EEG Seizure Research Articles

Early MRI changes in status epilepticus: Associations with seizure characteristics, EEG findings, and prognosis in patients without large lesions.

To investigate the role, frequency, and pattern of signal changes in cranial MRI associated with status epilepticus (SE) and their correlation with EEG and clinical findings in patients with large lesions, such as tumors, strokes, or major space-occupying anomalies. This retrospective cohort study included 44 patients diagnosed with SE between January 2013 and June 2019. Data on demographic and clinical characteristics, seizure semiology, SE features (type and prognosis), and EEG and MRI findings were collected from hospital records. The relationships between periictal MRI abnormalities, MRI lateralization, clinical semiology, EEG findings, SE prognosis, and outcome at discharge were analyzed. The median age of participants was 61.5 years, with 65.91% being female. Bilateral MRI signals were significantly more common in patients with generalized convulsive SE. Patients with SWI signal changes had a significantly lower median age and a higher percentage of previous epilepsy history. Increased signal intensity on DWI and T2-FLAIR sequences was observed in 86.4% and 22.7% of patients, respectively. Among those with increased DWI signals, the neocortex was a common localization (45.45%). The group with T2-FLAIR signal increases had a significantly lower median age, a higher percentage of generalized convulsive SE, and a lower percentage of non-convulsive SE. Poor prognosis was observed in 40.91% of patients, with generalized EEG findings significantly more frequent in this group. Periictal MRI findings in SE patients demonstrated significant associations with clinical presentation but showed no correlation with EEG or prognosis. Further research is needed to explore the link between MRI findings and SE prognosis in the acute phase.

Predisposing Factors of Progression from Refractory Status Epilepticus to Super-Refractory Status Epilepticus in ICU-Admitted Patients: Multicenter Retrospective Cohort Study in a Resource-Limited Setting.

Super-refractory status epilepticus (SRSE) is an extremely serious neurological emergency. Risk factors and mechanisms involved in transition from refractory status epilepticus (RSE) to SRSE are insufficiently studied. This was a multicenter retrospective cohort study of consecutive patients diagnosed and treated for RSE at two reference hospital over 5years in Ecuador. A total of 140 patients were included. Potential demographic, clinical, and treatment variables that may predict progression from refractory to SRSE were analyzed. Super-refractory status epilepticus was identified in 67/140 (48%) of patients. In univariate analyses, level of consciousness on hospital admission (Glasgow Coma Score < 12, odds ratio [OR] 2.9, p < 0.01), traumatic brain injury (OR 2.3, p = 0.05), acute etiology (OR 3.0, p = 0.04), higher Status Epilepticus Severity Score (STESS) (OR 1.7, p < 0.01), and new clinical or electrographic seizure within 6h (OR 4.2, p < 0.01) of starting anesthetic infusion were important factors related to super-refractory disease. The best independents predictors of SRSE when the presence of other potential factors were considered for multivariate analysis. Two models were calculated to avoid interactions between similar variables. Glasgow Coma Score on hospital admission < 12 (OR 3.1 [95% confidence interval {CI} 1.16-8.29], p = 0.02) and new clinical or electroencephalography (EEG) seizure after first 6h of starting anesthetic infusion (OR 3.1 [95% CI 1.36-7.09], p = 0.01) were associated with higher risk of progression to SRSE in model 1. In contrast, model 2 indicated that patients with STESS ≥ 3 points (OR 2.9 [95% CI 1.24-6.65], p = 0.01) and new clinical or EEG seizure after 6h starting anesthetic infusion (OR 3.0 [95% CI 1.32-6.97], p = 0.01) were the factors independentlyrelated to super-refractory disease. The rate of patients with RSE admitted to intensive care units developing SRSE was high. Low level of consciousness on admission, higher STESS scores, and patients who did not achieve total control of clinical or EEG seizure in the first 6h of starting intravenous anesthetic infusion may be early indicators of SRSE.

Prediction of Pharmacoresistance in Drug-Naïve Temporal Lobe Epilepsy Using Ictal EEGs Based on Convolutional Neural Network.

Approximately 30%-40% of epilepsy patients do not respond well to adequate anti-seizure medications (ASMs), a condition known as pharmacoresistant epilepsy. The management of pharmacoresistant epilepsy remains an intractable issue in the clinic. Its early prediction is important for prevention and diagnosis. However, it still lacks effective predictors and approaches. Here, a classical model of pharmacoresistant temporal lobe epilepsy (TLE) was established to screen pharmacoresistant and pharmaco-responsive individuals by applying phenytoin to amygdaloid-kindled rats. Ictal electroencephalograms (EEGs) recorded before phenytoin treatment were analyzed. Based on ictal EEGs from pharmacoresistant and pharmaco-responsive rats, a convolutional neural network predictive model was constructed to predict pharmacoresistance, and achieved 78% prediction accuracy. We further found the ictal EEGs from pharmacoresistant rats have a lower gamma-band power, which was verified in seizure EEGs from pharmacoresistant TLE patients. Prospectively, therapies targeting the subiculum in those predicted as "pharmacoresistant" individual rats significantly reduced the subsequent occurrence of pharmacoresistance. These results demonstrate a new methodology to predict whether TLE individuals become resistant to ASMs in a classic pharmacoresistant TLE model. This may be of translational importance for the precise management of pharmacoresistant TLE.

Ictal EEG of benign convulsion with mild gastroenteritis with in infants and children.

There are fewer reports on the ictal electroencephalogram(EEG) of convulsions in infants and children with mild gastroenteritis (BCWG). Our study retrospectively analyzed the ictal EEG characteristics of convulsive episodes of BCWG. The seizure-phase EEGs of children diagnosed with BCWG from September 2016 to January 2022 were searched and analyzed, and a total of thirteen seizure-phase EEGs of eight cases were analyzed retrospectively. The age of onset of the disease in the eight children ranged from one year to two years and seven months. No epileptiform discharges were found during the interictal EEG. A total of thirteen epileptic seizures were monitored, of which nine were focal with secondary generalisation. Scalp EEG showed three onset of EEG seizures were in the right occipital region, two were in the right parietal and occipital regions, one was in the right parietal, occipital and posterior temporal region, one was in the right posterior temporal region, one was in the right occipital and posterior temporal region and one was in the right central and central midline region. In addition, four non-convulsive epileptic seizures, which manifested themselves as a decrease in movement and consciousness, with local δ slow-wave activity in bilateral occipital regions evolved to diffuse δ slow wave activity in epileptic seizures. Focal secondary generalised tonic clonic seizures were the main type of seizures in BCWG, and the seizure onset may been mostly in posterior cephalic cortex. It was previously unreported that some children of BCWG may combine with non-convulsive epileptic seizures with the onset of slow wave activity in the occipital region bilaterally and evolving into diffuse δ slow wave activity, which was not easily detected by parents and clinicians.

A Case of Asymmetric Seizure Termination During an Acute Course of Right Unilateral Electroconvulsive Therapy.

Electroencephalogram (EEG) monitoring during electroconvulsive therapy (ECT) is commonly done using a 2-channel EEG in order to capture activity from both brain hemispheres, though many institutions may instead opt to utilize a 1-channel EEG, often for reasons of convenience. We present a novel case of asymmetric termination of EEG seizure activity during an acute course of right unilateral ECT, prompting a full neurological workup to investigate potential underlying structural or physiological causative factors. This case assists in informing the necessity of bilateral hemispheric EEG monitoring as well as highlights the importance of searching for undiagnosed or latent neurological dysfunction in certain clinical situations arising during ECT.

Epilepsy EEG Seizure Prediction Based on the Combination of Graph Convolutional Neural Network Combined with Long- and Short-Term Memory Cell Network

With the increasing research of deep learning in the EEG field, it becomes more and more important to fully extract the characteristics of EEG signals. Traditional EEG signal classification prediction neither considers the topological structure between the electrodes of the signal collection device nor the data structure of the Euclidean space to accurately reflect the interaction between signals. Graph neural networks can effectively extract features of non-Euclidean spatial data. Therefore, this paper proposes a feature selection method for epilepsy EEG classification based on graph convolutional neural networks (GCNs) and long short-term memory (LSTM) cells. While enriching the input of LSTM, it also makes full use of the information hidden in the EEG signals. In the automatic detection of epileptic seizures based on neural networks, due to the strong non-stationarity and large background noise of the EEG signal, the analysis and processing of the EEG signal has always been a challenging research. Therefore, experiments were conducted using the preprocessed Boston Children’s Hospital epilepsy EEG dataset, and input it into the GCN-LSTM model for deep feature extraction. The GCN network built by the graph convolution layer learns spatial features, then LSTM extracts sequence information, and the final prediction is performed by fully connected and softmax layers. The introduced method has been experimentally proven to be effective in improving the accuracy of epileptic EEG seizure detection. Experimental results show that the average accuracy of binary classification on the CHB-MIT dataset is 99.39%, and the average accuracy of ternary classification is 98.69%.

Digital Twin for EEG seizure prediction using time reassigned Multisynchrosqueezing transform-based CNN-BiLSTM-Attention mechanism model

The prediction of epileptic seizures is a classical research problem, representing one of the most challenging tasks in the analysis of brain disorders. There is active research into digital twins (DT) for various healthcare applications, as they can transform research into customized and personalized healthcare. The widespread adoption of DT technology relies on ample patient data to ensure precise monitoring and decision-making, leveraging Machine Learning (ML) and Deep Learning (DL) algorithms. Given the non-stationarity of EEG recordings, characterized by substantial frequency variations over time, there is a notable preference for advanced time-frequency methods in seizure prediction. This research proposes a DT-based seizure prediction system by applying an advanced time-frequency analysis approach known as Time-Reassigned MultiSynchroSqueezing Transform (TMSST) to EEG data to extract patient-specific impulse features and subsequently, a Deep Learning strategy, CNN-BiLSTM-Attention mechanism model is utilized in learning and classifying features for seizure prediction. The proposed architecture is named as 'Digital Twin-Net'. By estimating the group delay in the time direction, TMSST produces the frequency components that are responsible for the EEG signal's temporal behavior and those time-frequency signatures are learned by the developed CNN-BiLSTM-Attention mechanism model. Thus the combination acts as a digital twin of a patient for the prediction of epileptic seizures. The experimental results showed that the suggested approach achieved an accuracy of 99.70% when tested on 22 patients from the publicly accessible CHB-MIT dataset. The proposed method surpasses previous solutions in terms of overall performance. Consequently, the suggested method can be regarded as an efficient approach to EEG seizure prediction.

EEG background activity, seizure burden and early childhood outcomes in neonatal encephalopathy in Uganda: a prospective feasibility cohort study

Intrapartum-related neonatal encephalopathy (NE) is a leading cause of childhood mortality and morbidity. Continuous electroencephalography (EEG) is gold standard for neonatal brain monitoring; however, low-income country data is lacking. We examined EEG in a Ugandan cohort with NE to describe feasibility, background activity, seizure prevalence and burden, and associations with clinical presentation and outcome. Neonates with NE were recruited from a single hospital referral centre in Kampala, Uganda (Oct 2019-Oct 2020) and underwent EEG monitoring. Feasibility was assessed as to whether EEG monitoring of diagnostic quality could be achieved from days 1-5. Evolution of clinical presentation was assessed by Sarnat classification and daily Thompson score was performed. EEG background severity was graded at 12, 24, 48 and 72h after birth, and at time of Thompson score. Seizures were annotated remotely by experts and assessed for frequency, duration, burden, and status epilepticus. Early childhood outcome was assessed at follow up, and adverse outcome defined as death or neurodevelopmental impairment (NDI) at 18-24 months of age. In this prospective feasibility cohort study, diagnostic quality EEGs were recorded for 50 of 51 recruited neonates (median duration 71.4h, IQR 52.4-72.2), indicating feasibility. Of 39 participants followed to 18-24 months, 13 died and 7 had NDI. Daily Thompson score and EEG background grade were strongly correlated across all timepoints (days 1-5). Thompson score of ≥7 was most predictive of moderate-severe EEG background abnormality (AUC 0.83). Prognostic accuracy of moderate-severe EEG background grade to predict NDI was high (AUC 0.74). Electrographic seizures were seen in 52% (26); median seizure burden was high at 264min (IQR 27.8-523.7, range 1.3-1374.1); half (13) had status epilepticus. EEG monitoring was feasible as a research tool in this sub-Saharan Africa setting. EEG background activity correlated strongly with scored neurological assessment and predicted adverse early childhood outcome. Seizure prevalence and burden, including status epilepticus, were high in this uncooled cohort with important potential longer-term implications for survivors. Bill & Melinda Gates Foundation grant number OPP1210890; Wellcome Trust Innovator award (209325/Z/17/Z).

FBSE-Based Approach for Discriminating Seizure and Normal EEG Signals

FBSE-Based Approach for Discriminating Seizure and Normal EEG Signals

Trust EEG epileptic seizure detection via evidential multi-view learning

Epilepsy is one of the most common neurological disease in the world. Researchers focus on automatic electroencephalogram (EEG) seizure detection methods and achieve remarkable detection accuracy. However, there still exist highly uncertain decisions, which may be caused by the noise signals such as ocular artifacts. Considering the misclassification of an epileptic patient as non-seizure could have severe consequences, we point out that the automatic EEG seizure detection methods should explicitly provide the reliability of the detection. To achieve this goal, we propose an Evidential Multi-view Learning (EML) method, which reduces noises by multiple feature extraction methods and make trusted decision accordingly. EML constructs initial multi-view features to capture the diverse information of EEG signals. For each view, EML establishes deep neural networks to learn high-level features and view-specific evidence of each category, which could be termed as the amount of support to each category collected from data. By dynamically fusing different views at the evidence level, EML makes reliable prediction accordingly (strong evidence indicates high prediction reliability). We empirically evaluate EML on a public EEG Epileptic Seizure Detection dataset (CHB_MIT). Experiments show the superiority of EML over state-of-the-art baseline methods. We will release the code in https://github.com/Wednesque/Trust-EEG-Epileptic-Seizure-Detection-via-Evidential-Multi-view-Learning.

Advancements in NMDA Receptor-Targeted Antidepressants: From d-Cycloserine Discovery to Preclinical Efficacy of Lu AF90103.

The discovery of d-cycloserine (DCS), a partial agonist of the NMDA receptor that exhibits antidepressant effects without the psychotomimetic effects of ketamine, has fueled interest in new NMDA-targeting antidepressants. Our objective was to identify potent partial agonists mirroring DCS, particularly tailored for the GluN2B subtype of the NMDA receptor. Through a structure-based drug design approach, we discovered compound 42d. This compound acts as a partial agonist of the GluN1/GluN2B complex, exhibiting 24% efficacy, and has an EC50 value of 78 nM. Subsequent investigations led us to 42e (Lu AF90103), a methyl ester prodrug of 42d capable of penetrating the blood-brain barrier, as confirmed by rat microdialysis studies. In different rat in vivo models relevant to neuropsychiatric diseases, administering 42e led to 42d demonstrating both acute effects, observed in a seizure model and EEG, and lasting effects in the stress-sensitive hippocampal pathway and an antidepressant-sensitive model.

Defining neonatal status epilepticus: A scoping review from the ILAE neonatal task force.

To review the available literature concerning the definition of neonatal status epilepticus (SE) and/or seizure burden. The International League Against Epilepsy Neonatal Task Force performed a scoping review of the definitions of neonatal SE. Following a systematic literature review, articles were screened and data were abstracted regarding: (1) article characteristics (author identification, publication year, journal name, digital object identifier, title, objective, and study design); (2) cohort characteristics (sample size, gestational age, seizure etiology); (3) definition of SE and/or seizure burden; and (4) the method used to identify and classify SE, including routine EEG (EEG), continuous EEG monitoring (cEEG), amplitude-integrated EEG (aEEG), or clinical features. The scoping review yielded 44 articles containing a definition of neonatal SE. Studies mainly included infants with hypoxic-ischemic encephalopathy or neonates considered at risk for seizures. SE identification and classification most often relied on cEEG. The majority of studies based the definition of SE on seizure duration, including summed duration of seizures comprising ≥50% of any 1-h epoch, recurrent seizures for >50% of the total recording time, or either electrographic seizures lasting >30 min and/or repeated electrographic seizures totaling >50% in any 1-h period. Seizure burden was reported in 20 studies, and the most commonly used approach assessed total seizure burden, defined as total duration of EEG seizures in minutes. Sixteen studies assessed the relationship between seizure burden and outcomes, and most identified a significant association between higher seizure burden and unfavorable outcomes. This scoping review demonstrates a substantial variation in neonatal SE definitions across the literature. The most common definitions were based around a 30-min seizure duration criterion, but evidence was insufficient to support that 30 min was a cutoff defining prolonged seizures or that seizures exceeding this burden were more likely to be pharmacoresistant or associated with worse outcomes. As a next step, the Neonatal Task Force intends to develop a standardized approach to assessing and describing neonatal seizure burden and defining neonatal SE. Prolonged seizures are a neurologic emergency, if untreated, can lead to permanent injury or death. In adults and children, seizures lasting longer than 30 min are believed to cause brain damage. However, it is not clear if this definition can be applied to neonates. The International League Against Epilepsy Neonatal Taskforce performed a scoping literature review which identified 44 articles containing a definition of neonatal status epilepticus. In this article, the authors reviewed the current used definitions for prolonged seizures in neonates to establish a relationship between seizure duration and neurological outcome. As a next step, the Neonatal Task Force intends to develop a standardized approach to assessing and describing neonatal seizure burden and defining neonatal SE.

Association of Seizure Foci and Location of Tau and Amyloid Deposition and Brain Atrophy in Patients With Alzheimer Disease and Seizures.

Alzheimer disease (AD) is associated with a 2 to 3-fold increased risk of developing late-onset focal epilepsy, yet it remains unclear how development of focal epilepsy in AD is related to AD pathology. The objective of this study was to examine spatial relationships between the epileptogenic zone and tau deposition, amyloid deposition, and brain atrophy in individuals with AD who developed late-onset, otherwise unexplained focal epilepsy. We hypothesized that if network hyperexcitability is mechanistically linked to AD pathology, then there would be increased tau and amyloid deposition within the epileptogenic hemisphere. In this cross-sectional study, we performed tau and amyloid PET imaging, brain MRI, and overnight scalp EEG in individuals with early clinical stages of AD who developed late-onset, otherwise unexplained focal epilepsy (AD-Ep). Participants were referred from epilepsy and memory disorders clinics at our institutions. We determined epilepsy localization based on EEG findings and seizure semiology. We quantified tau deposition, amyloid deposition, and atrophy across brain regions and calculated asymmetry indices for these measures. We compared findings in AD-Ep with those in a control AD group without epilepsy (AD-NoEp). The AD-Ep group included 8 individuals with a mean age of 69.5 ± 4.2 years at PET imaging. The AD-NoEp group included 14 individuals with a mean age of 71.7 ± 9.8 years at PET imaging. In AD-Ep, we found a highly asymmetric pattern of tau deposition, with significantly greater tau in the epileptogenic hemisphere. Amyloid deposition and cortical atrophy were also greater in the epileptogenic hemisphere, although the magnitudes of asymmetry were reduced compared with tau. Compared with AD-NoEp, the AD-Ep group had significantly greater tau asymmetry and trends toward greater asymmetry of amyloid and atrophy. AD-Ep also had significantly greater amyloid burden bilaterally and trends toward greater tau burden within the epileptogenic hemisphere, compared with AD-NoEp. Our results reveal a spatial association between the epileptogenic focus and tau deposition, amyloid deposition, and neurodegeneration in early clinical stages of AD. Within the limitations of a cross-sectional study with small sample sizes, these findings contribute to our understanding of the clinicopathologic heterogeneity of AD, demonstrating an association between focal epilepsy and lateralized pathology in AD.

Seizure Sources Can Be Imaged from Scalp EEG by Means of Biophysically Constrained Deep Neural Networks.

Seizure localization is important for managing drug-resistant focal epilepsy. Here, the capability of a novel deep learning-based source imaging framework (DeepSIF) for imaging seizure activities from electroencephalogram (EEG) recordings in drug-resistant focal epilepsy patients is investigated. The neural mass model of ictal oscillations is adopted to generate synthetic training data with spatio-temporal-spectra features similar to ictal dynamics. The trained DeepSIF model is rigorously validated using computer simulations and in a cohort of 33 drug-resistant focal epilepsy patients with high-density (76-channel) EEG seizure recordings, by comparing DeepSIF estimates with surgical resection outcome and seizure onset zone (SOZ). These findings show that the trained DeepSIF model outperforms other methods in estimating the spatial and temporal information of origins of ictal activities. It achieves a high spatial specificity of 96% and a low spatial dispersion of 3.80±5.74mm when compared to the resection region. The source imaging results also demonstrate good coverage of SOZ, with an average distance of 10.89±10.14mm (from the SOZ to the reconstruction). These promising results suggest that DeepSIF has significant potential for advancing noninvasive imaging of the origins of ictal activities in patients with focal epilepsy, aiding management of intractable epilepsy.

Patterns of ictal surface EEG in occipital seizures: A simultaneous scalp and intracerebral recording study

ObjectiveTo describe the ictal scalp EEG patterns of occipital seizures (OS) and their spatiotemporal correlations with intracerebral occipital ictal discharges derived from simultaneous SEEG-EEG recordings. MethodsPatients with SEEG confirmed OS (14 OS from 8 patients) were selected from an epilepsy surgery center and were monitored 3–10 days using simultaneous scalp EEG and SEEG recordings. ResultsOn scalp EEG, the most common onset patterns were background activity suppression (28.6 %) and high amplitude slow wave corresponding to intracerebral DC-shift (28.6 %) and occurred with a median delay of 0 s after intra-cerebral onset. The initial discharge involved occipital electrodes in only 50 % of the seizures (7/14) with additional basal temporal (8/14) or parietal electrodes (5/14). The onset was ipsilateral to the intra-cerebral onset zone in 71.4 % of seizures and bilateral in the remaining (28.6 %). The most common propagation pattern was either unilateral (50 %) or bilateral (50 %) and a rhythmic slow activity (66.7 %). Different OS subtypes display distinct scalp EEG patterns. ConclusionScalp EEG accurately determines intra-cerebral seizure onset time in OS and has good lateralizing value. However, initial scalp modification does not always involves occipital electrodes and the second modification is well lateralizing in only 50 % of seizures. SignificanceThis study describes will help clinicians to better identify OS during video EEG and better plan intra-cerebral explorations for epilepsy surgery.

Allopregnanolone and progesterone in relation to a single electroconvulsive therapy seizure and subsequent clinical outcome: an observational cohort study

BackgroundElectroconvulsive therapy (ECT) is an important treatment for several severe psychiatric conditions, yet its precise mechanism of action remains unknown. Increased inhibition in the brain after ECT seizures, mediated by γ-aminobutyric acid (GABA), has been linked to clinical effectiveness. Case series on epileptic patients report a postictal serum concentration increase of the GABAA receptor agonist allopregnanolone. Serum allopregnanolone remains unchanged after a full ECT series, but possible transient effects directly after a single ECT seizure remain unexplored. The primary aim was to measure serum concentrations of allopregnanolone and its substrate progesterone after one ECT seizure. Secondary aims were to examine whether concentrations at baseline, or postictal changes, either correlate with seizure generalization or predict clinical outcome ratings after ECT.MethodsA total of 130 participants (18–85 years) were included. Generalization parameters comprised peak ictal heart rate, electroencephalographic (EEG) seizure duration, and prolactin increase. Outcome measures were ratings of clinical global improvement, perceived health status and subjective memory impairment. Non-parametric tests were used for group comparisons and correlations. The prediction analyses were conducted with binary logistic and simple linear regression analyses.ResultsAllopregnanolone and progesterone remained unchanged and correlated neither with seizure generalization nor with clinical outcome. In men (n = 50), progesterone increased and allopregnanolone change correlated negatively with EEG seizure duration. In a subgroup analysis (n = 62), higher baseline allopregnanolone and progesterone correlated with postictal EEG suppression.ConclusionsECT seizures have different physiologic effects than generalized seizures in epilepsy. Progesterone might have implications for psychiatric illness in men.

Identifying the infraslow activity associated with faciobrachial dystonic seizures in EEG.

Content available: Video.

Machine Learning Models for Probability Classification in Spectrographic EEG Seizures Dataset

The examination of brain signals, namely the Electroencephalogram (EEG) signals, is an approach to possibly detect seizures of the brain. Due to the nature of these signals, deep learning techniques have offered the opportunity to perform automatic or semi-automatic analysis which could support decision and therapeutical approaches. This paper focuses on the possibility of classifying EEG seizure using convolutional layers (namely EfficientNetV2 architectures, i.e., EfficientNetV2S and EfficientNetV2B2), Long Short-Term Memory (LSTM) units, and fine-tuned mechanisms of attention. We use these techniques to untangle the complexity of these signals and accurately predict seizures. The proposed system provided interesting results with an 86.45% accuracy under the Kullback-Leibler Divergence loss of 0.95. Moreover, these results showed that embedding LSTM layers deeply increases the quality of the results since these layers support the analysis of the spatial-temporal dynamics of the EEG signals. On the other hand, it is important to mention that hardware limitations could affect these results and therefore it is important, when setting this architectural system, to fine-tune the data set and balance the performance vs the computational cost of the process.

Effect of quantitative consciousness index on seizure parameters during electroconvulsive therapy in patients with major depressive disorder

BACKGROUND Electroconvulsive therapy (ECT) is both an effective treatment for patients with major depressive disorder (MDD) and a noxious stimulus. Although some studies have explored the effect of sedation depth on seizure parameters in ECT, there is little research on the noxious stimulation response to ECT. In this study, we used two electroencephalography (EEG)-derived indices, the quantitative consciousness (qCON) index and quantitative nociceptive (qNOX) index, to monitor sedation, hypnosis, and noxious stimulation response in patients with MDD undergoing acute ECT. AIM To evaluate the effect of anesthesia depth based on the qCON and qNOX indices on seizure parameters. METHODS Patients with MDD (n = 24) underwent acute bilateral temporal ECT under propofol anesthesia. Before ECT, the patients were randomly divided into three groups according to qCON scores (qCON60-70, qCON50-60, and qCON40-50). Continuous qCON monitoring was performed 3 minutes before and during ECT, and the qCON, qNOX, vital signs, EEG seizure parameters, and complications during the recovery period were recorded. The 24-item Hamilton Rating Scale for Depression, Zung’s Self-rating Depression Scale, and Montreal Cognitive Assessment scores were evaluated before the first ECT session, after the fourth ECT session, and after the full course of ECT. RESULTS A total of 193 ECT sessions were performed on 24 participants. The qCON index significantly affected the EEG seizure duration, peak mid-ictal amplitude, and maximum heart rate during ECT (P &lt; 0.05). The qNOX index significantly affected the post-ictal suppression index (P &lt; 0.05). Age, number of ECT sessions, and anesthetic-ECT time intervals also had a significant effect on EEG seizure parameters (P &lt; 0.05). However, there were no significant differences in complications, 24-item Hamilton Rating Scale for Depression scores, Zung’s Self-rating Depression Scale scores, or Montreal Cognitive Assessment scores among the three groups (P &gt; 0.05). CONCLUSION Electrical stimulation at a qCON index of 60-70 resulted in better EEG seizure parameters without increasing complications in patients with MDD undergoing bilateral temporal ECT under propofol anesthesia.

Total posterior quadrant disconnection for drug-resistant epilepsy in children.

To assess seizure outcomes, prognostic factors, and developmental changes in children undergoing total posterior quadrant disconnection (PQD) for drug-resistant epilepsy (DRE). We conducted a retrospective analysis of the clinical data of children with DRE who underwent total PQD surgery. The study focused on Engel's classification for seizure outcomes, exploring correlation of preoperative data and surgical effectiveness, and predictors of seizure prognosis. It involved a comparative analysis of developmental levels pre- and 3 months postoperatively using Griffiths Mental Development Scales-China (GMDS-C), and the correlation between clinical characteristics and GMDS-C results. Out of 61 pediatric patients, 70.5% showed no seizure recurrence postoperatively. In the univariate analysis, interictal electroencephalogram (EEG), magnetic resonance imaging (MRI), fluorodeoxyglucose positron emission tomography (FDG-PET), and acute postoperative seizure (APOS) were significantly related to surgical prognosis. In multivariate analysis, interictal EEG and APOS were identified as predictors of seizure prognosis. Survival analysis indicated significant associations between MRI, interictal EEG, FDG-PET, APOS and postoperative seizure occurrence. Preoperative GMDS-C levels were significantly correlated with epilepsy duration, seizure frequency, interictal EEG, and FDG-PET. GMDS-C scores improved postoperatively, while developmental quotients remained stable. For patients with structural abnormalities in the entire posterior quadrant, thorough preoperative assessment and timely total PQD surgery can effectively control seizures without causing neurological development deterioration. APOS and interictal EEG abnormalities beyond the posterior quadrant are predictors for seizure prognosis but should not be deemed contraindications for surgery. Due to lack of analysis on pediatric total PQD cases, 61 pediatric patients who underwent total PQD surgery were retrospectively enrolled. Seizure and development results were collected and analyzed as dependent variables. The study found that 70.5% of patients were seizure-free and showed development improvement, with no deaths or severe complications reported. Prognosis predictors included APOS and interictal EEG abnormalities beyond the posterior quadrant.