Brain network classification based on dynamic graph attention information bottleneck

BACKGROUND AND OBJECTIVES

Graph neural networks (GNN) have demonstrated remarkable encoding capabilities in the context of brain network classification tasks. They excel at uncovering hidden static connections between brain states. However, brain network signals can be influenced by physiological traits and external variables during clinical detection, resulting in noisy brain graphs. Additionally, many existing algorithms for brain networks primarily focus on static topologies determined by threshold-based criteria, thereby overlooking the real-time variability in brain channel connectivity. These sources of noise and the persistence of static structures inevitably hinder the effective exchange of information during brain network computations.

METHODS

To address these challenges, we propose a novel framework called the dynamic graph attention information bottleneck (DGAIB). This framework is designed to dynamically enhance the input raw brain graph structure from the perspective of information theory and graph theory. First, we employ the Spearman function to construct a raw graph. Then, we use a graph information bottleneck (GIB) to optimize the internal graph connections by selectively masking redundant feature embeddings. Finally, we enhance the feature aggregation of each brain state by utilizing a graph attention network (GAT), which promotes improved information exchange among distinct brain regions within the model. These processed representations serve as input for subsequent classification tasks.

EXPERIMENT AND RESULTS

We systematically evaluated the robustness and generalizability of our proposed framework through a series of experiments. This evaluation included patient-specific experiments using the electroencephalography (EEG)-based CHB-MIT dataset and cross-patient experiments leveraging the functional magnetic resonance imaging (fMRI)-based ABIDE-I dataset from multiple perspectives.

Deep Learning-Based Classification of Epileptic Electroencephalography Signals Using a Concentrated Time-Frequency Approach

ConceFT (concentration of frequency and time) is a new time-frequency (TF) analysis method which combines multitaper technique and synchrosqueezing transform (SST). This combination produces highly concentrated TF representations with approximately perfect time and frequency resolutions. In this paper, it is aimed to show the TF representation performance and robustness of ConceFT by using it for the classification of the epileptic electroencephalography (EEG) signals. Therefore, a signal classification algorithm which uses TF images obtained with ConceFT to feed the transfer learning structure has been presented. Epilepsy is a common neurological disorder that millions of people suffer worldwide. Daily lives of the patients are quite difficult because of the unpredictable time of seizures. EEG signals monitoring the electrical activity of the brain can be used to detect approaching seizures and make possible to warn the patient before the attack. GoogLeNet which is a well-known deep learning model has been preferred to classify TF images. Classification performance is directly related to the TF representation accuracy of the ConceFT. The proposed method has been tested for various classification scenarios and obtained accuracies between 95.83% and 99.58% for two and three-class classification scenarios. High results show that ConceFT is a successful and promising TF analysis method for non-stationary biomedical signals.

Ameliorative effects of Albizia adianthifolia aqueous extract against pentylenetetrazole-induced epilepsy and associated memory loss in mice: Role of GABAergic, antioxidant defense and anti-inflammatory systems

Albizia adianthifolia (Schumach.) (Fabaceae) is a medicinal herb used for the treatment of epilepsy and memory impairment. This study aims to investigate the anticonvulsant effects of Albizia adianthifolia aqueous extract against pentylenetetrazole (PTZ)-induced spontaneous convulsions in mice; and determine whether the extract could mitigate memory impairment, oxidative/nitrergic stress, GABA depletion and neuroinflammation. Ultra-high performance liquid chromatography/mass spectrometry analysis was done to identify active compounds from the extract. Mice were injected with PTZ once every 48 h until kindling was developed. Animals received distilled water for the normal group and negative control groups, doses of extract (40, 80, or 160 mg/kg) for the test groups and sodium valproate (300 mg/kg) for the positive control group. Memory was measured using Y maze, novel object recognition (NOR) and open field paradigms, while the oxidative/nitrosative stresses (MDA, GSH, CAT, SOD and NO), GABAergic transmission (GABA, GABA-T and GAD) and neuro-inflammation (TNF-α, IFN-γ, IL- 1β, and IL-6) were determined. Brain photomicrograph was also studied. Apigenin, murrayanine and safranal were identified in the extract. The extract (80-160 mg/kg) significantly protected mice against seizures and mortality induced by PTZ. The extract significantly increased the spontaneous alternation and the discrimination index in the Y maze and NOR tests, respectively. PTZ kindling induced oxidative/nitrosative stress, GABA depletion, neuroinflammation and neuronal cells death was strongly reversed by the extract. The results suggest that the anticonvulsant activity of Albizia adianthifolia extract is accompanied by its anti-amnesic property, and may be supported by the amelioration of oxidative stress, GABAergic transmission and neuroinflammation.

A Class-Imbalance Aware and Explainable Spatio-Temporal Graph Attention Network for Neonatal Seizure Detection

Seizures are the most prevalent clinical indication of neurological disorders in neonates. In this study, a class-imbalance aware and explainable deep learning approach based on Convolutional Neural Networks (CNNs) and Graph Attention Networks (GATs) is proposed for the accurate automated detection of neonatal seizures. The proposed model integrates the temporal information of EEG signals with the spatial information on the EEG channels through the graph representation of the multi-channel EEG segments. One-dimensional CNNs are used to automatically develop a feature set that accurately represents the differences between seizure and nonseizure epochs in the time domain. By employing GAT, the attention mechanism is utilized to emphasize the critical channel pairs and information flow among brain regions. GAT coefficients were then used to empirically visualize the important regions during the seizure and nonseizure epochs, which can provide valuable insight into the location of seizures in the neonatal brain. Additionally, to tackle the severe class imbalance in the neonatal seizure dataset using under-sampling and focal loss techniques are used. Overall, the final Spatio-Temporal Graph Attention Network (ST-GAT) outperformed previous benchmarked methods with a mean AUC of 96.6% and Kappa of 0.88, demonstrating its high accuracy and potential for clinical applications.

Early prediction of MODS interventions in the intensive care unit using machine learning

Background

Multiple organ dysfunction syndrome (MODS) is one of the leading causes of death in critically ill patients. MODS is the result of a dysregulated inflammatory response that can be triggered by various causes. Owing to the lack of an effective treatment for patients with MODS, early identification and intervention are the most effective strategies. Therefore, we have developed a variety of early warning models whose prediction results can be interpreted by Kernel SHapley Additive exPlanations (Kernel-SHAP) and reversed by diverse counterfactual explanations (DiCE). So we can predict the probability of MODS 12 h in advance, quantify the risk factors, and automatically recommend relevant interventions.

Methods

We used various machine learning algorithms to complete the early risk assessment of MODS, and used a stacked ensemble to improve the prediction performance. The kernel-SHAP algorithm was used to quantify the positive and minus factors corresponding to the individual prediction results, and finally, the DiCE method was used to automatically recommend interventions. We completed the model training and testing based on the MIMIC-III and MIMIC-IV databases, in which the sample features in the model training included the patients' vital signs, laboratory test results, test reports, and data related to the use of ventilators.

Results

The customizable model called SuperLearner, which integrated multiple machine learning algorithms, had the highest authenticity of screening, and its Yordon index (YI), sensitivity, accuracy, and utility_score on the MIMIC-IV test set were 0.813, 0.884, 0.893, and 0.763, respectively, which were all maximum values of eleven models. The area under the curve of the deep-wide neural network (DWNN) model on the MIMIC-IV test set was 0.960, and the specificity was 0.935, which were both the maximum values of all these models. The Kernel-SHAP algorithm combined with SuperLearner was used to determine the minimum value of glasgow coma scale (GCS) in the current hour (OR = 0.609, 95% CI   0.606-0.612), maximum value of MODS score corresponding to GCS in the past 24 h (OR = 2.632, 95% CI 2.588-2.676), and maximum score of MODS corresponding to creatinine in the past 24 h (OR = 3.281, 95% CI   3.267-3.295) were generally the most influential factors.

Conclusion

The MODS early warning model based on machine learning algorithms has considerable application value, and the prediction efficiency of SuperLearner is superior to those of SubSuperLearner, DWNN, and other eight common machine learning models. Considering that the attribution analysis of Kernel-SHAP is a static analysis of the prediction results, we introduce the DiCE algorithm to automatically recommend counterfactuals to reverse the prediction results, which will be an important step towards the practical application of automatic MODS early intervention.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40537-023-00719-2.

DSCNN-LSTMs: A Lightweight and Efficient Model for Epilepsy Recognition

Epilepsy is the second most common disease of the nervous system. Because of its high disability rate and the long course of the disease, it is a worldwide medical problem and social public health problem. Therefore, the timely detection and treatment of epilepsy are very important. Currently, medical professionals use their own diagnostic experience to identify seizures by visual inspection of the electroencephalogram (EEG). Not only does it require a lot of time and effort, but the process is also very cumbersome. Machine learning-based methods have recently been proposed for epilepsy detection, which can help clinicians make rapid and correct diagnoses. However, these methods often require extracting the features of EEG signals before using the data. In addition, the selection of features often requires domain knowledge, and feature types also have a significant impact on the performance of the classifier. In this paper, a one-dimensional depthwise separable convolutional neural network and long short-term memory networks (1D DSCNN-LSTMs) model is proposed to identify epileptic seizures by autonomously extracting the features of raw EEG. On the UCI dataset, the performance of the proposed 1D DSCNN-LSTMs model is verified by cross-validation and time complexity comparison. Compared with other previous models, the experimental results show that the highest recognition rates of binary and quintuple classification are 99.57% and 81.30%, respectively. It can be concluded that the 1D DSCNN-LSTMs model proposed in this paper is an effective method to identify seizures based on EEG signals.

A deep learning framework for epileptic seizure detection based on neonatal EEG signals

Electroencephalogram (EEG) is one of the main diagnostic tests for epilepsy. The detection of epileptic activity is usually performed by a human expert and is based on finding specific patterns in the multi-channel electroencephalogram. This is a difficult and time-consuming task, therefore various attempts are made to automate it using both conventional and Deep Learning (DL) techniques. Unfortunately, authors do not often provide sufficiently detailed and complete information to be able to reproduce their results. Our work is intended to fill this gap. Using a carefully selected 79 neonatal EEG recordings we developed a complete framework for seizure detection using DL approch. We share a ready to use R and Python codes which allow: (a) read raw European Data Format files, (b) read data files containing the seizure annotations made by human experts, (c) extract train, validation and test data, (d) create an appropriate Convolutional Neural Network (CNN) model, (e) train the model, (f) check the quality of the neural classifier, (g) save all learning results.

SEEG-Net: An explainable and deep learning-based cross-subject pathological activity detection method for drug-resistant epilepsy

OBJECTIVE

Precise preoperative evaluation of drug-resistant epilepsy (DRE) requires accurate analysis of invasive stereoelectroencephalography (SEEG). With the tremendous breakthrough of Artificial intelligence (AI), previous studies can help clinical experts to identify pathological activities automatically. However, they still face limitations when applied in real-world clinical DRE scenarios, such as sample imbalance, cross-subject domain shift, and poor interpretability. Our objective is to propose a model that can address the above problems and realizes high-sensitivity SEEG pathological activity detection based on two real clinical datasets.

METHODS

Our proposed innovative and effective SEEG-Net introduces a multiscale convolutional neural network (MSCNN) to increase the receptive field of the model, and to learn SEEG multiple frequency domain features, local and global features. Moreover, we designed a novel focal domain generalization loss (FDG-loss) function to enhance the target sample weight and to learn domain consistency features. Furthermore, to enhance the interpretability and flexibility of SEEG-Net, we explain SEEG-Net from multiple perspectives, such as significantly different features, interpretable models, and model learning process interpretation by Grad-CAM++.

RESULTS

The performance of our proposed method is verified on a public benchmark multicenter SEEG dataset and a private clinical SEEG dataset for a robust comparison. The experimental results demonstrate that the SEEG-Net model achieves the highest sensitivity and is state-of-the-art on cross-subject (for different patients) evaluation, and well deal with the known problems. Besides, we provide an SEEG processing and database construction flow, by maintaining consistency with the real-world clinical scenarios.

SIGNIFICANCE

According to the results, SEEG-Net is constructed to increase the sensitivity of SEEG pathological activity detection. Simultaneously, we settled certain problems about AI assistance in clinical DRE, built a bridge between AI algorithm application and clinical practice.

Multi-view cross-subject seizure detection with information bottleneck attribution

OBJECTIVE

Significant progress has been witnessed in within-subject seizure detection from Electroencephalography (EEG) signals. Consequently, more and more works have been shifted from within-subject seizure detection to cross-subject scenarios. However, the progress is hindered by inter-patient variations caused by gender, seizure type, etc. Approach: To tackle this problem, we propose a multi-view cross-object seizure detection model with information bottleneck attribution. Feature representations specific to seizures are learned from raw EEG data by adversarial deep learning. Combined with the manually designed discriminative features, the model can detect seizures across different subjects. In addition, we introduce information bottleneck attribution to provide insights into the decision-making of the adversarial learning process, thus enhancing the interpretability of the model.

MAIN RESULTS

Extensive experiments are conducted on two benchmark datasets. The experimental results verify the efficacy of the model.

Both Cross-Patient and Patient-Specific Seizure Detection Based on Self-Organizing Fuzzy Logic

Automatic epilepsy detection is of great significance for the diagnosis and treatment of patients. Most detection methods are based on patient-specific models and have achieved good results. However, in practice, new patients do not have their own previous EEG data and therefore cannot be initially diagnosed. If the EEG data of other patients can be used to achieve cross-patient detection, and cross-patient and patient-specific experiments can be combined at the same time, this method will be more widely used. In this work, an EEG classification model based on a self-organizing fuzzy logic (SOF) classifier is proposed for both cross-patient and patient-specific seizure detection. After preprocessing, the features of the original EEG signal are extracted and sent to the SOF classifier. This classification model is free from predefined parameters or a prior assumption regarding the EEG data generation model and only stores the key meta-parameters in memory. Therefore, it is very suitable for large-scale EEG signals in cross-patient detection. Selecting different granularity and classification distance in two different experiments after post-processing will achieve the best results. Experiments were conducted using a long-term continuous scalp EEG database and the [Formula: see text]-mean of cross-patient and patient-specific detection reached 83.35% and 92.04%, respectively. A comparison with other methods shows that there is greater performance and generalizability with this method.

Seizure Prediction in EEG Signals Using STFT and Domain Adaptation

Epileptic seizure prediction is one of the most used therapeutic adjuvant strategies for drug-resistant epilepsy. Conventional approaches commonly collect training and testing samples from the same patient due to inter-individual variability. However, the challenging problem of domain shift between various subjects remains unsolved, resulting in a low conversion rate to the clinic. In this work, a domain adaptation (DA)-based model is proposed to circumvent this issue. The short-time Fourier transform (STFT) is employed to extract the time-frequency features from raw EEG data, and an autoencoder is developed to map these features into high-dimensional space. By minimizing the inter-domain distance in the embedding space, this model learns the domain-invariant information, such that the generalization ability is improved by distribution alignment. Besides, to increase the feasibility of its application, this work mimics the data distribution under the clinical sampling situation and tests the model under this condition, which is the first study that adopts the assessment strategy. Experimental results on both intracranial and scalp EEG databases demonstrate that this method can minimize the domain gap effectively compared with previous approaches.

Automatic Diagnosis of Epileptic Seizures in EEG Signals Using Fractal Dimension Features and Convolutional Autoencoder Method

This paper proposes a new method for epileptic seizure detection in electroencephalography (EEG) signals using nonlinear features based on fractal dimension (FD) and a deep learning (DL) model. Firstly, Bonn and Freiburg datasets were used to perform experiments. The Bonn dataset consists of binary and multi-class classification problems, and the Freiburg dataset consists of two-class EEG classification problems. In the preprocessing step, all datasets were prepossessed using a Butterworth band pass filter with 0.5–60 Hz cut-off frequency. Then, the EEG signals of the datasets were segmented into different time windows. In this section, dual-tree complex wavelet transform (DT-CWT) was used to decompose the EEG signals into the different sub-bands. In the following section, in order to feature extraction, various FD techniques were used, including Higuchi (HFD), Katz (KFD), Petrosian (PFD), Hurst exponent (HE), detrended fluctuation analysis (DFA), Sevcik, box counting (BC), multiresolution box-counting (MBC), Margaos-Sun (MSFD), multifractal DFA (MF-DFA), and recurrence quantification analysis (RQA). In the next step, the minimum redundancy maximum relevance (mRMR) technique was used for feature selection. Finally, the k-nearest neighbors (KNN), support vector machine (SVM), and convolutional autoencoder (CNN-AE) were used for the classification step. In the classification step, the K-fold cross-validation with k = 10 was employed to demonstrate the effectiveness of the classifier methods. The experiment results show that the proposed CNN-AE method achieved an accuracy of 99.736% and 99.176% for the Bonn and Freiburg datasets, respectively.

Epileptic Seizures Detection in EEG Signals Using Fusion Handcrafted and Deep Learning Features

Epilepsy is a brain disorder disease that affects people's quality of life. Electroencephalography (EEG) signals are used to diagnose epileptic seizures. This paper provides a computer-aided diagnosis system (CADS) for the automatic diagnosis of epileptic seizures in EEG signals. The proposed method consists of three steps, including preprocessing, feature extraction, and classification. In order to perform the simulations, the Bonn and Freiburg datasets are used. Firstly, we used a band-pass filter with 0.5-40 Hz cut-off frequency for removal artifacts of the EEG datasets. Tunable-Q Wavelet Transform (TQWT) is used for EEG signal decomposition. In the second step, various linear and nonlinear features are extracted from TQWT sub-bands. In this step, various statistical, frequency, and nonlinear features are extracted from the sub-bands. The nonlinear features used are based on fractal dimensions (FDs) and entropy theories. In the classification step, different approaches based on conventional machine learning (ML) and deep learning (DL) are discussed. In this step, a CNN-RNN-based DL method with the number of layers proposed is applied. The extracted features have been fed to the input of the proposed CNN-RNN model, and satisfactory results have been reported. In the classification step, the K-fold cross-validation with k = 10 is employed to demonstrate the effectiveness of the proposed CNN-RNN classification procedure. The results revealed that the proposed CNN-RNN method for Bonn and Freiburg datasets achieved an accuracy of 99.71% and 99.13%, respectively.

Patient-Independent Seizure Detection Based on Channel-Perturbation Convolutional Neural Network and Bidirectional Long Short-Term Memory

Automatic seizure detection is of great significance for epilepsy diagnosis and alleviating the massive burden caused by manual inspection of long-term EEG. At present, most seizure detection methods are highly patient-dependent and have poor generalization performance. In this study, a novel patient-independent approach is proposed to effectively detect seizure onsets. First, the multi-channel EEG recordings are preprocessed by wavelet decomposition. Then, the Convolutional Neural Network (CNN) with proper depth works as an EEG feature extractor. Next, the obtained features are fed into a Bidirectional Long Short-Term Memory (BiLSTM) network to further capture the temporal variation characteristics. Finally, aiming to reduce the false detection rate (FDR) and improve the sensitivity, the postprocessing, including smoothing and collar, is performed on the outputs of the model. During the training stage, a novel channel perturbation technique is introduced to enhance the model generalization ability. The proposed approach is comprehensively evaluated on the CHB-MIT public scalp EEG database as well as a more challenging SH-SDU scalp EEG database we collected. Segment-based average accuracies of 97.51% and 93.70%, event-based average sensitivities of 86.51% and 89.89%, and average AUC-ROC of 90.82% and 90.75% are yielded on the CHB-MIT database and SH-SDU database, respectively.

One-Dimensional Convolutional Neural Networks Combined with Channel Selection Strategy for Seizure Prediction Using Long-Term Intracranial EEG

Seizure prediction using intracranial electroencephalogram (iEEG) has attracted an increasing attention during recent years. iEEG signals are commonly recorded in the form of multiple channels. Many previous studies generally used the iEEG signals of all channels to predict seizures, ignoring the consideration of channel selection. In this study, a method of one-dimensional convolutional neural networks (1D-CNN) combined with channel selection strategy was proposed for seizure prediction. First, we used 30-s sliding windows to segment the raw iEEG signals. Then, the 30-s iEEG segments, which were in three channel forms (single channel, channels only from seizure onset or free zone and all channels from seizure onset and free zones), were used as the inputs of 1D-CNN for classification, and the patient-specific model was trained. Finally, the channel form with the best classification was selected for each patient. The proposed method was evaluated on the Freiburg Hospital iEEG dataset. In the situation of seizure occurrence period (SOP) of 30[Formula: see text]min and seizure prediction horizon (SPH) of 5[Formula: see text]min, 98.60[Formula: see text] accuracy, 98.85[Formula: see text] sensitivity and 0.01/h false prediction rate (FPR) were achieved. In the situation of SOP of 60[Formula: see text]min and SPH of 5[Formula: see text]min, 98.32[Formula: see text] accuracy, 98.48[Formula: see text] sensitivity and 0.01/h FPR were attained. Compared with the many existing methods using the same iEEG dataset, our method showed a better performance.

Modeling plasticity during epileptogenesis by long short term memory neural networks

Understanding the pathogenesis of epilepsy including changes in synaptic pathways can improve our knowledge about epilepsy and development of new treatments. In this regard, data-driven models such as artificial neural networks, which are able to capture the effects of synaptic plasticity, can play an important role. This paper proposes long short term memory (LSTM) as the ideal architecture for modeling plasticity changes, and validates this proposal via experimental data. As a special class of recurrent neural networks (RNNs), LSTM is able to track information through time and control its flow via several gating mechanisms, which allow for maintaining the relevant and forgetting the irrelevant information. In our experiments, potentiation and depotentiation of motor circuit and perforant pathway as two forms of plasticity were respectively induced by kindled and kindled + transcranial magnetic stimulation of animal groups. In kindling, both procedure duration and gradual synaptic changes play critical roles. The stimulation of both groups continued for six days. Both after-discharge (AD) and seizure behavior as two biologically measurable effects of plasticity were recorded immediately post each stimulation. Three classes of artificial neural networks-LSTM, RNN, and feedforward neural network (FFNN)-were trained to predict AD and seizure behavior as indicators of plasticity during these six days. Results obtained from the collected data confirm the superiority of LSTM. For seizure behavior, the prediction accuracies achieved by these three models were 0.91 ± 0.01, 0.77 ± 0.02, and 0.59 ± 0.02%, respectively, and for AD, the prediction accuracies were 0.82 ± 0.01, 0.74 ± 0.08 and 0.42 ± 0.1, respectively.

Vagus Nerve Electroneurogram-Based Detection of Acute Pentylenetetrazol Induced Seizures in Rats

On-demand stimulation improves the efficacy of vagus nerve stimulation (VNS) in refractory epilepsy. The vagus nerve is the main peripheral parasympathetic connection and seizures are known to exhibit autonomic symptoms. Therefore, we hypothesized that seizure detection is possible through vagus nerve electroneurogram (VENG) recording. We developed a metric able to measure abrupt changes in amplitude and frequency of spontaneous vagus nerve action potentials. A classifier was trained using a "leave-one-out" method on a set of 6 seizures and 3 control recordings to utilize the VENG spike feature-based metric for seizure detection. We were able to detect pentylenetetrazol (PTZ) induced acute seizures in 6/6 animals during different stages of the seizure with no false detection. The classifier detected the seizure during an early stage in 3/6 animals and at the onset of tonic clonic stage of the seizure in 3/6 animals. EMG and motion artefacts often accompany epileptic activity. We showed the "epileptic" neural signal to be independent from EMG and motion artefacts. We confirmed the existence of seizure related signals in the VENG recording and proved their applicability for seizure detection. This detection might be a promising tool to improve efficacy of VNS treatment by developing new responsive stimulation systems.

Minireview of Epilepsy Detection Techniques Based on Electroencephalogram Signals

Epilepsy is one of the most common neurological disorders typically characterized by recurrent and uncontrollable seizures, which seriously affects the quality of life of epilepsy patients. The effective tool utilized in the clinical diagnosis of epilepsy is the Electroencephalogram (EEG). The emergence of machine learning promotes the development of automated epilepsy detection techniques. New algorithms are continuously introduced to shorten the detection time and improve classification accuracy. This minireview summarized the latest research of epilepsy detection techniques that focused on acquiring, preprocessing, feature extraction, and classification of epileptic EEG signals. The application of seizure prediction and localization based on EEG signals in the diagnosis of epilepsy was also introduced. And then, the future development trend of epilepsy detection technology has prospected at the end of the article.

Graph Attention Network with Focal Loss for Seizure Detection on Electroencephalography Signals

Automatic seizure detection from electroencephalogram (EEG) plays a vital role in accelerating epilepsy diagnosis. Previous researches on seizure detection mainly focused on extracting time-domain and frequency-domain features from single electrodes, while paying little attention to the positional correlations between different EEG channels of the same subject. Moreover, data imbalance is common in seizure detection scenarios where the duration of nonseizure periods is much longer than the duration of seizures. To cope with the two challenges, a novel seizure detection method based on graph attention network (GAT) is presented. The approach acts on graph-structured data and takes the raw EEG data as input. The positional relationship between different EEG signals is exploited by GAT. The loss function of the GAT model is redefined using the focal loss to tackle data imbalance problem. Experiments are conducted on the CHB-MIT dataset. The accuracy, sensitivity and specificity of the proposed method are 98.89[Formula: see text], 97.10[Formula: see text] and 99.63[Formula: see text], respectively.

A Deep Fourier Neural Network for Seizure Prediction Using Convolutional Neural Network and Ratios of Spectral Power

Epileptic seizure prediction is one of the most used therapeutic adjuvant strategies for drug-resistant epilepsy. Conventional methods usually adopt handcrafted features and manual parameter setting. The over-reliance on the expertise of specialists may lead to weak exploitation of features and low popularization of clinical application. This paper proposes a novel parameterless patient-specific method based on Fourier Neural Network (FNN), where the Fourier transform and backpropagation learning are synthesized to make the predictor more efficient and practical. The employment of FNN is the first attempt in the field of seizure prediction due to its automatic extraction of immanent spectra in epileptic signals. Despite the self-adaptive superiority of FNN, we introduce Convolutional Neural Network (CNN) to further improve its search capability in high-dimensional feature spaces. The study also develops a multi-layer module to estimate spectral power ratios of raw recordings, which optimizes the prediction by enhancing feature diversity. Based on these modules, this paper proposes a two-channel deep neural network: Fourier Ratio Convolutional Neural Network (FRCNN). To demonstrate the reliability of the model, we explain the mathematical meaning of hidden-layer neurons in FRCNN theoretically. This approach is evaluated on both intracranial and scalp EEG datasets. It shows that the predictor achieved a sensitivity of 91.2% and a false prediction rate (FPR) of 0.06[Formula: see text]h[Formula: see text] across intracranial subjects and a sensitivity of 85.4% and an FPR of 0.14[Formula: see text]h[Formula: see text] over scalp subjects. The results indicate that FRCNN enables the convenience of epilepsy treatments while preserving a high degree of precision. In the end, a detailed comparison with the previous methods demonstrates that FRCNN has achieved higher performance and generalization ability.

Personalized EEG Feature Selection for Low-Complexity Seizure Monitoring

Approximately, one third of patients with epilepsy are refractory to medical therapy and thus can be at high risk of injuries and sudden unexpected death. A low-complexity electroencephalography (EEG)-based seizure monitoring algorithm is critically important for daily use, especially for wearable monitoring platforms. This paper presents a personalized EEG feature selection approach, which is the key to achieve a reliable seizure monitoring with a low computational cost. We advocate a two-step, personalized feature selection strategy to enhance monitoring performances for each patient. In the first step, linear discriminant analysis (LDA) is applied to find a few seizure-indicative channels. Then in the second step, least absolute shrinkage and selection operator (LASSO) method is employed to select a discriminative subset of both frequency and time domain features (spectral powers and entropy). A personalization strategy is further customized to find the best settings (number of channels and features) that yield the highest classification scores for each subject. Experimental results of analyzing 23 subjects in CHB-MIT database are quite promising. We have achieved an average F-1 score of 88% with excellent sensitivity and specificity using not more than 7 features extracted from at most 3 channels.

Automatic epileptic seizure detection via Stein kernel-based sparse representation

Epileptic seizure detection is of great significance in the diagnosis of epilepsy and relieving the heavy workload of visual inspection of electroencephalogram (EEG) recordings. This paper presents a novel method for seizure detection using the Stein kernel-based sparse representation (SR) for EEG recordings. Different from the traditional SR scheme that works with vector data in Euclidean space, the Stein kernel-based SR framework is constructed for seizure detection in the space of the symmetric positive definite (SPD) matrices, which form a Riemannian manifold. Due to the non-Euclidean geometry of the Riemannian manifold, the Stein kernel on the manifold permits the embedding of the manifold in a high-dimensional reproducing kernel Hilbert space (RKHS) to perform SR. In the Stein kernel-based SR framework, EEG samples are described by SPD matrices in the form of covariance descriptors (CovDs). Then, a test EEG sample is sparsely represented on the training set, and the test sample is classified as a member of the class, which leads to the minimum reconstructed residual. Finally, by using three widely used EEG datasets to evaluate the detection performance of the proposed method, the experimental results demonstrate that it achieves good classification accuracy on each dataset. Furthermore, the fast computational speed of the Stein kernel-based SR also meets the basic requirements for real-time seizure detection.

Classification of Epileptic EEG Signals Using Synchrosqueezing Transform and Machine Learning

Epilepsy is a neurological disease that is very common worldwide. Patient's electroencephalography (EEG) signals are frequently used for the detection of epileptic seizure segments. In this paper, a high-resolution time-frequency (TF) representation called Synchrosqueezing Transform (SST) is used to detect epileptic seizures. Two different EEG data sets, the IKCU data set we collected, and the publicly available CHB-MIT data set are analyzed to test the performance of the proposed model in seizure detection. The SST representations of seizure and nonseizure (pre-seizure or inter-seizure) EEG segments of epilepsy patients are calculated. Various features like higher-order joint TF (HOJ-TF) moments and gray-level co-occurrence matrix (GLCM)-based features are calculated using the SST representation. By using single and ensemble machine learning methods such as k-Nearest Neighbor (kNN), Logistic Regression (LR), Naive Bayes (NB), Support Vector Machine (SVM), Boosted Trees (BT), and Subspace kNN (S-kNN), EEG features are classified. The proposed SST-based approach achieved 95.1% ACC, 96.87% PRE, 95.54% REC values for the IKCU data set, and 95.13% ACC, 93.37% PRE, 90.30% REC values for the CHB-MIT data set in seizure detection. Results show that the proposed SST-based method utilizing novel TF features outperforms the short-time Fourier transform (STFT)-based approach, providing over 95% accuracy for most cases, and compares well with the existing methods.

The Automatic Detection of Seizure Based on Tensor Distance And Bayesian Linear Discriminant Analysis

Electroencephalogram (EEG) plays an important role in recording brain activity to diagnose epilepsy. However, it is not only laborious, but also not very cost effective for medical experts to manually identify the features on EEG. Therefore, automatic seizure detection in accordance with the EEG recordings is significant for the diagnosis and treatment of epilepsy. Here, a new method for detecting seizures using tensor distance (TD) is proposed. First, the time-frequency characteristics of EEG signals are obtained by wavelet transformation, and the tensor representation of EEG signals is then obtained. Tucker decomposition is used to obtain the principal components of the EEG tensor. After, the distances between different categories of EEG tensors are calculated as the EEG features. Finally, the TD features are classified through the Bayesian Linear Discriminant Analysis (Bayesian LDA) classifier. The performance of this method is measured by the sensitivity, specificity, and recognition accuracy. Results indicate 95.12% sensitivity, 97.60% specificity, 97.60% recognition accuracy, and a false detection rate of 0.76 per hour in the invasive EEG dataset, which included 566.57[Formula: see text]h of EEG recording data from 21 patients. Taken together, the results show that TD has a good detection effect for seizure classification and that this method has high computational speed and great potential for real-time diagnosis.

Detection of Epileptic Seizure Using Pretrained Deep Convolutional Neural Network and Transfer Learning

INTRODUCTION

The diagnosis of epilepsy takes a certain process, depending entirely on the attending physician. However, the human factor may cause erroneous diagnosis in the analysis of the EEG signal. In the past 2 decades, many advanced signal processing and machine learning methods have been developed for the detection of epileptic seizures. However, many of these methods require large data sets and complex operations.

METHODS

In this study, an end-to-end machine learning model is presented for detection of epileptic seizure using the pretrained deep two-dimensional convolutional neural network (CNN) and the concept of transfer learning. The EEG signal is converted directly into visual data with a spectrogram and used directly as input data.

RESULTS

The authors analyzed the results of the training of the proposed pretrained AlexNet CNN model. Both binary and ternary classifications were performed without any extra procedure such as feature extraction. By performing data set creation from short-term spectrogram graphic images, the authors were able to achieve 100% accuracy for binary classification for epileptic seizure detection and 100% for ternary classification.

DISCUSSION/CONCLUSION

The proposed automatic identification and classification model can help in the early diagnosis of epilepsy, thus providing the opportunity for effective early treatment.

A New dispersion entropy and fuzzy logic system methodology for automated classification of dementia stages using electroencephalograms

A new EEG-based methodology is presented for differential diagnosis of the Alzheimer's disease (AD), Mild Cognitive Impairment (MCI), and healthy subjects employing the discrete wavelet transform (DWT), dispersion entropy index (DEI), a recently-proposed nonlinear measurement, and a fuzzy logic-based classification algorithm. The effectiveness and usefulness of the proposed methodology are evaluated by employing a database of measured EEG data acquired from 135 subjects, 45 MCI, 45 AD and 45 healthy subjects. The proposed methodology differentiates MCI and AD patients from HC subjects with an accuracy of 82.6-86.9%, sensitivity of 91 %, and specificity of 87 %.

The Effect of Low Magnesium Concentration on Ictal Discharges In A Non-Synaptic Model

Magnesium (Mg[Formula: see text] is an essential mineral for several cellular functions. The concentration of this ion below the physiological concentration induces recurrent neuronal discharges both in slices of the hippocampus and in neuronal cultures. These epileptiform discharges are initially sensitive to the application of [Formula: see text]-methyl-D-aspartate (NMDA) receptor antagonists, but these antagonists may lose their effectiveness with prolonged exposure to low [Mg[Formula: see text]], when extracellular Ca[Formula: see text] reduction occurs, typical of ictal periods, indicating the absence of synaptic connections. The study herein presented aimed at investigating the effect of reducing the [Mg[Formula: see text]] during the induction of Nonsynaptic Epileptiform Activities (NSEA). As an experimental protocol, NSEA were induced in rat hippocampal dentate gyrus (DG), using a bath solution containing high-K[Formula: see text] and zero-added-Ca[Formula: see text]. Additionally, computer simulations were performed using a mathematical model that represents electrochemical characteristics of the tissue of the DG granular layer. The experimental results show that the reduction of [Mg[Formula: see text]] causes an increase in the duration of the ictal period and a reduction in the interictal period, intensifying epileptiform discharges. The computer simulations suggest that the reduction of the Mg[Formula: see text] level intensifies the epileptiform discharges by a joint effect of reducing the surface charge screening and reducing the activity of the Na/K pump.

Classifying 2-year recurrence in patients with dlbcl using clinical variables with imbalanced data and machine learning methods

BACKGROUND

Treatments are limited for patients with relapsed/refractory Diffuse large B-cell lymphoma (DLBCL), and their survival rate is low. Prediction of the recurrence hazard for each patient could provide a reference regarding chemotherapy regimens for clinicians to extend patients' period of long-term remission. As current strategies cannot satisfy such need, we have established predictive models to classify patients with DLBCL with complete remission who had recurrences in 2 years from ones who did not.

METHODS

We assessed 518 patients with DLBCL and measured 52 variables of each patient. They were treated between January 2011 and July 2016. 17 variables were first selected by variable selection methods (including Lasso, Adaptive Lasso, and Elastic net). Then, we set classifiers and probability models for imbalanced data by combining the SMOTE sampling, cost-sensitive, and ensemble learning (consisting of AdaBoost, voting strategy, and Stacking) methods with the machine learning methods (Support Vector Machine, BackPropagation Artificial Neural Network, Random Forest), respectively. Last, assessed their performance.

RESULTS

The disease stage and other 5 variables are significant indicators for recurrence. The SVM with AdaBoost ensemble learning method modeling by SMOTE data performs the best (Sensitivity=97.3%, AUC=96%, RMSE=19.6%, G-mean=96%) in all classifiers. The SVM with AdaBoost method(AUC=98.7%, RMSE=17.7%, MXE=12.7%, Cal mean=3.2%, BS0=2.5%, BS1=4%, BSALL=3.1%) and random forest (AUC=99.5%, RMSE=19.8%, MXE=16.2%, Cal mean=9.1%, BS0=4.8%, BS1=2.9%, BSALL=3.9%) both modeling by SMOTE sampling data perform well in probability models.

CONCLUSIONS

This predictive model has high accuracy for almost all DLBCL patients and the six indicators can be recurrence signals.

Improved Overlap-based Undersampling for Imbalanced Dataset Classification with Application to Epilepsy and Parkinson’s Disease

Classification of imbalanced datasets has attracted substantial research interest over the past decades. Imbalanced datasets are common in several domains such as health, finance, security and others. A wide range of solutions to handle imbalanced datasets focus mainly on the class distribution problem and aim at providing more balanced datasets by means of resampling. However, existing literature shows that class overlap has a higher negative impact on the learning process than class distribution. In this paper, we propose overlap-based undersampling methods for maximizing the visibility of the minority class instances in the overlapping region. This is achieved by the use of soft clustering and the elimination threshold that is adaptable to the overlap degree to identify and eliminate negative instances in the overlapping region. For more accurate clustering and detection of overlapped negative instances, the presence of the minority class at the borderline areas is emphasized by means of oversampling. Extensive experiments using simulated and real-world datasets covering a wide range of imbalance and overlap scenarios including extreme cases were carried out. Results show significant improvement in sensitivity and competitive performance with well-established and state-of-the-art methods.

EEG Connectivity Analysis Using Denoising Autoencoders for the Detection of Dyslexia

The Temporal Sampling Framework (TSF) theorizes that the characteristic phonological difficulties of dyslexia are caused by an atypical oscillatory sampling at one or more temporal rates. The LEEDUCA study conducted a series of Electroencephalography (EEG) experiments on children listening to amplitude modulated (AM) noise with slow-rythmic prosodic (0.5-1[Formula: see text]Hz), syllabic (4-8[Formula: see text]Hz) or the phoneme (12-40[Formula: see text]Hz) rates, aimed at detecting differences in perception of oscillatory sampling that could be associated with dyslexia. The purpose of this work is to check whether these differences exist and how they are related to children's performance in different language and cognitive tasks commonly used to detect dyslexia. To this purpose, temporal and spectral inter-channel EEG connectivity was estimated, and a denoising autoencoder (DAE) was trained to learn a low-dimensional representation of the connectivity matrices. This representation was studied via correlation and classification analysis, which revealed ability in detecting dyslexic subjects with an accuracy higher than 0.8, and balanced accuracy around 0.7. Some features of the DAE representation were significantly correlated ([Formula: see text]) with children's performance in language and cognitive tasks of the phonological hypothesis category such as phonological awareness and rapid symbolic naming, as well as reading efficiency and reading comprehension. Finally, a deeper analysis of the adjacency matrix revealed a reduced bilateral connection between electrodes of the temporal lobe (roughly the primary auditory cortex) in DD subjects, as well as an increased connectivity of the F7 electrode, placed roughly on Broca's area. These results pave the way for a complementary assessment of dyslexia using more objective methodologies such as EEG.

Modeling Hippocampal CA1 Gabaergic Synapses of Audiogenic Rats

Wistar Audiogenic Rats (WARs) are genetically susceptible to sound-induced seizures that start in the brainstem and, in response to repetitive stimulation, spread to limbic areas, such as hippocampus. Analysis of the distribution of interevent intervals of GABAergic inhibitory postsynaptic currents (IPSCs) in CA1 pyramidal cells showed a monoexponential trend in Wistar rats, suggestive of a homogeneous population of synapses, but a biexponential trend in WARs. Based on this, we hypothesize that there are two populations of GABAergic synaptic release sites in CA1 pyramidal neurons from WARs. To address this hypothesis, we used a well-established neuronal computational model of a CA1 pyramidal neuron previously developed to replicate physiological properties of these cells. Our simulations replicated the biexponential trend only when we decreased the release frequency of synaptic currents by a factor of six in at least 40% of distal synapses. Our results suggest that almost half of the GABAergic synapses of WARs have a drastically reduced spontaneous release frequency. The computational model was able to reproduce the temporal dynamics of GABAergic inhibition that could underlie susceptibility to the spread of seizures.