In the field of precision healthcare,where accurate decision-making is paramount,this study underscores the indispensability of eXplainable Artificial Intelligence(XAI)in the context of epilepsy management within the ...In the field of precision healthcare,where accurate decision-making is paramount,this study underscores the indispensability of eXplainable Artificial Intelligence(XAI)in the context of epilepsy management within the Internet of Medical Things(IoMT).The methodology entails meticulous preprocessing,involving the application of a band-pass filter and epoch segmentation to optimize the quality of Electroencephalograph(EEG)data.The subsequent extraction of statistical features facilitates the differentiation between seizure and non-seizure patterns.The classification phase integrates Support Vector Machine(SVM),K-Nearest Neighbor(KNN),and Random Forest classifiers.Notably,SVM attains an accuracy of 97.26%,excelling in the precision,recall,specificity,and F1 score for identifying seizures and non-seizure instances.Conversely,KNN achieves an accuracy of 72.69%,accompanied by certain trade-offs.The Random Forest classifierstands out with a remarkable accuracy of 99.89%,coupled with an exceptional precision(99.73%),recall(100%),specificity(99.80%),and F1 score(99.86%),surpassing both SVM and KNN performances.XAI techniques,namely Local Interpretable ModelAgnostic Explanations(LIME)and SHapley Additive exPlanation(SHAP),enhance the system’s transparency.This combination of machine learning and XAI not only improves the reliability and accuracy of the seizure detection system but also enhances trust and interpretability.Healthcare professionals can leverage the identified important features and their dependencies to gain deeper insights into the decision-making process,aiding in informed diagnosis and treatment decisions for patients with epilepsy.展开更多
Behavioral scoring based on clinical observations remains the gold standard for screening,diagnosing,and evaluating infantile epileptic spasm syndrome(IESS).The accurate identification of seizures is crucial for clini...Behavioral scoring based on clinical observations remains the gold standard for screening,diagnosing,and evaluating infantile epileptic spasm syndrome(IESS).The accurate identification of seizures is crucial for clinical diagnosis and assessment.In this study,we propose an innovative seizure detection method based on video feature recognition of patient spasms.To capture the temporal characteristics of the spasm behavior presented in the videos effectively,we incorporate asymmetric convolutions and convolution–batch normalization–ReLU(CBR)modules.Specifically within the 3D-ResNet residual blocks,we split the larger convolutional kernels into two asymmetric 3D convolutional kernels.These kernels are connected in series to enhance the ability of the convolutional layers to extract key local features,both horizontally and vertically.In addition,we introduce a 3D convolutional block attention module to enhance the spatial correlations between video frame channels efficiently.To improve the generalization ability,we design a composite loss function that combines cross-entropy loss with triplet loss to balance the classification and similarity requirements.We train and evaluate our method using the PLA IESS-VIDEO dataset,achieving an average seizure recognition accuracy of 90.59%,precision of 90.94%,and recall of 87.64%.To validate its generalization capability further,we conducted external validation using six different patient monitoring videos compared with assessments by six human experts from various medical centers.The final test results demonstrate that our method achieved a recall of 0.6476,surpassing the average level achieved by human experts(0.5595),while attaining a high F1-score of 0.7219.These findings have substantial significance for the long-term assessment of patients with IESS.展开更多
Epilepsy can be defined as a dysfunction of the brain network,and each type of epilepsy involves different brain-network changes that are implicated diffe rently in the control and propagation of interictal or ictal d...Epilepsy can be defined as a dysfunction of the brain network,and each type of epilepsy involves different brain-network changes that are implicated diffe rently in the control and propagation of interictal or ictal discharges.Gaining more detailed information on brain network alterations can help us to further understand the mechanisms of epilepsy and pave the way for brain network-based precise therapeutic approaches in clinical practice.An increasing number of advanced neuroimaging techniques and electrophysiological techniques such as diffusion tensor imaging-based fiber tra ctography,diffusion kurtosis imaging-based fiber tractography,fiber ball imagingbased tra ctography,electroencephalography,functional magnetic resonance imaging,magnetoencephalography,positron emission tomography,molecular imaging,and functional ultrasound imaging have been extensively used to delineate epileptic networks.In this review,we summarize the relevant neuroimaging and neuroelectrophysiological techniques for assessing structural and functional brain networks in patients with epilepsy,and extensively analyze the imaging mechanisms,advantages,limitations,and clinical application ranges of each technique.A greater focus on emerging advanced technologies,new data analysis software,a combination of multiple techniques,and the construction of personalized virtual epilepsy models can provide a theoretical basis to better understand the brain network mechanisms of epilepsy and make surgical decisions.展开更多
Although low-frequency repetitive transcranial magnetic simulation can potentially treat epilepsy, its underlying mechanism remains unclear. This study investigated the influence of low-frequency re-petitive transcran...Although low-frequency repetitive transcranial magnetic simulation can potentially treat epilepsy, its underlying mechanism remains unclear. This study investigated the influence of low-frequency re-petitive transcranial magnetic simulation on changes in several nonlinear dynamic electroenceph-alographic parameters in rats with chronic epilepsy and explored the mechanism underlying repeti-tive transcranial magnetic simulation-induced antiepileptic effects. An epilepsy model was estab-lished using lithium-pilocarpine intraperitoneal injection into adult Sprague-Dawley rats, which were then treated with repetitive transcranial magnetic simulation for 7 consecutive days. Nonlinear elec-electroencephalographic parameters were obtained from the rats at 7, 14, and 28 days post-stimulation. Results showed significantly lower mean correlation-dimension and Kolmogo-rov-entropy values for stimulated rats than for non-stimulated rats. At 28 days, the complexity and point-wise correlation dimensional values were lower in stimulated rats. Low-frequency repetitive transcranial magnetic simulation has suppressive effects on electrical activity in epileptic rats, thus explaining its effectiveness in treating epilepsy.展开更多
OBJECTIVE To evaluate whether ginsenoside Rb1 has antiepileptic effects on pen⁃tylenetetrazole(PTZ)-induced epileptic mice via intranasal therapeutic administration.METHODS Rb1 monoclonal antibody was used to observe ...OBJECTIVE To evaluate whether ginsenoside Rb1 has antiepileptic effects on pen⁃tylenetetrazole(PTZ)-induced epileptic mice via intranasal therapeutic administration.METHODS Rb1 monoclonal antibody was used to observe the distribution of Rb120 mg·kg-1 in mouse brain tissues under different administration routes and to explore the feasibility of intranasal Rb1.PTZ was injected intraperitoneally into healthy ICR mice every 48 hours to construct a tonic-clonic epileptic model.Then Rb120 or 40 mg·kg-1 or valproate 300 mg·kg-1 or saline was administered intranasally for 30 d,and PTZ was continued every five days to imitate occa⁃sional convulsions in the clinic.Racine scale(RCS)and wireless electroencephalogram(EEG)monitoring were used to assess the presence and severity of seizure.Immunofluorescence(IF)was performed after drug treatment to evalu⁃ate the effect of Rb1 on brain neuron,microglia and astrocyte in epileptic mice.RESULTS Rb1 had specific binding with anti-Rb1 in the brain under different administration routes,and intrana⁃sal Rb1 was able to enter the brain and play a therapeutic role(P<0.01).PTZ-injured mice pre⁃sented body mass loss,higher seizure stage and shorter seizure latency.At the same time,epilep⁃tic waves,mainly spikes,were detected by wire⁃less EEG.Compared with PTZ group,intranasal Rb1 increased mice weight(P<0.01)and seizure latency(P<0.05),reduced seizure stage(P<0.01)and EEG spikes.In addition,Rb1 significantly reduced neuron loss(P<0.01)indicated by NeuN staining and decreased the number of acti⁃vated microglia(P<0.01)indicated by Iba-1 staining in the cortex and CA1 area of hippocam⁃pus.Moreover,Rb1 reduced the decrease of GLT-1 and GS expression(P<0.05)induced by PTZ.CONCLUTION Intranasal Rb1 has anti-epi⁃leptic effects on PTZ mice.Moreover,Intranasal Rb1 affects the functions of neurons,astrocytes and microglia through regulating the expression of GLT and GS in astrocytes,which may be related to its anti-epileptic effect.展开更多
Psychogenic nonepileptic seizures (PNES) are episodes of movement, sensation or behavior changes similar to epileptic seizures but without neurological origin. They are somatic manifestations of psychological distress...Psychogenic nonepileptic seizures (PNES) are episodes of movement, sensation or behavior changes similar to epileptic seizures but without neurological origin. They are somatic manifestations of psychological distress. The aim of this article is to provide a comprehensive review of the practical aspects of this, most often misdiagnosed disorder, which will be of clinical relevance to all practicing neurologists. Patients with PNES are often misdiagnosed and treated for epilepsy for years, resulting in significant morbidity. Video-EEG monitoring is the gold standard for diagnosis. Five to ten percent of outpatient epilepsy populations and 20 to 40 percent of inpatient and specialty epilepsy center patients have PNES. These patients inevitably have comorbid psychiatric illnesses, most commonly depression, post-traumatic stress disorder (PTSD), other dissociative and somatoform disorders, and personality pathology, especially borderline type. Many have a history of sexual and physical abuse. 75 to 85 percent of patients with PNES are women. Although PNES can occur at any age, they typically begin in young adulthood. Treatment involves discontinuing antiepileptic drugs in patients without concurrent epilepsy and referring for appropriate psychiatric care. Additional larger controlled studies to determine the best treatment modalities are needed.展开更多
<strong>Background:</strong><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;"> The epileptic encephalo...<strong>Background:</strong><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;"> The epileptic encephalopathies collectively</span></span></span><span><span><span style="font-family:""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">exact an immense personal, medical, and financial toll on</span></span></span><span><span><span style="font-family:""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">the affected children, their families, and</span></span></span><span><span><span style="font-family:""> </span></span></span><span><span><span style="font-family:""><span style="font-family:Verdana;">the healthcare system.</span><b><span style="font-family:Verdana;"> Objective:</span></b><span style="font-family:Verdana;"> This study was aimed to delineate the clinical spectrum of patients with Epileptic encephalopathies (EEs) and classify them under various epileptic syndromes. </span><b><span style="font-family:Verdana;">Methods:</span></b><span style="font-family:Verdana;"> This was a cross-sectional study that was carried out in the department of Neurophysiology of the National Institute of Neurosciences and Hospital, Bangladesh from July 2016 to June 2019.</span></span></span></span><span><span><span style="font-family:""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">Children with recurrent seizures which w</span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">ere </span></span></span><span><span><span style="font-family:""><span style="font-family:Verdana;">difficult to control and associated with developmental arrest or regression in absence of a progressive brain pathology were considered to be suffering from EE. Children under 12 years of age fulfilling the inclusion criteria were enrolled in the study. These patients were evaluated clinically and Electroencephalography (EEG) was done in all children at presentation. Based on the clinical profile and EEG findings the patients were categorized under various epileptic syndromes according to International League Against Epilepsy (ILAE) classification 2010.</span><b><span style="font-family:Verdana;"> Results:</span></b><span style="font-family:Verdana;"> A total of 1256 children under 12 years of age were referred to the Neurophysiology Department. Among them, 162</span></span></span></span><span><span><span style="font-family:""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">(12.90%) fulfilled the inclusion criteria. Most of the patients were male (64.2%) and below 1 year (37.7%) of age. The majority (56.8%) were delivered at the hospital and 40.1% had a history of perinatal asphyxia. Development was age-appropriate before the onset of a seizure in 38.9% of cases. Most (53.7%) of the patients had seizure onset within 3 months of age. Categorization of Epileptic syndromes found that majority had West Syndrome (WS)</span></span></span><span><span><span style="font-family:""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">(37.65%) followed by Lennox-Gastaut syndrome (LGS) (22.22%), Otahara syndrome (11.73%), Continuous spike-and-wave during sleep (CSWS) (5.66%), Myoclonic astatic epilepsy (MAE)</span></span></span><span><span><span style="font-family:""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">(4.94%), Early myoclonic encephalopathy (EME) (3.7%), Dravet</span></span></span><span><span><span style="font-family:""> </span></span></span><span><span><span style="font-family:""><span style="font-family:Verdana;">syndrome (3.7%) and Landau-Kleffner syndrome (LKS) (1.23%). 9.26% of syndromes were unclassified. </span><b><span style="font-family:Verdana;">Conclusion:</span></b><span style="font-family:Verdana;"> EEG was found to be a useful tool in the evaluation of Epileptic encephalopathies. The clinico-electroencephalographic features are age-related. Their recognition and appropriate management are critical.</span></span></span></span>展开更多
Background: Moderate to severe hypoxic-ischemic encephalopathy (HIE) in neonates is often treated with hypothermia. However, some neonates may experience epileptic seizures during therapeutic hypothermia (TH). Data on...Background: Moderate to severe hypoxic-ischemic encephalopathy (HIE) in neonates is often treated with hypothermia. However, some neonates may experience epileptic seizures during therapeutic hypothermia (TH). Data on the electrophysiologic and evolutionary aspects of these seizures are scarce in African countries. Objectives: To determine the types of epileptic seizures caused by HIE in neonates in Brazzaville;to describe the evolution of background EEG activities during TH and rewarming;to report the evolution of epileptic seizures. Methods: This was a cross-sectional, descriptive study conducted from January 2020 to July 2022. It took place in Brazzaville in the Neonatology Department of the Blanche Gomez Mother and Child Hospital. It focused on term neonates suffering from moderate or severe HIE. They were treated with hypothermia combined with phenobarbital for 72 hours. Results: Among 36 neonates meeting inclusion criteria, there were 18 boys and 18 girls. Thirty-one (86.1%) neonates had grade 2 and 5 (13.9%) grade 3 HIE. In our neonates, HIE had induced isolated electrographic seizures (n = 11;30.6%), electroclinical seizures (n = 25;69.4%), and 6 types of background EEG activity. During TH and rewarming, there were 52.8% of patients with improved background EEG activity, 41.7% of patients with unchanged background EEG activity, and 5.5% of patients with worsened background EEG activity. At the end of rewarming, only 9 (25%) patients still had seizures. Conclusion: Isolated electrographic and electroclinical seizures are the only pathological entities found in our studied population. In neonates with moderate HIE, the applied therapeutic strategy positively influences the evolution of both seizures and background EEG activity. On the other hand, in neonates with severe HIE, the same therapeutic strategy is ineffective. .展开更多
We examined a total of 16 children with epileptic encephalopathy using fluorine-18-fluoro-2-deoxy-D-glucose （18F-FDG） positron emission computed tomography （PET）, magnetic resonance imaging （MRI） and electroence...We examined a total of 16 children with epileptic encephalopathy using fluorine-18-fluoro-2-deoxy-D-glucose （18F-FDG） positron emission computed tomography （PET）, magnetic resonance imaging （MRI） and electroencephalography. Children with infantile spasms showed significant mental retardation, severely abnormal electroencephalogram recordings, and bilateral diffuse cerebral cortex hypometabolism with I^F-FDG PET imaging. MRI in these cases showed brain atrophy, multi-micropolygyria, macrogyria, and porencephalia. In cases with Lennox-Gastaut syndrome, 18F-FDG PET showed bilateral diffuse glucose hypometabolism, while MRI showed cortical atrophy, heterotopic gray matter and tuberous sclerosis. MRI in cases with myoclonic encephalopathy demonstrated bilateral frontal and temporal cortical and white matter atrophy and 18F-FDG PET imaging showed bilateral frontal lobe atrophy with reduced bilateral frontal cortex, occipital cortex, temporal cortex and cerebellar glucose uptake. In children who could not be clearly classified, MRI demonstrated cerebral cortical atrophy and ~aF-FDG PET exhibited multifocal glucose hypometabolism. Overall, this study demonstrated that the degree of brain metabolic abnormality was consistent with clinical seizure severity. In addition, ~SF-FDG PET imaging after treatment was consistent with clinical outcomes. These findings indicate that ~SF-FDG PET can be used to assess the severity of brain injury and prognosis in children with epileptic encephalopathy.展开更多
The visual analysis of common neurological disorders such as epileptic seizures in electroencephalography(EEG) is an oversensitive operation and prone to errors,which has motivated the researchers to develop effective...The visual analysis of common neurological disorders such as epileptic seizures in electroencephalography(EEG) is an oversensitive operation and prone to errors,which has motivated the researchers to develop effective automated seizure detection methods.This paper proposes a robust automatic seizure detection method that can establish a veritable diagnosis of these diseases.The proposed method consists of three steps:(i) remove artifact from EEG data using Savitzky-Golay filter and multi-scale principal component analysis(MSPCA),(ii) extract features from EEG signals using signal decomposition representations based on empirical mode decomposition(EMD),discrete wavelet transform(DWT),and dual-tree complex wavelet transform(DTCWT) allowing to overcome the non-linearity and non-stationary of EEG signals,and(iii) allocate the feature vector to the relevant class(i.e.,seizure class "ictal" or free seizure class "interictal") using machine learning techniques such as support vector machine(SVM),k-nearest neighbor(k-NN),and linear discriminant analysis(LDA).The experimental results were based on two EEG datasets generated from the CHB-MIT database with and without overlapping process.The results obtained have shown the effectiveness of the proposed method that allows achieving a higher classification accuracy rate up to 100% and also outperforms similar state-of-the-art methods.展开更多
The problem of automated seizure detection is treated using clinical electroencephalograms(EEG) and machine learning algorithms on the Temple University Hospital EEG Seizure Corpus(TUSZ).Performances on this complex d...The problem of automated seizure detection is treated using clinical electroencephalograms(EEG) and machine learning algorithms on the Temple University Hospital EEG Seizure Corpus(TUSZ).Performances on this complex data set are still not encountering expectations.The purpose of this work is to determine to what extent the use of larger amount of data can help to improve the performances.Two methods are explored:a standard partitioning on a recent and larger version of the TUSZ,and a leave-one-out approach used to increase the amount of data for the training set.XGBoost,a fast implementation of the gradient boosting classifier,is the ideal algorithm for these tasks.The performances obtained are in the range of what is reported until now in the literature with deep learning models.We give interpretation to our results by identifying the most relevant features and analyzing performances by seizure types.We show that generalized seizures tend to be far better predicted than focal ones.We also notice that some EEG channels and features are more important than others to distinguish seizure from background.展开更多
The electroencephalogram (EEG) signal plays a key role in the diagnosis of epilepsy. Substantial data is generated by the EEG recordings of ambulatory recording systems, and detection of epileptic activity requires a ...The electroencephalogram (EEG) signal plays a key role in the diagnosis of epilepsy. Substantial data is generated by the EEG recordings of ambulatory recording systems, and detection of epileptic activity requires a time-consuming analysis of the complete length of the EEG time series data by a neurology expert. A variety of automatic epilepsy detection systems have been developed during the last ten years. In this paper, we investigate the potential of a recently-proposed statistical measure parameter regarded as Sample Entropy (SampEn), as a method of feature extraction to the task of classifying three different kinds of EEG signals (normal, interictal and ictal) and detecting epileptic seizures. It is known that the value of the SampEn falls suddenly during an epileptic seizure and this fact is utilized in the proposed diagnosis system. Two different kinds of classification models, back-propagation neural network (BPNN) and the recently-developed extreme learning machine (ELM) are tested in this study. Results show that the proposed automatic epilepsy detection system which uses sample entropy (SampEn) as the only input feature, together with extreme learning machine (ELM) classification model, not only achieves high classification accuracy (95.67%) but also very fast speed.展开更多
BAOKGROUND： Bcl-2 and Fas proteins are well known as anti-apoptotic and pro-apoptotic factors respectively. However, whether the anti-epileptic mechanism of low-frequency repetitive transcranial magnetic stimulation ...BAOKGROUND： Bcl-2 and Fas proteins are well known as anti-apoptotic and pro-apoptotic factors respectively. However, whether the anti-epileptic mechanism of low-frequency repetitive transcranial magnetic stimulation （rTMS） involves an anti-apoptotic effect via regulating Bcl-2 and Fas protein expression remains to be determined. OBJECTIVE： To verify the correlation between the anti-epileptic mechanism following pretreatment of low-frequency rTMS and anti-hippocampal apoptosis. DESIGN, TIME AND SETTING： A randomized controlled animal experiment was performed at Institute of Neurological Disorders, Affiliated Hospital of North Sichuan Medical College between September 2007 and March 2008. MATERIALS： Pilocarpine （053K13011） was provided by Sigma, USA; lithium was provided by Shanghai Biotechnology Co., Ltd., China; Dantec Maglite-r25 rTMS instrument was provided by Dundee, Denmark. METHODS： A total of 21 adult male Wistar rats were randomly divided into control （n = 6）, rTMS pretreatment （n = 9）, and sham-stimulation （n = 6） groups. The rTMS pretreatment group was pretreated with low-frequency rTMS （0.5 Hz, 75% threshold intensity, 20 times/bundle, and 5 bundles/day）, while the sham-stimulation group was sham-stimulated with a similar sound for 7 successive days to establish lithium-pilocarpine-induced epileptic state models. MAIN OUTCOME MEASURES： Epileptic stroke latency; neuronal morphology was observed using hematoxylin and eosin staining; mean positive-reactive cell number and mean absorbance of Bcl-2 and Fas protein in the hippocampal CA1 region was observed using immunohistochemistry. RESULTS： Epileptic latency in the rTMS pretreatment group was significantly enhanced （P 〈 0.01）, and a number of degenerated neurons were observed to be apoptotic. Bcl-2 protein expression increased at each time point, but Fas protein expression decreased （P 〈 0.01）. CONCLUSION： Low-frequency rTMS has an anti-epileptic effect, which may be via regulation of Bcl-2 and Fas protein expression in the hippocampal region.展开更多
We are here to present a new method for the classification of epileptic seizures from electroencephalogram(EEG) signals.It consists of applying empirical mode decomposition(EMD) to extract the most relevant intrinsic ...We are here to present a new method for the classification of epileptic seizures from electroencephalogram(EEG) signals.It consists of applying empirical mode decomposition(EMD) to extract the most relevant intrinsic mode functions(IMFs) and subsequent computation of the Teager and instantaneous energy,Higuchi and Petrosian fractal dimension,and detrended fluctuation analysis(DFA) for each IMF.We validated the method using a public dataset of 24 subjects with EEG signals from 22 channels and showed that it is possible to classify the epileptic seizures,even with segments of six seconds and a smaller number of channels(e.g.,an accuracy of0.93 using five channels).We were able to create a general machine-learning-based model to detect epileptic seizures of new subjects using epileptic-seizure data from various subjects,after reducing the number of instances,based on the k-means algorithm.展开更多
Synaptic vesicle protein 2A（SV2A） involvement has been reported in the animal models of epilepsy and in human intractable epilepsy. The difference between pharmacosensitive epilepsy and pharmacoresistant epilepsy re...Synaptic vesicle protein 2A（SV2A） involvement has been reported in the animal models of epilepsy and in human intractable epilepsy. The difference between pharmacosensitive epilepsy and pharmacoresistant epilepsy remains poorly understood. The present study aimed to observe the hippocampus SV2 A protein expression in amygdale-kindling pharmacoresistant epileptic rats. The pharmacosensitive epileptic rats served as control. Amygdaloid-kindling model of epilepsy was established in 100 healthy adult male Sprague-Dawley rats. The kindled rat model of epilepsy was used to select pharmacoresistance by testing their seizure response to phenytoin and phenobarbital. The selected pharmacoresistant rats were assigned to a pharmacoresistant epileptic group（PRE group）. Another 12 pharmacosensitive epileptic rats（PSE group） served as control. Immunohistochemistry,real-time PCR and Western blotting were used to determine SV2 A expression in the hippocampus tissue samples from both the PRE and the PSE rats. Immunohistochemistry staining showed that SV2 A was mainly accumulated in the cytoplasm of the neurons,as well as along their dendrites throughout all subfields of the hippocampus. Immunoreactive staining level of SV2A-positive cells was 0.483±0.304 in the PRE group and 0.866±0.090 in the PSE group（P〈0.05）. Real-time PCR analysis demonstrated that 2-ΔΔCt value of SV2 A m RNA was 0.30±0.43 in the PRE group and 0.76±0.18 in the PSE group（P〈0.05）. Western blotting analysis obtained the similar findings（0.27±0.21 versus 1.12±0.21,P〈0.05）. PRE rats displayed a significant decrease of SV2 A in the brain. SV2 A may be associated with the pathogenesis of intractable epilepsy of the amygdaloid-kindling rats.展开更多
Suppression of epileptic seizure byacupuncture was described early in the an-cient medical literature,and now this treat-ment is occasionally seen reported.The chiefadvantage of the acupuncture treatment isabsence of ...Suppression of epileptic seizure byacupuncture was described early in the an-cient medical literature,and now this treat-ment is occasionally seen reported.The chiefadvantage of the acupuncture treatment isabsence of side-effects which antiepilepticdrugs usually have.Patients showing no re-sponse to drugs have been reported curedwhen treated by acupuncture.展开更多
This special issue of The Journal of Biomedical Research features novel studies on epileptic seizure detection and prediction based on advanced EEG signal processing and machine learning algorithms.The articles select...This special issue of The Journal of Biomedical Research features novel studies on epileptic seizure detection and prediction based on advanced EEG signal processing and machine learning algorithms.The articles selected present important findings including new experimental results and theoretical studies.展开更多
Detection of epileptic seizures on the basis of Electroencephalogram(EEG)recordings is a challenging task due to the complex,non-stationary and non-linear nature of these biomedical signals.In the existing literature,...Detection of epileptic seizures on the basis of Electroencephalogram(EEG)recordings is a challenging task due to the complex,non-stationary and non-linear nature of these biomedical signals.In the existing literature,a number of automatic epileptic seizure detection methods have been proposed that extract useful features from EEG segments and classify them using machine learning algorithms.Some characterizing features of epileptic and non-epileptic EEG signals overlap;therefore,it requires that analysis of signals must be performed from diverse perspectives.Few studies analyzed these signals in diverse domains to identify distinguishing characteristics of epileptic EEG signals.To pose the challenge mentioned above,in this paper,a fuzzy-based epileptic seizure detection model is proposed that incorporates a novel feature extraction and selection method along with fuzzy classifiers.The proposed work extracts pattern features along with time-domain,frequencydomain,and non-linear analysis of signals.It applies a feature selection strategy on extracted features to get more discriminating features that build fuzzy machine learning classifiers for the detection of epileptic seizures.The empirical evaluation of the proposed model was conducted on the benchmark Bonn EEG dataset.It shows significant accuracy of 98%to 100%for normal vs.ictal classification cases while for three class classification of normal vs.inter-ictal vs.ictal accuracy reaches to above 97.5%.The obtained results for ten classification cases(including normal,seizure or ictal,and seizure-free or inter-ictal classes)prove the superior performance of proposed work as compared to other state-of-the-art counterparts.展开更多
Machine learning (ML) becomes a familiar topic among decisionmakers in several domains, particularly healthcare. Effective design of MLmodels assists to detect and classify the occurrence of diseases using healthcared...Machine learning (ML) becomes a familiar topic among decisionmakers in several domains, particularly healthcare. Effective design of MLmodels assists to detect and classify the occurrence of diseases using healthcaredata. Besides, the parameter tuning of the ML models is also essentialto accomplish effective classification results. This article develops a novelred colobuses monkey optimization with kernel extreme learning machine(RCMO-KELM) technique for epileptic seizure detection and classification.The proposed RCMO-KELM technique initially extracts the chaotic, time,and frequency domain features in the actual EEG signals. In addition, the minmax normalization approach is employed for the pre-processing of the EEGsignals. Moreover, KELM model is used for the detection and classificationof epileptic seizures utilizing EEG signal. Furthermore, the RCMO techniquewas utilized for the optimal parameter tuning of the KELM technique insuch a way that the overall detection outcomes can be considerably enhanced.The experimental result analysis of the RCMO-KELM technique has beenexamined using benchmark dataset and the results are inspected under severalaspects. The comparative result analysis reported the better outcomes of theRCMO-KELM technique over the recent approaches with the accuy of 0.956.展开更多
This present study was aimed to investigate the localizable diagnostic value of magnetoencephalography （MEG） combined with synthetic aperture magnetometry （SAM） in childhood absence epilepsy （CAE）. Thirteen CAE ...This present study was aimed to investigate the localizable diagnostic value of magnetoencephalography （MEG） combined with synthetic aperture magnetometry （SAM） in childhood absence epilepsy （CAE）. Thirteen CAE patients underwent MEG detection at resting state and after hyperventilation, and then the epileptic loci were located by SAM. In the thirteen CAE patients, epileptic foci were found in five cases （38.5%）, and they were all located in the bilateral frontal lobe, suggesting that the frontal lobe in some CAE patients may serve as the epileptic foci. Our findings indicate that MEG combined with SAM could be of diagnostic value in localizing the epileptic foci in certain CAE patients.展开更多
文摘In the field of precision healthcare,where accurate decision-making is paramount,this study underscores the indispensability of eXplainable Artificial Intelligence(XAI)in the context of epilepsy management within the Internet of Medical Things(IoMT).The methodology entails meticulous preprocessing,involving the application of a band-pass filter and epoch segmentation to optimize the quality of Electroencephalograph(EEG)data.The subsequent extraction of statistical features facilitates the differentiation between seizure and non-seizure patterns.The classification phase integrates Support Vector Machine(SVM),K-Nearest Neighbor(KNN),and Random Forest classifiers.Notably,SVM attains an accuracy of 97.26%,excelling in the precision,recall,specificity,and F1 score for identifying seizures and non-seizure instances.Conversely,KNN achieves an accuracy of 72.69%,accompanied by certain trade-offs.The Random Forest classifierstands out with a remarkable accuracy of 99.89%,coupled with an exceptional precision(99.73%),recall(100%),specificity(99.80%),and F1 score(99.86%),surpassing both SVM and KNN performances.XAI techniques,namely Local Interpretable ModelAgnostic Explanations(LIME)and SHapley Additive exPlanation(SHAP),enhance the system’s transparency.This combination of machine learning and XAI not only improves the reliability and accuracy of the seizure detection system but also enhances trust and interpretability.Healthcare professionals can leverage the identified important features and their dependencies to gain deeper insights into the decision-making process,aiding in informed diagnosis and treatment decisions for patients with epilepsy.
基金the National Social Science Foundation of China(No.21BTQ106),the Natural Science Foundation of Beijing(No.7222187),and the Key Project of Innovation Cultivation Fund of the Seventh Medical Center of PLA General Hospital(No.qzx-2023-1)。
文摘Behavioral scoring based on clinical observations remains the gold standard for screening,diagnosing,and evaluating infantile epileptic spasm syndrome(IESS).The accurate identification of seizures is crucial for clinical diagnosis and assessment.In this study,we propose an innovative seizure detection method based on video feature recognition of patient spasms.To capture the temporal characteristics of the spasm behavior presented in the videos effectively,we incorporate asymmetric convolutions and convolution–batch normalization–ReLU(CBR)modules.Specifically within the 3D-ResNet residual blocks,we split the larger convolutional kernels into two asymmetric 3D convolutional kernels.These kernels are connected in series to enhance the ability of the convolutional layers to extract key local features,both horizontally and vertically.In addition,we introduce a 3D convolutional block attention module to enhance the spatial correlations between video frame channels efficiently.To improve the generalization ability,we design a composite loss function that combines cross-entropy loss with triplet loss to balance the classification and similarity requirements.We train and evaluate our method using the PLA IESS-VIDEO dataset,achieving an average seizure recognition accuracy of 90.59%,precision of 90.94%,and recall of 87.64%.To validate its generalization capability further,we conducted external validation using six different patient monitoring videos compared with assessments by six human experts from various medical centers.The final test results demonstrate that our method achieved a recall of 0.6476,surpassing the average level achieved by human experts(0.5595),while attaining a high F1-score of 0.7219.These findings have substantial significance for the long-term assessment of patients with IESS.
基金supported by the Natural Science Foundation of Sichuan Province of China,Nos.2022NSFSC1545 (to YG),2022NSFSC1387 (to ZF)the Natural Science Foundation of Chongqing of China,Nos.CSTB2022NSCQ-LZX0038,cstc2021ycjh-bgzxm0035 (both to XT)+3 种基金the National Natural Science Foundation of China,No.82001378 (to XT)the Joint Project of Chongqing Health Commission and Science and Technology Bureau,No.2023QNXM009 (to XT)the Science and Technology Research Program of Chongqing Education Commission of China,No.KJQN202200435 (to XT)the Chongqing Talents:Exceptional Young Talents Project,No.CQYC202005014 (to XT)。
文摘Epilepsy can be defined as a dysfunction of the brain network,and each type of epilepsy involves different brain-network changes that are implicated diffe rently in the control and propagation of interictal or ictal discharges.Gaining more detailed information on brain network alterations can help us to further understand the mechanisms of epilepsy and pave the way for brain network-based precise therapeutic approaches in clinical practice.An increasing number of advanced neuroimaging techniques and electrophysiological techniques such as diffusion tensor imaging-based fiber tra ctography,diffusion kurtosis imaging-based fiber tractography,fiber ball imagingbased tra ctography,electroencephalography,functional magnetic resonance imaging,magnetoencephalography,positron emission tomography,molecular imaging,and functional ultrasound imaging have been extensively used to delineate epileptic networks.In this review,we summarize the relevant neuroimaging and neuroelectrophysiological techniques for assessing structural and functional brain networks in patients with epilepsy,and extensively analyze the imaging mechanisms,advantages,limitations,and clinical application ranges of each technique.A greater focus on emerging advanced technologies,new data analysis software,a combination of multiple techniques,and the construction of personalized virtual epilepsy models can provide a theoretical basis to better understand the brain network mechanisms of epilepsy and make surgical decisions.
基金supported by the Key Project of Sichuan Provincial Education Department,No.(2010)597
文摘Although low-frequency repetitive transcranial magnetic simulation can potentially treat epilepsy, its underlying mechanism remains unclear. This study investigated the influence of low-frequency re-petitive transcranial magnetic simulation on changes in several nonlinear dynamic electroenceph-alographic parameters in rats with chronic epilepsy and explored the mechanism underlying repeti-tive transcranial magnetic simulation-induced antiepileptic effects. An epilepsy model was estab-lished using lithium-pilocarpine intraperitoneal injection into adult Sprague-Dawley rats, which were then treated with repetitive transcranial magnetic simulation for 7 consecutive days. Nonlinear elec-electroencephalographic parameters were obtained from the rats at 7, 14, and 28 days post-stimulation. Results showed significantly lower mean correlation-dimension and Kolmogo-rov-entropy values for stimulated rats than for non-stimulated rats. At 28 days, the complexity and point-wise correlation dimensional values were lower in stimulated rats. Low-frequency repetitive transcranial magnetic simulation has suppressive effects on electrical activity in epileptic rats, thus explaining its effectiveness in treating epilepsy.
文摘OBJECTIVE To evaluate whether ginsenoside Rb1 has antiepileptic effects on pen⁃tylenetetrazole(PTZ)-induced epileptic mice via intranasal therapeutic administration.METHODS Rb1 monoclonal antibody was used to observe the distribution of Rb120 mg·kg-1 in mouse brain tissues under different administration routes and to explore the feasibility of intranasal Rb1.PTZ was injected intraperitoneally into healthy ICR mice every 48 hours to construct a tonic-clonic epileptic model.Then Rb120 or 40 mg·kg-1 or valproate 300 mg·kg-1 or saline was administered intranasally for 30 d,and PTZ was continued every five days to imitate occa⁃sional convulsions in the clinic.Racine scale(RCS)and wireless electroencephalogram(EEG)monitoring were used to assess the presence and severity of seizure.Immunofluorescence(IF)was performed after drug treatment to evalu⁃ate the effect of Rb1 on brain neuron,microglia and astrocyte in epileptic mice.RESULTS Rb1 had specific binding with anti-Rb1 in the brain under different administration routes,and intrana⁃sal Rb1 was able to enter the brain and play a therapeutic role(P<0.01).PTZ-injured mice pre⁃sented body mass loss,higher seizure stage and shorter seizure latency.At the same time,epilep⁃tic waves,mainly spikes,were detected by wire⁃less EEG.Compared with PTZ group,intranasal Rb1 increased mice weight(P<0.01)and seizure latency(P<0.05),reduced seizure stage(P<0.01)and EEG spikes.In addition,Rb1 significantly reduced neuron loss(P<0.01)indicated by NeuN staining and decreased the number of acti⁃vated microglia(P<0.01)indicated by Iba-1 staining in the cortex and CA1 area of hippocam⁃pus.Moreover,Rb1 reduced the decrease of GLT-1 and GS expression(P<0.05)induced by PTZ.CONCLUTION Intranasal Rb1 has anti-epi⁃leptic effects on PTZ mice.Moreover,Intranasal Rb1 affects the functions of neurons,astrocytes and microglia through regulating the expression of GLT and GS in astrocytes,which may be related to its anti-epileptic effect.
文摘Psychogenic nonepileptic seizures (PNES) are episodes of movement, sensation or behavior changes similar to epileptic seizures but without neurological origin. They are somatic manifestations of psychological distress. The aim of this article is to provide a comprehensive review of the practical aspects of this, most often misdiagnosed disorder, which will be of clinical relevance to all practicing neurologists. Patients with PNES are often misdiagnosed and treated for epilepsy for years, resulting in significant morbidity. Video-EEG monitoring is the gold standard for diagnosis. Five to ten percent of outpatient epilepsy populations and 20 to 40 percent of inpatient and specialty epilepsy center patients have PNES. These patients inevitably have comorbid psychiatric illnesses, most commonly depression, post-traumatic stress disorder (PTSD), other dissociative and somatoform disorders, and personality pathology, especially borderline type. Many have a history of sexual and physical abuse. 75 to 85 percent of patients with PNES are women. Although PNES can occur at any age, they typically begin in young adulthood. Treatment involves discontinuing antiepileptic drugs in patients without concurrent epilepsy and referring for appropriate psychiatric care. Additional larger controlled studies to determine the best treatment modalities are needed.
文摘<strong>Background:</strong><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;"> The epileptic encephalopathies collectively</span></span></span><span><span><span style="font-family:""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">exact an immense personal, medical, and financial toll on</span></span></span><span><span><span style="font-family:""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">the affected children, their families, and</span></span></span><span><span><span style="font-family:""> </span></span></span><span><span><span style="font-family:""><span style="font-family:Verdana;">the healthcare system.</span><b><span style="font-family:Verdana;"> Objective:</span></b><span style="font-family:Verdana;"> This study was aimed to delineate the clinical spectrum of patients with Epileptic encephalopathies (EEs) and classify them under various epileptic syndromes. </span><b><span style="font-family:Verdana;">Methods:</span></b><span style="font-family:Verdana;"> This was a cross-sectional study that was carried out in the department of Neurophysiology of the National Institute of Neurosciences and Hospital, Bangladesh from July 2016 to June 2019.</span></span></span></span><span><span><span style="font-family:""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">Children with recurrent seizures which w</span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">ere </span></span></span><span><span><span style="font-family:""><span style="font-family:Verdana;">difficult to control and associated with developmental arrest or regression in absence of a progressive brain pathology were considered to be suffering from EE. Children under 12 years of age fulfilling the inclusion criteria were enrolled in the study. These patients were evaluated clinically and Electroencephalography (EEG) was done in all children at presentation. Based on the clinical profile and EEG findings the patients were categorized under various epileptic syndromes according to International League Against Epilepsy (ILAE) classification 2010.</span><b><span style="font-family:Verdana;"> Results:</span></b><span style="font-family:Verdana;"> A total of 1256 children under 12 years of age were referred to the Neurophysiology Department. Among them, 162</span></span></span></span><span><span><span style="font-family:""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">(12.90%) fulfilled the inclusion criteria. Most of the patients were male (64.2%) and below 1 year (37.7%) of age. The majority (56.8%) were delivered at the hospital and 40.1% had a history of perinatal asphyxia. Development was age-appropriate before the onset of a seizure in 38.9% of cases. Most (53.7%) of the patients had seizure onset within 3 months of age. Categorization of Epileptic syndromes found that majority had West Syndrome (WS)</span></span></span><span><span><span style="font-family:""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">(37.65%) followed by Lennox-Gastaut syndrome (LGS) (22.22%), Otahara syndrome (11.73%), Continuous spike-and-wave during sleep (CSWS) (5.66%), Myoclonic astatic epilepsy (MAE)</span></span></span><span><span><span style="font-family:""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">(4.94%), Early myoclonic encephalopathy (EME) (3.7%), Dravet</span></span></span><span><span><span style="font-family:""> </span></span></span><span><span><span style="font-family:""><span style="font-family:Verdana;">syndrome (3.7%) and Landau-Kleffner syndrome (LKS) (1.23%). 9.26% of syndromes were unclassified. </span><b><span style="font-family:Verdana;">Conclusion:</span></b><span style="font-family:Verdana;"> EEG was found to be a useful tool in the evaluation of Epileptic encephalopathies. The clinico-electroencephalographic features are age-related. Their recognition and appropriate management are critical.</span></span></span></span>
文摘Background: Moderate to severe hypoxic-ischemic encephalopathy (HIE) in neonates is often treated with hypothermia. However, some neonates may experience epileptic seizures during therapeutic hypothermia (TH). Data on the electrophysiologic and evolutionary aspects of these seizures are scarce in African countries. Objectives: To determine the types of epileptic seizures caused by HIE in neonates in Brazzaville;to describe the evolution of background EEG activities during TH and rewarming;to report the evolution of epileptic seizures. Methods: This was a cross-sectional, descriptive study conducted from January 2020 to July 2022. It took place in Brazzaville in the Neonatology Department of the Blanche Gomez Mother and Child Hospital. It focused on term neonates suffering from moderate or severe HIE. They were treated with hypothermia combined with phenobarbital for 72 hours. Results: Among 36 neonates meeting inclusion criteria, there were 18 boys and 18 girls. Thirty-one (86.1%) neonates had grade 2 and 5 (13.9%) grade 3 HIE. In our neonates, HIE had induced isolated electrographic seizures (n = 11;30.6%), electroclinical seizures (n = 25;69.4%), and 6 types of background EEG activity. During TH and rewarming, there were 52.8% of patients with improved background EEG activity, 41.7% of patients with unchanged background EEG activity, and 5.5% of patients with worsened background EEG activity. At the end of rewarming, only 9 (25%) patients still had seizures. Conclusion: Isolated electrographic and electroclinical seizures are the only pathological entities found in our studied population. In neonates with moderate HIE, the applied therapeutic strategy positively influences the evolution of both seizures and background EEG activity. On the other hand, in neonates with severe HIE, the same therapeutic strategy is ineffective. .
基金the National Natural Science Foundation of China, No. 81071046the Guangdong Provincial Science and Technology Program, No. 2009B030801250+1 种基金2010 Guangdong Provincial Science and Technology Program, No. 2010B031600159the Guangdong Province Natural Science Foundation, No. 7001205
文摘We examined a total of 16 children with epileptic encephalopathy using fluorine-18-fluoro-2-deoxy-D-glucose （18F-FDG） positron emission computed tomography （PET）, magnetic resonance imaging （MRI） and electroencephalography. Children with infantile spasms showed significant mental retardation, severely abnormal electroencephalogram recordings, and bilateral diffuse cerebral cortex hypometabolism with I^F-FDG PET imaging. MRI in these cases showed brain atrophy, multi-micropolygyria, macrogyria, and porencephalia. In cases with Lennox-Gastaut syndrome, 18F-FDG PET showed bilateral diffuse glucose hypometabolism, while MRI showed cortical atrophy, heterotopic gray matter and tuberous sclerosis. MRI in cases with myoclonic encephalopathy demonstrated bilateral frontal and temporal cortical and white matter atrophy and 18F-FDG PET imaging showed bilateral frontal lobe atrophy with reduced bilateral frontal cortex, occipital cortex, temporal cortex and cerebellar glucose uptake. In children who could not be clearly classified, MRI demonstrated cerebral cortical atrophy and ~aF-FDG PET exhibited multifocal glucose hypometabolism. Overall, this study demonstrated that the degree of brain metabolic abnormality was consistent with clinical seizure severity. In addition, ~SF-FDG PET imaging after treatment was consistent with clinical outcomes. These findings indicate that ~SF-FDG PET can be used to assess the severity of brain injury and prognosis in children with epileptic encephalopathy.
文摘The visual analysis of common neurological disorders such as epileptic seizures in electroencephalography(EEG) is an oversensitive operation and prone to errors,which has motivated the researchers to develop effective automated seizure detection methods.This paper proposes a robust automatic seizure detection method that can establish a veritable diagnosis of these diseases.The proposed method consists of three steps:(i) remove artifact from EEG data using Savitzky-Golay filter and multi-scale principal component analysis(MSPCA),(ii) extract features from EEG signals using signal decomposition representations based on empirical mode decomposition(EMD),discrete wavelet transform(DWT),and dual-tree complex wavelet transform(DTCWT) allowing to overcome the non-linearity and non-stationary of EEG signals,and(iii) allocate the feature vector to the relevant class(i.e.,seizure class "ictal" or free seizure class "interictal") using machine learning techniques such as support vector machine(SVM),k-nearest neighbor(k-NN),and linear discriminant analysis(LDA).The experimental results were based on two EEG datasets generated from the CHB-MIT database with and without overlapping process.The results obtained have shown the effectiveness of the proposed method that allows achieving a higher classification accuracy rate up to 100% and also outperforms similar state-of-the-art methods.
文摘The problem of automated seizure detection is treated using clinical electroencephalograms(EEG) and machine learning algorithms on the Temple University Hospital EEG Seizure Corpus(TUSZ).Performances on this complex data set are still not encountering expectations.The purpose of this work is to determine to what extent the use of larger amount of data can help to improve the performances.Two methods are explored:a standard partitioning on a recent and larger version of the TUSZ,and a leave-one-out approach used to increase the amount of data for the training set.XGBoost,a fast implementation of the gradient boosting classifier,is the ideal algorithm for these tasks.The performances obtained are in the range of what is reported until now in the literature with deep learning models.We give interpretation to our results by identifying the most relevant features and analyzing performances by seizure types.We show that generalized seizures tend to be far better predicted than focal ones.We also notice that some EEG channels and features are more important than others to distinguish seizure from background.
文摘The electroencephalogram (EEG) signal plays a key role in the diagnosis of epilepsy. Substantial data is generated by the EEG recordings of ambulatory recording systems, and detection of epileptic activity requires a time-consuming analysis of the complete length of the EEG time series data by a neurology expert. A variety of automatic epilepsy detection systems have been developed during the last ten years. In this paper, we investigate the potential of a recently-proposed statistical measure parameter regarded as Sample Entropy (SampEn), as a method of feature extraction to the task of classifying three different kinds of EEG signals (normal, interictal and ictal) and detecting epileptic seizures. It is known that the value of the SampEn falls suddenly during an epileptic seizure and this fact is utilized in the proposed diagnosis system. Two different kinds of classification models, back-propagation neural network (BPNN) and the recently-developed extreme learning machine (ELM) are tested in this study. Results show that the proposed automatic epilepsy detection system which uses sample entropy (SampEn) as the only input feature, together with extreme learning machine (ELM) classification model, not only achieves high classification accuracy (95.67%) but also very fast speed.
基金Youth Foundation Project of Sichuan Province, No. 04ZQ026-010
文摘BAOKGROUND： Bcl-2 and Fas proteins are well known as anti-apoptotic and pro-apoptotic factors respectively. However, whether the anti-epileptic mechanism of low-frequency repetitive transcranial magnetic stimulation （rTMS） involves an anti-apoptotic effect via regulating Bcl-2 and Fas protein expression remains to be determined. OBJECTIVE： To verify the correlation between the anti-epileptic mechanism following pretreatment of low-frequency rTMS and anti-hippocampal apoptosis. DESIGN, TIME AND SETTING： A randomized controlled animal experiment was performed at Institute of Neurological Disorders, Affiliated Hospital of North Sichuan Medical College between September 2007 and March 2008. MATERIALS： Pilocarpine （053K13011） was provided by Sigma, USA; lithium was provided by Shanghai Biotechnology Co., Ltd., China; Dantec Maglite-r25 rTMS instrument was provided by Dundee, Denmark. METHODS： A total of 21 adult male Wistar rats were randomly divided into control （n = 6）, rTMS pretreatment （n = 9）, and sham-stimulation （n = 6） groups. The rTMS pretreatment group was pretreated with low-frequency rTMS （0.5 Hz, 75% threshold intensity, 20 times/bundle, and 5 bundles/day）, while the sham-stimulation group was sham-stimulated with a similar sound for 7 successive days to establish lithium-pilocarpine-induced epileptic state models. MAIN OUTCOME MEASURES： Epileptic stroke latency; neuronal morphology was observed using hematoxylin and eosin staining; mean positive-reactive cell number and mean absorbance of Bcl-2 and Fas protein in the hippocampal CA1 region was observed using immunohistochemistry. RESULTS： Epileptic latency in the rTMS pretreatment group was significantly enhanced （P 〈 0.01）, and a number of degenerated neurons were observed to be apoptotic. Bcl-2 protein expression increased at each time point, but Fas protein expression decreased （P 〈 0.01）. CONCLUSION： Low-frequency rTMS has an anti-epileptic effect, which may be via regulation of Bcl-2 and Fas protein expression in the hippocampal region.
文摘We are here to present a new method for the classification of epileptic seizures from electroencephalogram(EEG) signals.It consists of applying empirical mode decomposition(EMD) to extract the most relevant intrinsic mode functions(IMFs) and subsequent computation of the Teager and instantaneous energy,Higuchi and Petrosian fractal dimension,and detrended fluctuation analysis(DFA) for each IMF.We validated the method using a public dataset of 24 subjects with EEG signals from 22 channels and showed that it is possible to classify the epileptic seizures,even with segments of six seconds and a smaller number of channels(e.g.,an accuracy of0.93 using five channels).We were able to create a general machine-learning-based model to detect epileptic seizures of new subjects using epileptic-seizure data from various subjects,after reducing the number of instances,based on the k-means algorithm.
基金supported by grants from National Natural Science Foundation of China(No.81241129/H0913)Guizhou Province Governor Special Funds(No.1065-09)and Guizhou High-level Personnel Scientific Funds(No.TZJF-2010-054)
文摘Synaptic vesicle protein 2A（SV2A） involvement has been reported in the animal models of epilepsy and in human intractable epilepsy. The difference between pharmacosensitive epilepsy and pharmacoresistant epilepsy remains poorly understood. The present study aimed to observe the hippocampus SV2 A protein expression in amygdale-kindling pharmacoresistant epileptic rats. The pharmacosensitive epileptic rats served as control. Amygdaloid-kindling model of epilepsy was established in 100 healthy adult male Sprague-Dawley rats. The kindled rat model of epilepsy was used to select pharmacoresistance by testing their seizure response to phenytoin and phenobarbital. The selected pharmacoresistant rats were assigned to a pharmacoresistant epileptic group（PRE group）. Another 12 pharmacosensitive epileptic rats（PSE group） served as control. Immunohistochemistry,real-time PCR and Western blotting were used to determine SV2 A expression in the hippocampus tissue samples from both the PRE and the PSE rats. Immunohistochemistry staining showed that SV2 A was mainly accumulated in the cytoplasm of the neurons,as well as along their dendrites throughout all subfields of the hippocampus. Immunoreactive staining level of SV2A-positive cells was 0.483±0.304 in the PRE group and 0.866±0.090 in the PSE group（P〈0.05）. Real-time PCR analysis demonstrated that 2-ΔΔCt value of SV2 A m RNA was 0.30±0.43 in the PRE group and 0.76±0.18 in the PSE group（P〈0.05）. Western blotting analysis obtained the similar findings（0.27±0.21 versus 1.12±0.21,P〈0.05）. PRE rats displayed a significant decrease of SV2 A in the brain. SV2 A may be associated with the pathogenesis of intractable epilepsy of the amygdaloid-kindling rats.
文摘Suppression of epileptic seizure byacupuncture was described early in the an-cient medical literature,and now this treat-ment is occasionally seen reported.The chiefadvantage of the acupuncture treatment isabsence of side-effects which antiepilepticdrugs usually have.Patients showing no re-sponse to drugs have been reported curedwhen treated by acupuncture.
文摘This special issue of The Journal of Biomedical Research features novel studies on epileptic seizure detection and prediction based on advanced EEG signal processing and machine learning algorithms.The articles selected present important findings including new experimental results and theoretical studies.
基金This work was supported by the Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(Grant No.NRF-2020R1I1A3074141)the Brain Research Program through the NRF funded by the Ministry of Science,ICT and Future Planning(Grant No.NRF-2019M3C7A1020406),and“Regional Innovation Strategy(RIS)”through the NRF funded by the Ministry of Education.
文摘Detection of epileptic seizures on the basis of Electroencephalogram(EEG)recordings is a challenging task due to the complex,non-stationary and non-linear nature of these biomedical signals.In the existing literature,a number of automatic epileptic seizure detection methods have been proposed that extract useful features from EEG segments and classify them using machine learning algorithms.Some characterizing features of epileptic and non-epileptic EEG signals overlap;therefore,it requires that analysis of signals must be performed from diverse perspectives.Few studies analyzed these signals in diverse domains to identify distinguishing characteristics of epileptic EEG signals.To pose the challenge mentioned above,in this paper,a fuzzy-based epileptic seizure detection model is proposed that incorporates a novel feature extraction and selection method along with fuzzy classifiers.The proposed work extracts pattern features along with time-domain,frequencydomain,and non-linear analysis of signals.It applies a feature selection strategy on extracted features to get more discriminating features that build fuzzy machine learning classifiers for the detection of epileptic seizures.The empirical evaluation of the proposed model was conducted on the benchmark Bonn EEG dataset.It shows significant accuracy of 98%to 100%for normal vs.ictal classification cases while for three class classification of normal vs.inter-ictal vs.ictal accuracy reaches to above 97.5%.The obtained results for ten classification cases(including normal,seizure or ictal,and seizure-free or inter-ictal classes)prove the superior performance of proposed work as compared to other state-of-the-art counterparts.
基金The authors extend their appreciation to the Deanship of Scientific Research at King Khalid University for funding this work under Grant Number(RGP2/42/43)Princess Nourah bint Abdulrahman University Researchers Supporting Project Number(PNURSP2022R136)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Machine learning (ML) becomes a familiar topic among decisionmakers in several domains, particularly healthcare. Effective design of MLmodels assists to detect and classify the occurrence of diseases using healthcaredata. Besides, the parameter tuning of the ML models is also essentialto accomplish effective classification results. This article develops a novelred colobuses monkey optimization with kernel extreme learning machine(RCMO-KELM) technique for epileptic seizure detection and classification.The proposed RCMO-KELM technique initially extracts the chaotic, time,and frequency domain features in the actual EEG signals. In addition, the minmax normalization approach is employed for the pre-processing of the EEGsignals. Moreover, KELM model is used for the detection and classificationof epileptic seizures utilizing EEG signal. Furthermore, the RCMO techniquewas utilized for the optimal parameter tuning of the KELM technique insuch a way that the overall detection outcomes can be considerably enhanced.The experimental result analysis of the RCMO-KELM technique has beenexamined using benchmark dataset and the results are inspected under severalaspects. The comparative result analysis reported the better outcomes of theRCMO-KELM technique over the recent approaches with the accuy of 0.956.
基金supported by Nanjing Medical Technology Development Grant (No. ZKM05033)
文摘This present study was aimed to investigate the localizable diagnostic value of magnetoencephalography （MEG） combined with synthetic aperture magnetometry （SAM） in childhood absence epilepsy （CAE）. Thirteen CAE patients underwent MEG detection at resting state and after hyperventilation, and then the epileptic loci were located by SAM. In the thirteen CAE patients, epileptic foci were found in five cases （38.5%）, and they were all located in the bilateral frontal lobe, suggesting that the frontal lobe in some CAE patients may serve as the epileptic foci. Our findings indicate that MEG combined with SAM could be of diagnostic value in localizing the epileptic foci in certain CAE patients.
