Stroke Electroencephalogram Data Synthesizing through Progressive Efficient Self-Attention Generative Adversarial Network

Early and timely diagnosis of stroke is critical for effective treatment,and the electroencephalogram(EEG)offers a low-cost,non-invasive solution.However,the shortage of high-quality patient EEG data often hampers the accuracy of diagnostic classification methods based on deep learning.To address this issue,our study designed a deep data amplification model named Progressive Conditional Generative Adversarial Network with Efficient Approximating Self Attention(PCGAN-EASA),which incrementally improves the quality of generated EEG features.This network can yield full-scale,fine-grained EEG features from the low-scale,coarse ones.Specially,to overcome the limitations of traditional generative models that fail to generate features tailored to individual patient characteristics,we developed an encoder with an effective approximating self-attention mechanism.This encoder not only automatically extracts relevant features across different patients but also reduces the computational resource consumption.Furthermore,the adversarial loss and reconstruction loss functions were redesigned to better align with the training characteristics of the network and the spatial correlations among electrodes.Extensive experimental results demonstrate that PCGAN-EASA provides the highest generation quality and the lowest computational resource usage compared to several existing approaches.Additionally,it significantly improves the accuracy of subsequent stroke classification tasks.

Electroencephalogram findings in 10 patients with post-stroke epilepsy:A retrospective study

BACKGROUND Post-stroke epilepsy is a common and easily overlooked complication of acute cerebrovascular disease.Long-term seizures can seriously affect the prognosis and quality of life of patients.Electroencephalogram(EEG)is the simplest way to diagnose epilepsy,and plays an important role in predicting seizures and guiding medication.AIM To explore the EEG characteristics of patients with post-stroke epilepsy and improve the detection rate of inter-seizure epileptiform discharges.METHODS From January 2017 to June 2020,10 patients with post-stroke epilepsy in our hospital were included.The clinical,imaging,and EEG characteristics were collected.The stroke location,seizure type,and ictal and interictal EEG manifestations of the patients with post-stroke epilepsy were then retrospectively analyzed.RESULTS In all 10 patients,epileptiform waves occurred in the side opposite to the stroke lesion during the interictal stage;these manifested as sharp wave,sharp-wave complex,or spike discharges in the anterior head lead of the side opposite to the lesion.CONCLUSION In EEG,epileptiform waves can occur in the side opposite to the stroke lesion in patients with post-stroke epilepsy.

Classification of Electroencephalogram Signals Using LSTM and SVM Based on Fast Walsh-Hadamard Transform

Classification of electroencephalogram(EEG)signals for humans can be achieved via artificial intelligence(AI)techniques.Especially,the EEG signals associated with seizure epilepsy can be detected to distinguish between epileptic and non-epileptic regions.From this perspective,an automated AI technique with a digital processing method can be used to improve these signals.This paper proposes two classifiers:long short-term memory(LSTM)and support vector machine(SVM)for the classification of seizure and non-seizure EEG signals.These classifiers are applied to a public dataset,namely the University of Bonn,which consists of 2 classes–seizure and non-seizure.In addition,a fast Walsh-Hadamard Transform(FWHT)technique is implemented to analyze the EEG signals within the recurrence space of the brain.Thus,Hadamard coefficients of the EEG signals are obtained via the FWHT.Moreover,the FWHT is contributed to generate an efficient derivation of seizure EEG recordings from non-seizure EEG recordings.Also,a k-fold cross-validation technique is applied to validate the performance of the proposed classifiers.The LSTM classifier provides the best performance,with a testing accuracy of 99.00%.The training and testing loss rates for the LSTM are 0.0029 and 0.0602,respectively,while the weighted average precision,recall,and F1-score for the LSTM are 99.00%.The results of the SVM classifier in terms of accuracy,sensitivity,and specificity reached 91%,93.52%,and 91.3%,respectively.The computational time consumed for the training of the LSTM and SVM is 2000 and 2500 s,respectively.The results show that the LSTM classifier provides better performance than SVM in the classification of EEG signals.Eventually,the proposed classifiers provide high classification accuracy compared to previously published classifiers.

Functional role of frontal electroencephalogram alpha asymmetry in the resting state in patients with depression:A review

Depression is a psychological disorder that affects the general public worldwide.It is particularly important to make an objective and accurate diagnosis of depression,and the measurement methods of brain activity have gradually received increasing attention.Resting electroencephalogram(EEG)alpha asymmetry in patients with depression shows changes in activation of the alpha frequency band of the left and right frontal cortices.In this paper,we review the findings of the relationship between frontal EEG alpha asymmetry in the resting state and depression.Based on worldwide studies,we found the following:(1)Compared with individuals without depression,those with depression showed greater right frontal EEG alpha asymmetry in the resting state.However,the pattern of frontal EEG alpha asymmetry in the resting state in depressive individuals seemed to disappear with age;(2)Compared with individuals without maternal depression,those with maternal depression showed greater right frontal EEG alpha asymmetry in the resting state,which indicated that genetic or experience-based influences have an impact on frontal EEG alpha asymmetry at rest;and(3)Frontal EEG alpha asymmetry in the resting state was stable,and little or no change occurred after antidepressant treatment.Finally,we concluded that the contrasting results may be due to differences in methodology,clinical characteristics,and participant characteristics.

Serum neuronal pentraxin 2 is related to cognitive dysfunction and electroencephalogram slow wave/fast wave frequency ratio in epilepsy

BACKGROUND Cognitive dysfunction in epileptic patients is a high-incidence complication.Its mechanism is related to nervous system damage during seizures,but there is no effective diagnostic biomarker.Neuronal pentraxin 2(NPTX2)is thought to play a vital role in neurotransmission and the maintenance of synaptic plasticity.This study explored how serum NPTX2 and electroencephalogram(EEG)slow wave/fast wave frequency ratio relate to cognitive dysfunction in patients with epilepsy.AIM To determine if serum NPTX2 could serve as a potential biomarker for diagnosing cognitive impairment in epilepsy patients.METHODS The participants of this study,conducted from January 2020 to December 2021,comprised 74 epilepsy patients with normal cognitive function(normal group),37 epilepsy patients with cognitive dysfunction[epilepsy patients with cognitive dysfunction(ECD)group]and 30 healthy people(control group).The minimental state examination(MMSE)scale was used to evaluate cognitive function.We determined serum NPTX2 levels using an enzyme-linked immunosorbent kit and calculated the signal value of EEG regions according to the EEG recording.Pearson correlation coefficient was used to analyze the correlation between serum NPTX2 and the MMSE score.RESULTS The serum NPTX2 level in the control group,normal group and ECD group were 240.00±35.06 pg/mL,235.80±38.01 pg/mL and 193.80±42.72 pg/mL,respectively.The MMSE score was lowest in the ECD group among the three,while no significant difference was observed between the control and normal groups.In epilepsy patients with cognitive dysfunction,NPTX2 level had a positive correlation with the MMSE score(r=0.367,P=0.0253)and a negative correlation with epilepsy duration(r=−0.443,P=0.0061)and the EEG slow wave/fast wave frequency ratio value in the temporal region(r=−0.339,P=0.039).CONCLUSION Serum NPTX2 was found to be related to cognitive dysfunction and the EEG slow wave/fast wave frequency ratio in patients with epilepsy.It is thus a potential biomarker for the diagnosis of cognitive impairment in patients with epilepsy.

Effects of low-frequency repetitive transcranial magnetic stimulation on electroencephalogram and seizure frequency in 15 patients with temporal lobe epilepsy following dipole source localization

BACKGROUND： Low-frequency repetitive transcranial magnetic stimulation （rTMS） has been shown to significantly reduce epileptiform discharges and control clinical seizures in intractable epilepsy patients. The location of epileptic foci and magnetic stimulation sites remain uncertain. The effects of rTMS on electroencephalogram and seizure remain unclear in epileptic patients following dipole source localization. OBJECTIVE： To investigate the effects of low-frequency rTMS on electroencephalogram and seizure in temporal lobe epilepsy patients after dipole source localization. DESIGN, TIME AND SETTING： The randomized, controlled study was performed at the outpatient clinic Department of Neurology, Hospital Affiliated to North Sichuan Medical College from December 2003 to February 2007. PARTICIPANTS： A total of 30 temporal lobe epilepsy patients, comprising 19 males and 11 females, aged 1749 years, presented with epileptiform discharges and were enrolled for this study. Disease course ranged between 1-6 years, with 1-5 seizures per month. Imaging examinations revealed 11 patients with structural changes in the brain. The patients were randomly and equally assigned into drug treatment and transcranial magnetic stimulation （TMS） groups. METHODS： Patients in the drug treatment group were orally treated with carbamazepine. Patients in the TMS group received oral carbamazepine treatment of and TMS. A Maglite-r25 magnetic stimulator （Dantec Dynamics, Denmark） was used to stimulate epileptic foci in the temporal lobe following electroencephalogram dipole localization （1 Hz, 90% threshold intensity, at a stimulation frequency of 500 times, once a day, for 7 days）. MAIN OUTCOME MEASURES： At 30 days after TMS, seizure frequency and rate of epileptiform discharges were observed in patients from both groups. Therapeutic safety was investigated during treatment. RESULTS： Within 30 days of treatment, there were no significant differences in seizure frequency between the TMS group （1.5 ± 0.3） seizures and the drug treatment group [（1.9± 0.4） seizures] （P 〉 0.05）. The rate of epileptiform discharges [27% （4/15）] was significantly less in the TMS group than in the drug treatment group [73% （11/15）] （P 〈 0.05）. During TMS, five patients suffered from transient mild headache, but were completely relieved within 2 hours. CONCLUSION： Low-frequency rTMS exhibited inhibitory effects on epileptiform discharges over a short period of time, and decreased seizure frequency to some degree. Results from the present study suggested that low-frequency rTMS is safe.

Prognostic value of dynamic electroencephalogram in comatose patients with different diseased regions

BACKGROUND： It has proved that dynamic electroencephalogram （EEG） is definite in judging the outcome of ischemic hypoxic comatose patients, EEG is more sensitive to the cortical affection, but not sensitive to the subcortical and brainstem affections, thus it is necessary to clarify the indications of this technique in the clinical application.OBJECTIVE： To observe and compare the prognostic value of dynamic EEG and Glasgow coma score in comatose patients with different diseased region.DESIGN： A clinical case-controlled observation.SETTING： Union Hospital of Fujian Medical University.PARTICIPANTS： Sixty-eight comatose patients were selected from the Union Hospital affiliated to Fujian Medical University from June 1998 to January 2005. The diseased regions were identified using cranial CT （n =43） or MR （n =25）. According to different primarily diseased regions, the comatose patients were divided into two groups： ① brainstem affection group （n =23）： 13 males and 10 females, 14 - 62 years of age; ②diffuse cortical affection group （n =45）： 28 males and 17 females, 23 - 75 years of age.METHODS： The dynamic EEG and Glasgow coma score were examined in the 45 comatose patients with primarily cortical affection and 22 comatose patients with primarily brainstem affection at acute phase. The patients were followed-up for 3 months to observe the outcome, The termination of outcome judgment was 3 months after attack or the death. The clinical outcome was classified as complete rehabilitation, survived with disability, death or vegetative state. Correlations of dynamic EEG and Glasgow coma score with the outcome of patients were analyzed. The correlations of dynamic EEG grades and Glasgow coma scores with the outcome were analyzed, and the prognostic value of dynamic EEG grades was compared between the two groups.MAIN OUTCOME MEASURES： ① Correlations of dynamic EEG and Glasgow coma score with the outcome of patients; ② Comparison of the prognostic value of dynamic EEG grades between the two groups.RESULTS： All the 68 patients were involved in the analysis of results. ① Correlations of dynamic EEG grades and Glasgow scores and their correlation analysis： EEG grades had significant negative correlation with Glasgow coma scores in both the cortical affection group and brainstem affection group （r = - 0.743,- 0.564, P 〈 0.01, 0.05）. In the cortical affection group, the Glasgow coma scores and dynamic EEG grades in the patients with the outcome of death or vegetative state were significantly different from those with the outcome of rehabilitation （P 〈 0.05 - 0.01）. In the brainstem affection group, the Glasgow coma scores were only significantly different between the patients with outcome of rehabilitation and death （P 〈 0.05）, and there was no significant difference in dynamic EEG grades among the three prognostic states （P 〉 0.05）. ②Comparison of the prognostic value of dynamic EEG grades between comatose patients with cortical affection and brainstem affection： The sensitivity, specificity and accuracy were all higher （P 〈 0.05）, while the error rate was lower （P〈0.05） in the cortical affection group than in the brainstem affection group.CONCLUSION： Dynamic EEG was valuable in predicting the outcome of comatose patients with primarily cortical affection, but it was not certainly valuable in those with primarily brainstem affection.

Detrended cross-correlation analysis of electroencephalogram

In the paper we use detrended cross-correlation analysis （DCCA） to study the electroencephalograms of healthy young subjects and healthy old subjects. It is found that the cross-correlation between different leads of a healthy young subject is larger than that of a healthy old subject. It was shown that the cross-correlation relationship decreases with the aging process and the phenomenon can help to diagnose whether the subject＇s brain function is healthy or not.

Discrimination of Motor Imagery Patterns by Electroencephalogram Phase Synchronization Combined With Frequency Band Energy

Central nerve signal evoked by thoughts can be directly used to control a robot or prosthetic devices without the involvement of the peripheral nerve and muscles.This is a new strategy of human-computer interaction.A method of electroencephalogram(EEG) phase synchronization combined with band energy was proposed to construct a feature vector for pattern recognition of brain-computer interaction based on EEG induced by motor imagery in this paper,rhythm and beta rhythm were first extracted from EEG by band pass filter and then the frequency band energy was calculated by the sliding time window;the instantaneous phase values were obtained using Hilbert transform and then the phase synchronization feature was calculated by the phase locking value(PLV) and the best time interval for extracting the phase synchronization feature was searched by the distribution of the PLV value in the time domain.Finally,discrimination of motor imagery patterns was performed by the support vector machine(SVM).The results showed that the phase synchronization feature more effective in4s-7s and the correct classification rate was 91.4%.Compared with the results achieved by a single EEG feature related to motor imagery,the correct classification rate was improved by 3.5 and4.3 percentage points by combining phase synchronization with band energy.These indicate that the proposed method is effective and it is expected that the study provides a way to improve the performance of the online real-time brain-computer interaction control system based on EEG related to motor imagery.

Approximate entropy and support vector machines for electroencephalogram signal classification

The automatic detection and identification of electroencephalogram waves play an important role in the prediction, diagnosis and treatment of epileptic seizures. In this study, a nonlinear dynamics index–approximate entropy and a support vector machine that has strong generalization ability were applied to classify electroencephalogram signals at epileptic interictal and ictal periods. Our aim was to verify whether approximate entropy waves can be effectively applied to the automatic real-time detection of epilepsy in the electroencephalogram, and to explore its generalization ability as a classifier trained using a nonlinear dynamics index. Four patients presenting with partial epileptic seizures were included in this study. They were all diagnosed with neocortex localized epilepsy and epileptic foci were clearly observed by electroencephalogram. The electroencephalogram data form the four involved patients were segmented and the characteristic values of each segment, that is, the approximate entropy, were extracted. The support vector machine classifier was constructed with the approximate entropy extracted from one epileptic case, and then electroencephalogram waves of the other three cases were classified, reaching a 93.33% accuracy rate. Our findings suggest that the use of approximate entropy allows the automatic real-time detection of electroencephalogram data in epileptic cases. The combination of approximate entropy and support vector machines shows good generalization ability for the classification of electroencephalogram signals for epilepsy.

Analysis of the effect of repeated-pulse transcranial magnetic stimulation at the Guangming point on electroencephalograms

Here, we administered repeated-pulse transcranial magnetic stimulation to healthy people at the left Guangming （GB37） and a mock point, and calculated the sample entropy of electroencephalo- gram signals using nonlinear dynamics. Additionally, we compared electroencephalogram sample entropy of signals in response to visual stimulation before, during, and after repeated-pulse tran- scranial magnetic stimulation at the Guangming. Results showed that electroencephalogram sample entropy at left （F3） and right （FP2） frontal electrodes were significantly different depending on where the magnetic stimulation was administered. Additionally, compared with the mock point, electroencephalogram sample entropy was higher after stimulating the Guangming point. When visual stimulation at Guangming was given before repeated-pulse transcranial magnetic stimula- tion, significant differences in sample entropy were found at five electrodes （C3, Cz, C4, P3, T8） in parietal cortex, the central gyrus, and the right temporal region compared with when it was given after repeated-pulse transcranial magnetic stimulation, indicating that repeated-pulse transcranial magnetic stimulation at Guangming can affect visual function. Analysis of electroencephalogram revealed that when visual stimulation preceded repeated pulse transcranial magnetic stimulation, sample entropy values were higher at the C3, C4, and P3 electrodes and lower at the Cz and T8 electrodes than visual stimulation followed preceded repeated pulse transcranial magnetic stimula- tion. The findings indicate that repeated-pulse transcranial magnetic stimulation at the Guangming evokes different patterns of electroencephalogram signals than repeated-pulse transcranial mag- netic stimulation at other nearby points on the body surface, and that repeated-pulse transcranial magnetic stimulation at the Guangrning is associated with changes in the complexity of visually evoked electroencephalogram signals in parietal regions, central gyrus, and temporal regions.

Blind source separation of multichannel electroencephalogram based on wavelet transform and ICA

Combination of the wavelet transform and independent component analysis （ICA） was employed for blind source separation （BSS） of multichannel electroencephalogram （EEG）. After denoising the original signals by discrete wavelet transform, high frequency components of some noises and artifacts were removed from the original signals. The denoised signals were reconstructed again for the purpose of ICA, such that the drawback that ICA cannot distinguish noises from source signals can be overcome effectively. The practical processing results showed that this method is an effective way to BSS of multichannel EEG. The method is actually a combination of wavelet transform with adaptive neural network, so it is also useful for BBS of other complex signals.

Electroencephalogram evidence for the activation of human mirror neuron system during the observation of intransitive shadow and line drawing actions

Previous studies have demonstrated that hand shadows may activate the motor cortex associated with the mirror neuron system in human brain. However, there is no evidence of activity of the human mirror neuron system during the observation of intransitive movements by shadows and line drawings of hands. This study examined the suppression of electroencephalography mu waves （8-13 Hz） induced by observation of stimuli in 18 healthy students. Three stimuli were used： real hand actions, hand shadow actions and actions made by line drawings of hands. The results showed significant desynchronization of the mu rhythm （＂mu suppression＂） across the sensodmotor cortex （recorded at C3, Cz and C4）, the frontal cortex （recorded at F3, Fz and F4） and the central and right posterior parietal cortex （recorded at Pz and P4） under all three conditions. Our experimental findings suggest that the observation of ＂impoverished hand actions＂, such as intransitive movements of shadows and line drawings of hands, is able to activate widespread cortical areas related to the putative human mirror neuron system.

Electroencephalogram and evoked potential parameters examined in Chinese mild head injury patients for forensic medicine

Objective To evaluate the usefulness of quantitative electroencephalogram （QEEG）, flash visual evoked potential （F-VEP） and auditory brainstem responses （ABR） as indicators of general neurological status. Methods Comparison was conducted on healthy controls （N=30） and patients with brain concussion （N=60） within 24 h after traumatic brain injury. Follow-up study of patient group was completed with the same standard paradigm 3 months later. All participants were recorded in multi-modality related potential testing in both early and late concussion at the same clinical setting. Glasgow coma scale, CT scanning, and physical examinations of neuro-psychological function, optic and auditory nervous system were performed before electroencephalogram （EEG） and evoked potential （EEG-EP） testing. Any participants showed abnormal changes of clinical examinations were excluded from the study. Average power of frequency spectrum and power ratios were selected for QEEG testing, and latency and amplitude of F-VEP and ABR were recorded. Results Between patients and normal controls, the results indicated： （1） Highly significance （P 〈 0.01） in average power of α1 and power ratios of θ/α1, 0/α2, α1/α2 of EEG recording; （2） N70-P 100 amplitude of F-VEP in significant difference at early brain concussion; and （3） apparent prolongation of Ⅰ～Ⅲ inter-peak latency of ABR appeared in some individuals at early stage after concussion. The follow-up study showed that some patients with concussion were also afflicted with characteristic changes of EEG components for both increments of α1 average power and θ/α2 power ratio after 3 months recording. Conclusion EEG testing has been shown to be more effective and sensitive than evoked potential tests alone on detecting functional state of patients with mild traumatic brain injury （MTBI）. Increments of α1 average power and θ/α2 power ratio are the sensitive EEG parameters to determining early concussion and evaluating outcome of postconcussion symptoms （PCS）. Follow-up study associated with persistent PCS may be consistent with the postulate of substantial biological, rather than psychological origin. The study suggests that combination of EEG and EP parameters can contribute to the evaluation of brain function as a whole for clinical and forensic applications.

Investigating the influence of monosodium L-glutamate on brain responses via scalp-electroencephalogram(scalp-EEG)

As the relevance between left and right brain neurons when transmitting electrical signals of umami taste is unknown,the aim of this work was to investigate responsive regions of the brain to the umami tastant monosodium glutamate(MSG)by using scalp-electroencephalogram(EEG)to identify the most responsive brain regions to MSG.Three concentrations of MSG(0.05,0.12,0.26 g/100 mL)were provided to participants for tasting while recoding their responsive reaction times and brain activities.The results indicated that the most responsive frequency to MSG was at 2 Hz,while the most responsive brain regions were T4 CzA2,F8 CzA2,and Fp2 CzA2.Moreover,the sensitivity of the brain to MSG was significantly higher in the right brain region.This study shows the potential of using EEG to investigate the relevance between different brains response to umami taste,which contributes to better understanding the mechanism of umami perception.

Effect of the environment in Antarctica on immune function and electroencephalogram

An observation on the changes of immune function(serum immunoglobulin, lymphocyte transformation ) and electroencephalogram were carried out when the explorers were residing in Antarctica for a long time.Serum IgM, IgG decreased by the end of twelve months residing in Antarctica. It were only 40%; 38% (P<0.01) of the previous value before leaving for Antarctica. Serum IgA increased first and then returned to its previous value before leaving for Antarctica. When they returned back to Beijing for 2 months serum IgA was lower than that before leaving (P<0. 05). Lymphocyte transformation rate decreased to 45% (P<0. 05 ) of its previous level before leaving for Antarctica. The low lymphocyte transformation rate lasted for 2 months after return. But the variation of Ig level and lymphocyte transformation rate were small in the control group at different seasons. It is obviously that the significant change of ig level and lymphocyte transformation rate of explorers residing in Antarctica is the result of special environment.The desynchronization process on electroencephalogram (EEG) increased. The frequency and index of β-wave band increased during their stay in Antarctica. There is a close relationship between the decrease of lymphocyte transformation rate and the increase of the index and amplitude of β-band on EEG. It indicated that the decrease of immunity (especially cell mediated immunity) resulted from living under stress for a long time.

THE EFFECT OF ACUPUNCTURING ACUPOINTS ON THE CHANGE OF ELECTROENCEPHALOGRAM (EEG) IN ENDOTOXIC SHOCKED RATS

In present work,EEG and BP were used as the indexes to observe the relationbetween the change of EEG and the change of BP in the endotoxic shocked rats。At maintainingshock for 1 hr,dysrhythmia of EEG appeared in 38/46 cases.Simultaneously,there was a markeddrop in Bp,P【0.05.Following the shocked time prolonged,dysrhythmia was getting severe。AfterEA”Rengzhong"(n=14)or“Zusanli”(n=12),BP was significantly increased(P【0.05),anddysrhythmia of EEG showed clear improvement in most of the rats。There was a close relation be-tween the changes of EEG and BP,the change of EEG had a direct bearing on the change of BP.

Electroencephalogram and brainstem auditory evoked potential in 539 patients with central coordination disorder

BACKGROUND： Electroencephalogram （EEG） and brainstem auditory evoked potential （BAEP） are objective non-invasive means of measuring brain electrophysiology. OBJECTIVE： To analyze the value of EEG and BAEP in early diagnosis, treatment and prognostic evaluation of central coordination disorder. DESIGN, TIME AND SETTING： This case analysis study was performed at the Rehabilitation Center of Hunan Children＇s Hospital from January 2002 to January 2006. PARTICIPANTS： A total of 593 patients with severe central coordination disorder, comprising 455 boys and 138 girls, aged 1-6 months were enrolled for this study. METHODS： EEG was monitored using electroencephalography. BAEP was recorded using a Keypoint electromyogram device. Intelligence was tested by professionals using the Gesell scale. MAIN OUTCOME MEASURES： （1） The rate of abnormal EEG and BAEP, （2） correlation of abnormalities of EEG and BAEP with associated injuries, （3） correlation of abnormalities of EEG and BAEP with high risk factors. RESULTS： The rate of abnormal EEG was 68.6% （407/593 patients）, and was increased in patients who also had mental retardation （P 〈 0.05）. The rate of abnormal BAEP was 21.4% （127/593 patients）. These 127 patients included 67 patients （52.8%） with peripheral auditory damage and 60 patients （47.2%） with central and mixed auditory damage. The rate of abnormal BAEP was significantly increased in patients who also had mental retardation （P 〈 0.01 ）. Logistic regression analysis showed that asphyxia （P 〈 0.05）, jaundice, preterm delivery, low birth weight and the umbilical cord around the neck were closely correlated with abnormal EEG in patients with central coordination disorder, lntracranial hemorrhage, jaundice （P 〈 0.05）, low birth weight and intrauterine infection （P 〈 0.05） were closely correlated with abnormal BAEP in patients with central coordination disorder. CONCLUSION： Central coordination disorder is often associated with abnormal EEG and BAEP. The rate of EEG or BAEP abnormality is positively associated with the size of the brain injury. Asphyxia is a high risk factor for abnormal EEG in central coordination disorder. Jaundice and intrauterine infection are high risk factors for abnormal BAEP in central coordination disorder.

Clinical and electroencephalogram characteristics and treatment outcomes in children with benign epilepsy and centrotemporal spikes

BACKGROUND Epilepsy is a syndrome characterized by transient,rigid,paroxysmal,and repetitive central nervous system dysfunction.Prevention,control,and improvement of cognitive and behavioral dysfunction are of great significance for improving the patients’intellectual development and quality of life.Electroencephalograms(EEG)can predict an accelerated decline in cognitive function.AIM To determine the clinical and EEG characteristics and treatment results of benign epilepsy in spiking children.METHODS A total of 106 cases of benign epilepsy in children with myocardial spines treated at our hospital from January 2017 to January 2020 were selected.Differences in clinical data and EGG characteristics between treatment-effective/-ineffective patients were analyzed,and children’s intellectual development before and after treatment evaluated using the Gesell Development Diagnostic Scale.RESULTS EEG showed that the discharge proportion in the awake and sleep periods was 66.04%,and the peak/peak discharge was mainly single-sided,accounting for 81.13%,while the discharge generalization accounted for 31.13%.There was no significant difference in any of these variables between sexes and ages(P>0.05).The proportion of patients with early onset(<5 years old)and seizure frequency>3 times/half a year was 40.00%and 60.00%,respectively;the incidence rate and seizure frequency in the younger age group(<5 years old)were significantly higher than those in the treatment-effective group(P<0.05),while the discharge index was significantly lower than that in the treatment-effective group(P<0.05).The discharge index was negatively correlated with fine motor skill and language development(r=-0.274 and-0.247,respectively;P<0.05),but not with the rest(P>0.05).Logistic regression analysis showed that low age onset(<5 years old)and seizure frequency were the factors affecting ineffective-treatment of benign epilepsy in children(odds ratio=11.304 and 5.784,respectively;P<0.05).The discharge index of the responsive group after treatment was significantly lower than that of the unresponsive group(P<0.05).However,there was no significant difference between groups after treatment in gross and fine motor skills,adaptability,language,and personal social development(P>0.05).CONCLUSION The EEG of children with benign epilepsy due to spinal wave in central time zone has characteristic changes,and the therapeutic effect is influenced by age of onset and attack frequency.

Electroencephalogram (EEG) Brain Signals to Detect Alcoholism Based on Deep Learning

The detection of alcoholism is of great importance due to its effects on individuals and society.Automatic alcoholism detection system(AADS)based on electroencephalogram(EEG)signals is effective,but the design of a robust AADS is a challenging problem.AADS’current designs are based on conventional,hand-engineered methods and restricted performance.Driven by the excellent deep learning(DL)success in many recognition tasks,we implement an AAD system based on EEG signals using DL.A DL model requires huge number of learnable parameters and also needs a large dataset of EEG signals for training which is not easy to obtain for the AAD problem.In order to solve this problem,we propose a multi-channel Pyramidal neural convolutional(MP-CNN)network that requires a less number of learnable parameters.Using the deep CNN model,we build an AAD system to detect from EEG signal segments whether the subject is alcoholic or normal.We validate the robustness and effectiveness of proposed AADS using KDD,a benchmark dataset for alcoholism detection problem.In order to find the brain region that contributes significant role in AAD,we investigated the effects of selected 19 EEG channels(SC-19),those from the whole brain(ALL-61),and 05 brain regions,i.e.,TEMP,OCCIP,CENT,FRONT,and PERI.The results show that SC-19 contributes significant role in AAD with the accuracy of 100%.The comparison reveals that the state-of-the-art systems are outperformed by the AADS.The proposed AADS will be useful in medical diagnosis research and health care systems.