Seizures Research Articles

Face swapping in seizure videos for patient deidentification

ObjectiveThis study aimed to test different AI-based face-swapping models applied to videos of epileptic seizures, with the goal of protecting patient privacy while retaining clinically useful seizure semiology. We hypothesized that specific models would show differences in semiologic fidelity compared to the original clinical videos. MethodsThree open-source models, SimSwap, MobileFaceSwap and GHOST were adopted for face-swapping. For every model, an AI generated male and female image were used to replace the original faces. One representative seizure per patient from three patients with epilepsy was chosen (3 seizure videos x 3 AI models x 2 M/F swap) and remade to 18 transformed video clips. To evaluate the performance of the three models, we used both objective (AI-based) and subjective (expert clinician) evaluation. The objective assessment included four metrics for facial appearance and four metrics for facial expression changes. Four experienced epileptologists reviewed the clips and scoring according to deidentification and preservation of semiology. Kruskal-Wallis H test was used for statistical analysis among the models. ResultsIn the reproduced videos, the swapped face cannot be recognized as the original face, with no significant difference in scores of deidentification either by objective or subjective assessment. Regarding semiology preservation, no significant differences between models were observed in the objective evaluations. The subjective evaluations revealed that the GHOST model outperformed the other two models (p=0.028). ConclusionThis is the first study evaluating AI face swapping models in epileptic seizure video clips. Optimization of AI face-swapping models could enhance the accessibility of seizure videos for education and research while protecting patient privacy and maintaining semiology.

Metabotropic glutamate receptors-guardians and gatekeepers in neonatal hypoxic-ischemic brain injury.

Injury to the developing central nervous system resulting from perinatal hypoxia-ischemia (HI) is still a clinical challenge. The only approach currently available in clinical practice for severe cases of HI is therapeutic hypothermia, initiated shortly after birth and supported by medications to regulate blood pressure, control epileptic seizures, and dialysis to support kidney function. However, these treatments are not effective enough to significantly improve infant survival or prevent brain damage. The need to create a new effective therapy has focused attention on metabotropic glutamate receptors (mGluR), which control signaling pathways involved in HI-induced neurodegeneration. The complexity of mGluR actions, considering their localization and developmental changes, and the functions of each subtype in HI-evoked brain damage, combined with difficulties in the availability of safe and effective modulators, raises the question whether modulation of mGluRs with subtype-selective ligands can become a new treatment in neonatal HI. Addressing this question, this review presents the available information concerning the role of each of the eight receptor subtypes of the three mGluR groups (group I, II, and III). Data obtained from experiments performed on in vitro and in vivo neonatal HI models show the neuroprotective potential of group I mGluR antagonists, as well as group II and III agonists. The information collected in this work indicates that the neuroprotective effects of manipulating mGluR in experimental HI models, despite the need to create more safe and selective ligands for particular receptors, provide a chance to create new therapies for the sensitive brains of infants at risk.

EEG-based epileptic seizure detection using deep learning techniques: A survey

Epilepsy is a complex neurological disorder marked by recurrent seizures, often stemming from abnormal discharge of the brain. Electroencephalogram (EEG) captures temporal and spatial shifts in cerebral electrical activity, holding pivotal diagnostic and therapeutic value for epilepsy. Deep learning techniques have made remarkable progress in EEG-based seizure detection over recent years. This review is dedicated to exploring seizure detection approaches based on deep learning, focusing on three distinct avenues. Primarily, we delve into the application of canonical deep learning methods in epilepsy detection. Subsequently, a more in-depth study was conducted on the hybrid models of deep learning. Next, the third is the integration of deep learning and traditional machine learning strategies. Finally, the challenges and future prospects related to this topic are put forward. The uniqueness of this review lies in its novel and comprehensive perspective on the latest research on deep learning-based epilepsy detection by systematically classifying methods, visualizing research progress, and addressing challenges and gaps in current research. It can provide valuable guidance for researchers who want to delve into the field of epileptic seizure detection based on EEG signals.

Moxibustion pre-treatment attenuates seizure severity during status epilepticus and counteracts the proconvulsant function of the purinergic P2X7 receptor.

Moxibustion, traditional Chinese medicine treatment, involves the warming of specific acupuncture points of the body using ignited herbal materials. Evidence suggests beneficial effects of moxibustion in several brain diseases including epilepsy, however, whether moxibustion pretreatment impacts on seizures and what are the underlying mechanisms remains to be established. Evidence has suggested the purinergic ATP-gated P2X7 receptor (P2X7R) to be involved in the actions of moxibustion. Moreover, P2X7R signalling is now well established to contribute to long-lasting brain hyperexcitability underlying epilepsy development. Whether P2X7R signalling is involved in the seizure-reducing actions of moxibustion has not been investigated to date. For our studies we used C57BL/6 male mice that received moxibustion pre-treatments at the acupoints Zusanli (ST36) and Dazhui (GV14) once daily for either 7, 14, or 21days. This was followed by an intraperitoneal injection of kainic acid (KA, 30mg/kg) to induce status epilepticus. Behavioral changes during KA-induced status epilepticus were analyzed according to the Racine scale. Changes in electrographic seizures were analyzed via cortical implanted electroencephalogram (EEG) electrodes. While no effect on seizure severity was observed following 7days of moxibustion pre-treatment, moxibustion pre-treatment at both ST36 and GV14 for 14 or 21days significantly reduced KA-induced behavior seizures at a similar rate. Cortical EEG recordings showed that 14days of moxibustion pre-treatments also reduced electrographic seizures, confirming the anticonvulsant actions of moxibustion pre-treatment. To determine whether moxibustion impacts the pro-convulsant actions of P2X7R signaling, mice were treated with the P2X7R agonist BzATP or P2X7R antagonist A438079. While treatment with the P2X7R agonist BzATP exacerbated seizure severity, treatment with the P2X7R antagonist reduced seizure severity. We further found that moxibustion pre-treatment attenuated epileptic seizures by counteracting the effects ofBzATP. These results suggest that moxibustion pre-treatment at the acupoints ST36 and GV14 for 14days has anti-epileptic effects, which may counteract the proconvulsant functions of the P2X7R.

Romanian Translation and Cultural Adaptation of the Seizure Severity Questionnaire.

Four translators were involved in obtaining conceptual analogies and the cultural importance of the translated notions. The final version was obtained for the Romanian population, with the same appearance as the original instrument. Sixty-seven patients with epilepsy completed the SSQ and the Patient-Weighted Quality of Life in Epilepsy Inventory-QOLIE-31-P. Females had a lower mean SSQ total score (TS) and perceived seizures less seriously than men. Patients with epilepsy with aura had a higher mean SSQ TS, with a more severe seizure perception, compared to those without aura. According to the frequency of seizures, patients with epilepsy with rare seizures had the lowest mean SSQ total score (TS) compared to those with frequent seizures. Patients who were on monotherapy had a less severe perception of epileptic seizures compared to those who were treated with two or more antiepileptic drugs. All QOLIE-31-P domains and TS correlated statistically significantly with the SSQ TS. This study explored SSQ translation, evaluated preliminary results, and showed the correlation between seizure frequency and severity, clinical factors, and quality of life. This tool could be useful for measuring seizure severity in Romanian patients with epilepsy and conducting comparative studies.

Pharmacogenetic insights into ABCB1, ABCC2, CYP1A2, and CYP2B6 variants with epilepsy susceptibility among Egyptian Children: A retrospective case-control study

BackgroundPediatric epilepsy is a complicated neuropsychiatric disorder that is characterized by recurrent seizures and unusual synchronized electrical activities within brain tissues. It has a substantial effect on the quality of life of children, thus understanding of the hereditary considerations influencing epilepsy susceptibility and the response to antiepileptic medications is crucial. This study focuses on assessing the correlation of the ABCB1, ABCC2, CYP1A2, and CYP2B6 genetic polymorphisms with the susceptibility to epileptic seizures and their contributions to antiepileptic medication throughout the course of the disease. MethodsThis study included 134 Egyptian epileptic children, comprising 67 drug-responsive and 67 drug-resistant patients, along with 124 healthy controls matching for age, gender, and geographical district. Genotyping of the rs2032582, rs717620, rs2273697, rs762551, and rs3745274 variants was performed using the PCR technique. Statistical analyses, including haplotype, multivariate, logistic regression, and bioinformatics approaches, were conducted to evaluate the associations within the disease. ResultsThe ABCC2*rs717620 (T allele) revealed an increased risk of epilepsy compared to healthy controls (OR = 2.12, p-value < 0.001), with the rs717620 (C/T + T/T genotypes) showing significant differences between drug-responsive and drug-resistant patients (p-value < 0.05). Moreover, the ABCC2*rs2273697 (A allele) indicated a decreased risk of epileptic seizures compared to healthy controls (OR = 0.51, p-value = 0.033), with the rs2273697 (G/A + A/A genotypes) indicating a significant association with drug-resistant patients (OR = 0.21, p-value = 0.002). The rs717620*T/rs2273697*G haplotype was significantly correlated with an elevated risk of epileptic seizures within drug-responsive patients (OR = 2.26, p-value = 0.019). Additionally, the CYP1A2*rs762551 (A allele) represented a protective effect against epilepsy susceptibility (OR = 0.50, p-value < 0.001), with the rs762551 (G/A + A/A genotypes) disclosing a substantial association with a decreased risk of epileptic seizures among drug-resistant patients compared to drug-responsive patients (OR = 0.07, p-value < 0.001). Conversely, the ABCB1*rs2032582 (G allele) and the CYP2B6*rs3745274 (T allele) did not attain a significant difference with the epilepsy risk compared to healthy controls (p-value > 0.05). ConclusionsThe findings of our study emphasize the importance of pharmacogenetic screening in epilepsy research, particularly regarding to drug-resistant patients. The ABCC2*rs717620 variant conferred a significant correlation with elevated risk of epileptic seizures, while the ABCC2*rs2273697 and CYP1A2*rs762551 variants confirmed their contributions as protective markers against epilepsy development. Conversely, the ABCB1*rs2032582 and CYP2B6*rs3745274 alleles were not considered as independent risk factors with the course of epilepsy disease.

B - 41 Mild Head Injury (MHI), Unrelated Abnormal Brain Findings, Collateral Support, Video EEG and Neuropsychological Findings: a Case Study of Functional Seizure Disorder

Abstract Objective Functional seizure disorders, a form of conversion disorder with contributing biological, psychological, and social factors, pose a differential diagnostic challenge. Integrating video EEG, CT Brain Scan, collateral support and neuropsychological findings in diagnosis is discussed. Method The absence of epileptiform activity in video-EEG distinguishes functional and epileptic seizures. A case study is presented of a young adult male who sustained a MHI in a motor vehicle accident, presenting with a seizure disorder two weeks thereafter. Twenty-four-hour video EEG using photic stimulation revealed grunting sounds, head extension, clenched hands, back arching, jerking with associated paradoxical heavy breathing (shown in video clip), similar to family eyewitness descriptions. Hyperventilation was associated with generalized slowing. No epileptiform activity was noted. Unenhanced CT Brain Scan revealed global symmetrical age-incongruent cerebral involutional change. Results Neuropsychological assessment using CNS Vital Signs Test revealed variable scores, with “very low” scores on Complex Attention (raw score 17; SS = 68; 2nd Percentile); Cognitive Flexibility (raw score 28; SS =66; 1st percentile) and Processing Speed (raw score = 38; SS = 67; 1st percentile). “Above average” scores were found for Composite Memory (raw score 107; SS = 113; 81st percentile) and Verbal Memory (raw score = 59; SS = 122; 93rd percentile). Conclusions Brain involutional changes suggest pre-existing functional immaturity, instability of brain regions, or reduced neural connections may precede the diagnosis of Functional Seizure Disorders, precipitated by the MHI. In addition to video EEG, selected neuropsychological findings and collateral information provide additional support to confirm this complex disorder.

Brain perfusion SPECT in the presurgical evaluation of epilepsy: is additional ictal SPECT required in case of high-confidence lateralization of the seizure onset zone by interictal SPECT and vice versa?

BackgroundIctal brain perfusion SPECT provides higher sensitivity for the identification of the epileptic seizure onset zone (SOZ) than interictal SPECT. However, ictal SPECT is demanding due to the unpredictable waiting period for the next seizure to allow for ictal tracer injection. Thus, starting with an interictal scan and skipping the ictal scan if the interictal scan provides a SOZ candidate with high confidence could be an efficient approach. The current study estimated the rate of high-confidence SOZ candidates and the false lateralization rate among them for interictal and ictal SPECT.Methods177 patients (48% females, median age 38y, interquartile range 27–48y) with ictal and interictal SPECT acquired with 99mTc-HMPAO (n = 141) or -ECD (n = 36) were included retrospectively. The vast majority of the patients was suspected to have temporal lobe epilepsy. Visual interpretation of the SPECT data was performed independently by 3 readers in 3 settings: “interictal only” (interictal SPECT and statistical hypoperfusion map), “ictal only” (ictal SPECT and hyperperfusion map), and “full” setting (side-by-side interpretation of ictal and interictal SPECT including statistical maps and SISCOM analysis). The readers lateralized the SOZ (right, left, none) and characterized their confidence using a 5-score. A case was considered "lateralizing with high confidence” if all readers lateralized to the same hemisphere with at least 4 of 5 confidence points. Lateralization of the SOZ in the “full” setting was used as reference standard.ResultsThe proportion of “lateralizing with high confidence” cases was 4.5/31.6/38.4% in the “interictal only”/“ictal only”/“full” setting. One (12.5%) of the 8 cases that were “lateralizing with high confidence” in the “interictal only” setting lateralized to the wrong hemisphere. Among the 56 cases that were “lateralizing with high confidence” in the “ictal only” setting, 54 (96.4%) were also lateralizing in the “full” setting, all to the same hemisphere.ConclusionsStarting brain perfusion SPECT in the presurgical evaluation of epilepsy with an interictal scan to skip the ictal scan in case of a high-confidence interictal SOZ candidate is not a useful approach. In contrast, starting with an ictal scan to skip the interictal scan in case of a high-confidence ictal SOZ candidate can be recommended.

A - 27 Case Study Approach to Initial Exploration of Adaptations of Cognitive Behavioral Therapy (CBT) for Non-Epileptic Seizures (NES) in the Context of Cognitive Impairment

Abstract Objective The following case study seeks to review implementation of CBT for NES, discuss psychotherapeutic adaptations and outcomes while balancing treatment fidelity, and offer preliminary recommendations for expansion of psychotherapeutic modalities for individuals with cognitive impairment. Methods 49-year-old Hispanic male with a history of mixed epileptic (non-lesional frontal lobe medically refractory) and non-epileptic events. Neurological workup included video EEG, which captured seven events without EEG correlate and an unremarkable brain MRI. Neuropsychological evaluation indicated mild cognitive impairment due to epilepsy with deficits in processing speed, executive functioning, and confrontation naming with borderline to low average core visual and verbal abilities. The patient participated in manualized CBT for PNES. Results Treatment adaptations included extending treatment sessions from 12–19 sessions and including the patient’s sister. They read the chapters together and practiced strategies outside of session. She participated in helping him notice patterns of manifestations of fear and anger and their influence on somatic symptoms. Omission of treatment elements with higher cognitive demand (i.e., thought chart). Outcomes included increased awareness of emotions, triggers, and warnings but not episode reduction in the context of increased epileptic seizures. Conclusions Feasibility of treatment may be limited for individuals with mixed epileptic and NES episodes, particularly if there is cognitive impairment and difficulty differentiating between the two. Psychotherapeutic techniques that are concrete and behaviorally based will = be beneficial for individuals with cognitive impairment. Episode reduction in isolation is likely reductionistic when considering treatment effectiveness. Ability to self-manage episodes, quality of life, functional status, and self-efficacy are valuable markers of improvement.

Developmental and epileptic encephalopathies after successful treatment of pediatric ALL: A case series and review of literature.

Successful treatment of acute lymphoblastic leukemia (ALL) requires multiagent chemotherapy regimens and central nervous system prophylaxis, including intrathecal methotrexate. Although acute symptomatic seizures can occur during ALL treatment, epilepsy is less common. Furthermore, drug resistant epilepsy (DRE) is rare, presenting with two phenotypes: focal epilepsy, such as temporal lobe, or epileptic encephalopathies (EE), such as Lennox-Gastaut syndrome (LGS). For ALL survivors, the development of DRE has significant impact on morbidity, mortality, and quality of life. We describe four patients with ALL remission, who developed EEs, of which 3 had LGS. Mean age at ALL diagnosis was 1.9 years; range 1.1-2.5 years. All, but one, had normal development prior to ALL. No patient had CNS leukemic involvement. All patients received CNS prophylaxis with intrathecal methotrexate, without cranial radiotherapy. Three had symptomatic methotrexate neurotoxicity during treatment. The mean age at first seizure was 5.6 years; range 3.9-7.5 years, with a mean latency of 3.7 years from ALL diagnosis. All patients developed drug resistant EEs, moderate intellectual disability, and neuropsychiatric co-morbidities. Two patients had a minimal response to corpus callosotomy (CC), and one did not respond the ketogenic diet. Successful treatment of childhood ALL is rarely associated with the development of DRE and EEs. Young age at ALL diagnosis (<3 years) may be a predisposing factor. Palliative treatments, including ketogenic diet and CC have limited benefit in these patients. Individual genetic susceptibility to MTX toxicity is likely related to epileptogenesis, and further research is required for epilepsy biomarkers.

Nonictal electroencephalographic measures for the diagnosis of functional seizures.

Functional seizures (FS) look like epileptic seizures but are characterized by a lack of epileptic activity in the brain. Approximately one in five referrals to epilepsy clinics are diagnosed with this condition. FS are diagnosed by recording a seizure using video-electroencephalography (EEG), from which an expert inspects the semiology and the EEG. However, this method can be expensive and inaccessible and can present significant patient burden. No single biomarker has been found to diagnose FS. However, the current limitations in FS diagnosis could be improved with machine learning to classify signal features extracted from EEG, thus providing a potentially very useful aid to clinicians. The current study has investigated the use of seizure-free EEG signals with machine learning to identify subjects with FS from those with epilepsy. The dataset included interictal and preictal EEG recordings from 48 subjects with FS (mean age = 34.76 ± 10.55 years, 14 males) and 29 subjects with epilepsy (mean age = 38.95 ± 13.93 years, 18 males) from which various statistical, temporal, and spectral features from the five EEG frequency bands were extracted then analyzed with threshold accuracy, five machine learning classifiers, and two feature importance approaches. The highest classification accuracy reported from thresholding was 60.67%. However, the temporal features were the best performing, with the highest balanced accuracy reported by the machine learning models: 95.71% with all frequency bands combined and a support vector machine classifier. Machine learning was much more effective than using individual features and could be a powerful aid in FS diagnosis. Furthermore, combining the frequency bands improved the accuracy of the classifiers in most cases, and the lowest performing EEG bands were consistently delta and gamma.

Deep Clustering for Epileptic Seizure Detection.

The objective of this study is to address the challenges of EEG-based epileptic seizure detection by introducing a novel methodology, Deep Embedded Gaussian Mixture (DEGM). The DEGM method begins with a deep autoencoder (DAE) for embedding the input EEG data, followed by Singular Value Decomposition (SVD) to enhance the representational quality of the embedding while achieving dimensionality reduction. A Gaussian Mixture Model (GMM) is then employed for clustering purposes. Unlike conventional supervised machine learning and deep learning techniques, DEGM leverages deep clustering (DC) algorithms for more effective seizure detection. Empirical results from two real-world epileptic datasets demonstrate the notable performance of DEGM. The method's effectiveness is particularly remarkable given the substantial size of the datasets, showcasing its ability to handle large-scale EEG data efficiently. In conclusion, the DEGM methodology provides a novel and effective approach for EEG-based epileptic seizure detection, addressing key challenges such as data variability and artifact contamination. By combining deep autoencoders, SVD, and GMM, DEGM achieves superior clustering performance compared to existing methods, representing a significant advancement in biomedical research and clinical applications for epilepsy. Its robust performance on large datasets underscores its potential for improving seizure detection accuracy, ultimately contributing to better patient outcomes.

Electric stimulation using stereoelectroencephalography electrodes

Electrical stimulation (ES) using stereoelectroencephalography is an essential component in the workup of surgical epilepsy. ES helps to solve two major problems in epilepsy surgery – total resection of the epileptogenic lesion while minimising the postoperative neurological deficit. ES allows to induce habitual epileptic seizures to define the neurophysiological characteristics and boundaries of the epileptogenic zone and to map eloquent areas to reduce the area of resection with prediction of post-operative neurological deficit. The results of studies using ES make a huge contribution not only to practical medicine, but also to fundamental science, allowing us to study the functions of individual parts of the brain and to understand the elements of the pathogenesis of various diseases of the nervous system.

Association of dietary fiber intake with epileptic seizures in U.S. adults: A Population-base study of 13,277 participants

ObjectiveEpilepsy, a neurological disorder, is identified by the presence of recurrent seizures. We aimed to detect dietary fiber intake and its association with epilepsy prevalence in U.S. adults. MethodsThis cross-sectional study obtained data from the 2013–2018 National Health and Nutrition Examination Survey database. Univariate and multivariate logistic regression models were employed to estimate the association between dietary fiber intake and epilepsy prevalence. The restricted cubic spline (RCS) model was also applied to investigate the dose-response relationships between dietary fiber intake and epileptic seizure events(ESEs). ResultsOur final sample included 13,277 NHANES participants, with the average prevalence of ESEs being 1.09 % (145/13277). After adjusting for all confounding factors, the third quartile of dietary fiber intake levels remained significantly associated with a decreased risk of ESEs[odds ratios (OR) 0.54,95 % confidence interval (CI) 0.33–0.88, P = 0.014)] compared to the first quartile. Higher fiber intake indicated a stable negative association with ESEs in the multivariate logistic regression analysis, weighted generalized additive model. A nonlinear dose-response relationship was observed between dietary fiber intake levels and decreased ESEs risk (P for overall=0.017, P for nonlinear=0.155). Interaction tests showed no significant effect of demographic and disease status on the association between dietary fiber intake and ESEs. ConclusionIn this cross-sectional study, people with a high dietary fiber intake were at a reduced risk of ESEs. However, further prospective studies are needed to investigate the effect of dietary fiber intake in epilepsy events and to determine causality.

Continuous locomotor activity monitoring to assess animal welfare following intracranial surgery in mice.

Locomotor activity can serve as a readout to identify discomfort and pain. Therefore, monitoring locomotor activity following interventions that induce potential discomfort may serve as a reliable method for evaluating animal health, complementing conventional methods such as body weight measurement. In this study, we used the digital ventilated cage (DVC®) system for the assessment of circadian locomotor activity, in addition to body weight monitoring, following intracranial stereotaxic surgery in an Alzheimer's disease mouse model (C57BL/6J/APPswe/PSEN1dE9). Stereotaxic surgery did not affect the organization of circadian locomotor activity of both 7-8-week-old and 19-21-week-old mice. However, we observed that both young and old mice exhibited a significant decrease in activity during the dark phase. Also, our study shows that changes in locomotor activity exhibit higher sensitivity in detecting alterations indicative of animal health compared to measuring body weight. In contrast to 7-8-week-old mice, where we observed no genotypic differences in locomotor activity, 19-21-week-old APP/PS1 mice showed increased locomotor activity compared to wild-type mice. Furthermore, our analyses revealed that a subset of the 7-8-week-old mice showed increased locomotor activity during the initial peak of the dark phase. One mouse experienced sudden death early in life, possibly due to epileptic seizures. Altogether, our findings affirm continuous activity measurements as used in the DVC® as a highly valuable objective method for post-surgical welfare monitoring. Its discerning capacity not only facilitates circadian locomotor rhythm assessment but also enables the identification of individual aberrant activity patterns, possibly indicative of epileptic seizures.

Analysis of New Hemogram Markers in Patients Presenting to the Emergency Department with Epileptic Seizures

Objective: We aimed to analyze the diagnostic value of new potential hemogram biomarkers in patients presenting to the emergency department with epileptic seizures. Materials and Methods: Patients presenting with epileptic seizures to a tertiary hospital's emergency department between January 1, 2023, and January 31, 2024, were retrospectively reviewed. The patients were categorized into Group A (seizure patients) and Group B (healthy volunteers). Hemogram and biochemistry data from routine blood tests were examined. To predict seizure status, ROC analysis was performed to evaluate NLR, PLR and PNR. The area under the curve and cutoff values were calculated for each marker. Results: Our study examined two groups: seizure patients and the control group. The mean age of the seizure group was 50.31±1.83 years, and the mean age of the control group was 49.58±1.96 years (p&gt;0.05). In the seizure group (n=116), 55.8% were male and 44.2% were female, whereas in the control group (n=104), 57.8% were male and 42.2% were female (p&gt;0.05). WBC, neutrophil count, NLR, and PLR values were significantly higher in seizure patients compared to the control group (p

Intelligent Health Assessment Based on Communication and AI Technologies for Public Health

Automating EEG pattern categorization in public health helps in the early detection of epilepsy and other brain illnesses. However, present methods have difficulties in reaching excellent accuracy and adaptability. This study utilizes a hybrid strategy that incorporates Spider wasp-tuned Convolutional neural network (SW-CNN). Convolutional neural networks (CNNs) use complex feature extraction from EEG data, and Spider wasp optimization (SWO) improves network parameters by comparing them to the pursuing and developing behaviors of spider wasps. By enhancing classification accuracy, precision, recall, and F1-score measures, the combined effect seeks to achieve significant improvements over conventional techniques. The research concludes that the SW-CNN hybrid model performs better at differentiating between non-seizure activity and epileptic seizures. This strategy improves diagnosis accuracy and efficiency in public health, resulting in better patient outcomes and treatment planning. Effective transmission of such results is critical for furthering clinical diagnosis and research in neurological diseases.

Brain network changes after the first seizure: an insight into medication response?

After a first epileptic seizure, anti-seizure medications (ASMs) can change the likelihood of having a further event. This prospective study aimed to quantify brain network changes associated with taking ASM monotherapy. We applied graph theoretical network analysis to longitudinal resting-state functional MRI (fMRI) data from 28 participants who had recently experienced their first seizure. Participants were imaged before and during long-term ASM therapy, with a mean inter-scan interval of 6.9 months. After commencing ASM, we observed an increase in the clustering coefficient and a decrease in network path length. Brain changes after ASM treatment were most prominent in the superior frontoparietal and inferior fronto-temporal regions. Participants with recurrent seizures display the most pronounced network changes after ASM treatment. This study shows changes in brain network function after ASM administration, particularly in participants with recurrent seizures. Larger studies that ideally include control cohorts are required to understand further the connection between ASM-related brain network changes and longer-term seizure status.

Advanced Epileptic Seizure Detection Using Deep Learning and Bayesian Optimization

Advanced Epileptic Seizure Detection Using Deep Learning and Bayesian Optimization

Focal cortical dysplasia (type II) detection with multi-modal MRI and a deep-learning framework

Focal cortical dysplasia type II (FCD-II) is a prominent cortical development malformation associated with drug-resistant epileptic seizures that leads to lifelong cognitive impairment. Efficient MRI, followed by its analysis (e.g., cortical abnormality distinction, precise localization assistance, etc.) plays a crucial role in the diagnosis and supervision (e.g., presurgery planning and postoperative care) of FCD-II. Involving machine learning techniques particularly, deep-learning (DL) approaches, could enable more effective analysis techniques. We performed a comprehensive study by choosing six different well-known DL models, three image planes (axial, coronal, and sagittal) of two MRI modalities (T1w and FLAIR), demographic characteristics (age and sex) and clinical characteristics (brain hemisphere and lobes) to identify a suitable DL model for analysing FCD-II. The outcomes show that the DenseNet201 model is more suitable because of its superior classification accuracy, high-precision, F1-score, and large area under the receiver operating characteristic (ROC) curve and precision–recall (PR) curve.