seizure activity (ictal). Neuropsychiatric symptoms, such as irritability and apathy, are among the most frequent pre-ictal manifestations. Ictal fear is reported by around 10% of patients with focal seizures, and sometimes can be difficult to differentiate from panic attacks. Post-ictal anxiety, mood and psychotic symptoms are also frequently reported by patients. Peri-ictal phenomena can occur as isolated symptom or as a cluster of symptoms, sometimes resembling a full-blown psychiatric syndrome. Actually, peri-ictal and interictal neuropsychiatric manifestations seem to be closely associated.

PV-specific loss of the transcriptional coactivator PGC-1α slows down the evolution of epileptic activity in an acute ictogenic model.

The transcriptional coactivator, PGC-1α (peroxisome proliferator-activated receptor γ coactivator 1α), plays a key role in coordinating energy requirement within cells. Its importance is reflected in the growing number of psychiatric and neurological conditions that have been associated with reduced PGC-1α levels. In cortical networks, PGC-1α is required for the induction of parvalbumin (PV) expression in interneurons, and PGC-1α deficiency affects synchronous GABAergic release. It is unknown, however, how this affects cortical excitability. We show here that knocking down PGC-1α specifically in the PV-expressing cells (PGC-1αPV-/-) blocks the activity-dependent regulation of the synaptic proteins, SYT2 and CPLX1. More surprisingly, this cell class-specific knockout of PGC-1α appears to have a novel antiepileptic effect, as assayed in brain slices bathed in 0 Mg2+ media. The rate of occurrence of preictal discharges developed approximately equivalently in wild-type and PGC-1αPV-/- brain slices, but the intensity of these discharges was lower in PGC-1αPV-/- slices, as evident from the reduced power in the γ range and reduced firing rates in both PV interneurons and pyramidal cells during these discharges. Reflecting this reduced intensity in the preictal discharges, the PGC-1αPV-/- brain slices experienced many more discharges before transitioning into a seizure-like event. Consequently, there was a large increase in the latency to the first seizure-like event in brain slices lacking PGC-1α in PV interneurons. We conclude that knocking down PGC-1α limits the range of PV interneuron firing and this slows the pathophysiological escalation during ictogenesis.NEW & NOTEWORTHY Parvalbumin expressing interneurons are considered to play an important role in regulating cortical activity. We were surprised, therefore, to find that knocking down the transcriptional coactivator, PGC-1α, specifically in this class of interneurons appears to slow ictogenesis. This anti-ictogenic effect is associated with reduced activity in preictal discharges, but with a far longer period of these discharges before the first seizure-like events finally start. Thus, PGC-1α knockdown may promote schizophrenia while reducing epileptic tendencies.

Detection of preictal state in epileptic seizures using ensemble classifier.

OBJECTIVE: Epilepsy affected patient experiences more than one frequency seizures which can not be treated with medication or surgical procedures in 30% of the cases. Therefore, an early prediction of these seizures is inevitable for these cases to control them with therapeutic interventions. METHODS: In recent years, researchers have proposed multiple deep learning based methods for detection of preictal state in electroencephalogram (EEG) signals, however, accurate detection of start of preictal state remains a challenge. We propose a novel ensemble classifier based method that gets the comprehensive feature set as input and combines three different classifiers to detect the preictal state. RESULTS: We have applied the proposed method on the publicly available scalp EEG dataset CHBMIT of 22 subjects. An average accuracy of 94.31% with sensitivity and specificity of 94.73% and 93.72% respectively has been achieved with the method proposed in this study. CONCLUSIONS: Proposed study utilizes the preprocessing techniques for noise removal, combines deep learning based and handcrafted features and an ensemble classifier for detection of start of preictal state. Proposed method gives better results in terms of accuracy, sensitivity, and specificity.

A deep learning based ensemble learning method for epileptic seizure prediction.

In epilepsy, patients suffer from seizures which cannot be controlled with medicines or surgical treatments in more than 30% of the cases. Prediction of epileptic seizures is extremely important so that they can be controlled with medication before they actually occur. Researchers have proposed multiple machine/deep learning based methods to predict epileptic seizures; however, accurate prediction of epileptic seizures with low false positive rate is still a challenge. In this research, we propose a deep learning based ensemble learning method to predict epileptic seizures. In the proposed method, EEG signals are preprocessed using empirical mode decomposition followed by bandpass filtering for noise removal. The class imbalance problem has been mitigated with synthetic preictal segments generated using generative adversarial networks. A three-layer customized convolutional neural network has been proposed to extract automated features from preprocessed EEG signals and combined them with handcrafted features to get a comprehensive feature set. The feature set is then used to train an ensemble classifier that combines the output of SVM, CNN and LSTM using Model agnostic meta learning. An average sensitivity of 96.28% and specificity of 95.65% with an average anticipation time of 33 min on all subjects of CHBMIT has been achieved by the proposed method, whereas, on American epilepsy society-Kaggle seizure prediction dataset, an average sensitivity of 94.2% and specificity of 95.8% has been achieved on all subjects.

Pre- and Postictal Changes in the Innate Immune System: Cause or Effect?

INTRODUCTION: Recent studies have shown that inflammatory processes might play a role in epileptogenesis. Their role in ictogenesis is much less clear. The aim of this study was to investigate peri-ictal changes of the innate immune system by analyzing changes of immune cells, as well as pro- and anti-inflammatory cytokines. METHODS: Patients with active epilepsy admitted for video-EEG monitoring for presurgical evaluation were included. Blood was sampled every 20 min for 5 h on 3 consecutive days until a seizure occurred. After a seizure, additional samples were drawn immediately, as well as 1 and 24 h later. To analyze the different populations of peripheral blood mononuclear cells, all samples underwent FACS for CD3, CD4, CD8, CD56, CD14, CD16, and CD19. For cytokine analysis, we used a custom bead-based multiplex immunoassay for IFN-γ, IL-1ß, IL-1RA, IL-4, IL-6, IL-10, IL-12, IL-17, MCP-1, MIP-1α, and TNFα. RESULTS: Fourteen patients with focal seizures during the sampling period were included. Natural killer (NK) cells showed a negative correlation (ρ = -0.3362, p = 0.0195) before seizure onset and an immediate increase to 1.95-fold afterward. T helper (TH) and B cells decreased by 2 and 8%, respectively, in the immediate postictal interval. Nonclassical and intermediate monocytes decreased not until 1 day after the seizures, and cytotoxic T (TC) cells showed a long-lasting postictal increase by 4%. IL-10 and MCP-1 increased significantly after seizures, and IL-12 decreased in the postictal phase. DISCUSSION/CONCLUSION: Our study argues for a role of the innate immune system in the pre- and postictal phases. NK cells might be involved in preictal changes or be altered as an epiphenomenon in the immediate preictal interval.

Psychoses of Epilepsy in Pregnancy: A Case Report.

To discuss the unique relationship between psychosis and seizures in a young individual, who is also pregnant. Psychosis of epilepsy can present in multitude of ways, including pre-ictal, ictal, post-ictal, chronic interictal, and forced normalization psychosis.