OBJECTIVE: To propose a semi-supervised epileptic seizure prediction model (ST-WGAN-GP-Bi-LSTM) to enhance the prediction performance by improving time-frequency analysis of electroencephalogram (EEG) signals, enhancing the stability of the unsupervised feature learning model and improving the design of back-end classifier. METHODS: Stockwell transform (ST) of the epileptic EEG signals was performed to locate the time-frequency information by adaptive adjustment of the resolution and retaining the absolute phase to obtain the time-frequency inputs. When there was no overlap between the generated data distribution and the real EEG data distribution, to avoid failure of feature learning due to a constant JS divergence, Wasserstein GAN was used as a feature learning model, and the cost function based on EM distance and gradient penalty strategy was adopted to constrain the unsupervised training process to allow the generation of a high-order feature extractor. A temporal prediction model was finally constructed based on a bi-directional long short term memory network (Bi-LSTM), and the classification performance was improved by obtaining the temporal correlation between high-order time-frequency features. The CHB-MIT scalp EEG dataset was used to validate the proposed patient-specific seizure prediction method. RESULTS: The AUC, sensitivity, and specificity of the proposed method reached 90.40%, 83.62%, and 86.69%, respectively. Compared with the existing semi-supervised methods, the propose method improved the original performance by 17.77%, 15.41%, and 53.66%. The performance of this method was comparable to that of a supervised prediction model based on CNN. CONCLUSION The utilization of ST, WGAN-GP, and Bi-LSTM effectively improves the prediction performance of the semi-supervised deep learning model, which can be used for optimization of unsupervised feature extraction in epileptic seizure prediction.
Humans ; Memory, Short-Term ; Seizures/diagnosis* ; Electroencephalography

Objective: To summarize the clinical characteristics of epileptic seizure associated with neurofibromatosis type 1 (NF1). Methods: From January 2017 to July 2023 at Children's Hospital Capital Institute of Pediatrics, medical records of patients with both NF1 and epileptic seizure were reviewed in this case series study. The clinical characteristics, treatment and prognosis were analyzed retrospectively. Results: A total of 15 patients(12 boys and 3 girls) were collected. Café-au-lait macules were observed in all 15 patients. There were 6 patients with neurodevelopmental disorders and the main manifestations were intellectual disability or developmental delay. The age at the first epileptic seizure was 2.5 (1.2, 5.5) years. There were various seizure types, including generalized tonic-clonic seizures in 8 patients, focal motor seizures in 6 patients, epileptic spasm in 4 patients, tonic seizures in 1 patient, absence in 1 patient, generalized myoclonic seizure in 1 patient and focal to bilateral tonic-clonic seizure in 1 patient. Among 14 patients whose brain magnetic resonance imaging results were available, there were abnormal signals in corpus callosum, basal ganglia, thalamus or cerebellum in 6 patients, dilated ventricles of different degrees in 3 patients, blurred gray and white matter boundary in 2 patients, agenesis of corpus callosum in 1 patient and no obvious abnormalities in the other patients. Among 13 epilepsy patients, 8 were seizure-free with 1 or 2 antiseizure medications(ASM), 1 with drug resistant epilepsy was seizure-free after left temporal lobectomy, and the other 4 patients who have received 2 to 9 ASM had persistent seizures. One patient with complex febrile convulsion achieved seizure freedom after oral administration of diazepam on demand. One patient had only 1 unprovoked epileptic seizure and did not have another seizure without taking any ASM. Conclusions: The first epileptic seizure in NF1 patients usually occurs in infancy and early childhood, with the main seizure type of generalized tonic-clonic seizure and focal motor seizure. Some patients have intellectual disability or developmental delay. Most epilepsy patients achieve seizure freedom with ASM.
Male ; Female ; Humans ; Child, Preschool ; Child ; Neurofibromatosis 1/diagnosis* ; Retrospective Studies ; Intellectual Disability ; Electroencephalography ; Epilepsy/etiology* ; Seizures/etiology*

There are some limitations in the localization of epileptogenic zone commonly used by human eyes to identify abnormal discharges of intracranial electroencephalography in epilepsy. However, at present, the accuracy of the localization of epileptogenic zone by extracting intracranial electroencephalography features needs to be further improved. As a new method using dynamic network model, neural fragility has potential application value in the localization of epileptogenic zone. In this paper, the neural fragility analysis method was used to analyze the stereoelectroencephalography signals of 35 seizures in 20 patients, and then the epileptogenic zone electrodes were classified using the random forest model, and the classification results were compared with the time-frequency characteristics of six different frequency bands extracted by short-time Fourier transform. The results showed that the area under curve (AUC) of epileptic focus electrodes based on time-frequency analysis was 0.870 (delta) to 0.956 (high gamma), and its classification accuracy increased with the increase of frequency band, while the AUC by using neural fragility could reach 0.957. After fusing the neural fragility and the time-frequency characteristics of the γ and high γ band, the AUC could be further increased to 0.969, which was improved on the original basis. This paper verifies the effectiveness of neural fragility in identifying epileptogenic zone, and provides a theoretical reference for its further clinical application.
Humans ; Electroencephalography/methods* ; Epilepsy/diagnosis* ; Seizures ; Stereotaxic Techniques

OBJECTIVES: To summarize the clinical phenotype and genetic characteristics of children with autosomal dominant mental retardation type 5 caused by SYNGAP1 gene mutations. METHODS: A retrospective analysis was performed on the medical data of 8 children with autosomal dominant mental retardation type 5 caused by SYNGAP1 gene mutations who were diagnosed and treated in the Department of Pediatrics, Xiangya Hospital of Central South University. RESULTS: The mean age of onset was 9 months for the 8 children. All children had moderate-to-severe developmental delay (especially delayed language development), among whom 7 children also had seizures. Among these 8 children, 7 had novel heterozygous mutations (3 with frameshift mutations, 2 with nonsense mutations, and 2 with missense mutations) and 1 had 6p21.3 microdeletion. According to the literature review, there were 48 Chinese children with mental retardation caused by SYNGAP1 gene mutations (including the children in this study), among whom 40 had seizures, and the mean age of onset of seizures was 31.4 months. Frameshift mutations (15/48, 31%) and nonsense mutations (19/48, 40%) were relatively common in these children. In terms of treatment, among the 33 children with a history of epileptic medication, 28 (28/33, 85%) showed response to valproic acid antiepileptic treatment and 16 (16/33, 48%) achieved complete seizure control after valproic acid monotherapy or combined therapy. CONCLUSIONS Children with autosomal dominant mental retardation type 5 caused by SYNGAP1 gene mutations tend to have an early age of onset, and most of them are accompanied by seizures. These children mainly have frameshift and nonsense mutations. Valproic acid is effective for the treatment of seizures in most children.
Child ; Humans ; Intellectual Disability/diagnosis* ; Codon, Nonsense ; Retrospective Studies ; Valproic Acid ; ras GTPase-Activating Proteins/genetics* ; Mutation ; Seizures/genetics*

Objective: To evaluate the value of the 2020 diagnostic criteria (Cellucci criteria) for pediatric autoimmune encephalitis (AE) in children with suspected AE in a single center. Methods: The clinical data of 121 children hospitalized at the First Affiliated Hospital of Zhengzhou University from October 2019 to October 2021, with a diagnosis of suspected AE, were retrospectively collected and analyzed. The children were divided into definite antibody-positive AE (dAPAE), probable antibody-negative AE (prANAE), possible AE (pAE) and non-AE groups according to the Chinese expert consensus and the Graus criteria. A new diagnosis was made according to the Cellucci criteria which was compared with the clinical diagnosis to evaluate the diagnostic value of the Cellucci criteria. The Mann-Whitney U test, Kruskal-Wallis test, and χ² test were used to compare the differences among groups. The sensitivity and specificity were used to evaluate efficacy of the Cellucci criteria. Results: Among the 121 children, 72 were males and 49 were females, with an age of 10.3 (6.5, 14.0) years at disease onset. There were 99 cases diagnosed as AE according the clinical diagnosis (58 males and 41 females), of which 43 cases were diagnosed as dAPAE, 14 cases as prANAE and 42 cases as pAE, and the other 22 cases were not AE (14 males and 8 females). The top 2 initial symptoms in the 99 children with AE were seizures (53 cases, 53.5%) and abnormal mental behaviors (35 cases, 35.4%). And the most common symptoms during the course of the disease were abnormal mental behaviors (77 cases, 77.8%) and seizures (64 cases, 64.6%). There were statistically differences in the incidence of consciousness disorders, autonomic dysfunctions during the course of the disease and the length of hospitalization among the 4 groups (χ²=21.63, 13.74, H=22.60, all P<0.05). Ninety-six of the 121 children were tested for AE-related antibodies, of which 45 cases (46.9%) were antibody-positive. According to the Cellucci criteria, 42 cases were diagnosed as dAPAE, 34 cases as prANAE and 14 cases as pAE. Compared with the clinical diagnosis, the sensitivity of the Cellucci criteria for the diagnosis of the 3 types of AE were 93.02%, 92.86% and 87.88%, and the specificity were 96.23%, 74.39% and 86.36%, respectively. Conclusions: The Cellucci criteria has a high sensitivity and specificity for the diagnosis of pAE and dAPAE in the clinical management of children with suspected AE, while a high sensitivity but low specificity for the diagnosis of prANAE. Therefore, it is recommended to apply the Cellucci criteria selectively in clinical practice according to the actual situation, especially in the diagnosis of prANAE.
Child ; Encephalitis/diagnosis* ; Female ; Hashimoto Disease/diagnosis* ; Humans ; Male ; Retrospective Studies ; Seizures

In recent years, epileptic seizure detection based on electroencephalogram (EEG) has attracted the widespread attention of the academic. However, it is difficult to collect data from epileptic seizure, and it is easy to cause over fitting phenomenon under the condition of few training data. In order to solve this problem, this paper took the CHB-MIT epilepsy EEG dataset from Boston Children's Hospital as the research object, and applied wavelet transform for data augmentation by setting different wavelet transform scale factors. In addition, by combining deep learning, ensemble learning, transfer learning and other methods, an epilepsy detection method with high accuracy for specific epilepsy patients was proposed under the condition of insufficient learning samples. In test, the wavelet transform scale factors 2, 4 and 8 were set for experimental comparison and verification. When the wavelet scale factor was 8, the average accuracy, average sensitivity and average specificity was 95.47%, 93.89% and 96.48%, respectively. Through comparative experiments with recent relevant literatures, the advantages of the proposed method were verified. Our results might provide reference for the clinical application of epilepsy detection.
Algorithms ; Child ; Deep Learning ; Electroencephalography ; Epilepsy/diagnosis* ; Humans ; Seizures/diagnosis* ; Signal Processing, Computer-Assisted ; Wavelet Analysis

Neonatal seizures are the most common clinical manifestations of critically ill neonates and often suggest serious diseases and complicated etiologies. The precise diagnosis of this disease can optimize the use of anti-seizure medication, reduce hospital costs, and improve the long-term neurodevelopmental outcomes. Currently, a few artificial intelligence-assisted diagnosis and treatment systems have been developed for neonatal seizures, but there is still a lack of high-level evidence for the diagnosis and treatment value in the real world. Based on an artificial intelligence-assisted diagnosis and treatment systems that has been developed for neonatal seizures, this study plans to recruit 370 neonates at a high risk of seizures from 6 neonatal intensive care units (NICUs) in China, in order to evaluate the effect of the system on the diagnosis, treatment, and prognosis of neonatal seizures in neonates with different gestational ages in the NICU. In this study, a diagnostic study protocol is used to evaluate the diagnostic value of the system, and a randomized parallel-controlled trial is designed to evaluate the effect of the system on the treatment and prognosis of neonates at a high risk of seizures. This multicenter prospective study will provide high-level evidence for the clinical application of artificial intelligence-assisted diagnosis and treatment systems for neonatal seizures in the real world.
Artificial Intelligence ; Electroencephalography/methods* ; Epilepsy/diagnosis* ; Humans ; Infant, Newborn ; Infant, Newborn, Diseases/diagnosis* ; Intensive Care Units, Neonatal ; Multicenter Studies as Topic ; Prospective Studies ; Randomized Controlled Trials as Topic ; Seizures/drug therapy*

It is very important for epilepsy treatment to distinguish epileptic seizure and non-seizure. In this study, an automatic seizure detection algorithm based on dual density dual tree complex wavelet transform (DD-DT CWT) for intracranial electroencephalogram (iEEG) was proposed. The experimental data were collected from 15 719 competition data set up by the National Institutes of Health (NINDS) in Kaggle. The processed database consisted of 55 023 seizure epochs and 501 990 non-seizure epochs. Each epoch was 1 second long and contained 174 sampling points. Firstly, the signal was resampled. Then, DD-DT CWT was used for EEG signal processing. Four kinds of features include wavelet entropy, variance, energy and mean value were extracted from the signal. Finally, these features were sent to least squares-support vector machine (LS-SVM) for learning and classification. The appropriate decomposition level was selected by comparing the experimental results under different wavelet decomposition levels. The experimental results showed that the features selected in this paper were different between seizure and non-seizure. Among the eight patients, the average accuracy of three-level decomposition classification was 91.98%, the sensitivity was 90.15%, and the specificity was 93.81%. The work of this paper shows that our algorithm has excellent performance in the two classification of EEG signals of epileptic patients, and can detect the seizure period automatically and efficiently.
Algorithms ; Electroencephalography ; Epilepsy/diagnosis* ; Humans ; Seizures/diagnosis* ; Signal Processing, Computer-Assisted ; Support Vector Machine ; Wavelet Analysis

As a common disease in nervous system, epilepsy is possessed of characteristics of high incidence, suddenness and recurrent seizures. Timely prediction with corresponding rescues and treatments can be regarded as effective countermeasure to epilepsy emergencies, while most accidental injuries can thus be avoided. Currently, how to use electroencephalogram (EEG) signals to predict seizure is becoming a highlight topic in epilepsy researches. In spite of significant progress that made, more efforts are still to be made before clinical applications. This paper reviews past epilepsy studies, including research records and critical technologies. Contributions of machine learning (ML) and deep learning (DL) on seizure predictions have been emphasized. Since feature selection and model generalization limit prediction ratings of conventional ML measures, DL based seizure predictions predominate future epilepsy studies. Consequently, more exploration may be vitally important for promoting clinical applications of epileptic seizure prediction.
Electroencephalography ; Epilepsy/diagnosis* ; Humans ; Machine Learning ; Seizures/diagnosis* ; Signal Processing, Computer-Assisted

No abstract available.
Diagnosis ; Seizures ; Tomography, Emission-Computed, Single-Photon