Spatio-Temporal-Spectral Hierarchical Graph Convolutional Network With Semisupervised Active Learning for Patient-Specific Seizure Prediction

A Compact Graph Convolutional Network With Adaptive Functional Connectivity for Seizure Prediction

Seizure prediction using EEG has significant implications for the daily monitoring and treatment of epilepsy patients. However, the task is challenging due to the underlying spatiotemporal correlations and patient heterogeneity. Traditional methods often use large-scale models with independent components to capture the spatial and temporal features of EEG separately or explore shared patterns among patients with the help of pre-defined functional connectivity. In this paper, we propose a compact model, called the graph convolutional network based on adaptive functional connectivity (AFC-GCN), for seizure prediction. The model can adaptively infer evolution of functional connectivity in epilepsy patients during seizures through data-driven methods and synchronously analyze spatiotemporal response of functional connectivity in multiple topologies. On CHB-MIT datasets, the experimental results demonstrate that AFC-GCN achieves accurate and robust performance with low complexity. (AUC: 0.9820, accuracy: 0.9815, sensitivity: 0.9802, FPR: 0.0172). The proposed method has the potential to predict seizure during daily monitoring.

IRIME: Mitigating exploitation-exploration imbalance in RIME optimization for feature selection

Rime optimization algorithm (RIME) encounters issues such as an imbalance between exploitation and exploration, susceptibility to local optima, and low convergence accuracy when handling problems. This paper introduces a variant of RIME called IRIME to address these drawbacks. IRIME integrates the soft besiege (SB) and composite mutation strategy (CMS) and restart strategy (RS). To comprehensively validate IRIME's performance, IEEE CEC 2017 benchmark tests were conducted, comparing it against many advanced algorithms. The results indicate that the performance of IRIME is the best. In addition, applying IRIME in four engineering problems reflects the performance of IRIME in solving practical problems. Finally, the paper proposes a binary version, bIRIME, that can be applied to feature selection problems. bIRIMR performs well on 12 low-dimensional datasets and 24 high-dimensional datasets. It outperforms other advanced algorithms in terms of the number of feature subsets and classification accuracy. In conclusion, bIRIME has great potential in feature selection.

A new machine learning model to predict the prognosis of cardiogenic brain infarction

Cardiogenic cerebral infarction (CCI) is a disease in which the blood supply to the blood vessels in the brain is insufficient due to atherosclerosis or stenosis of the coronary arteries in the patient's heart, which leads to neurological deficits. To predict the pathogenic factors of cardiogenic cerebral infarction, this paper proposes a machine learning based analytical prediction model. 494 patients with CCI who were hospitalized for the first time were consecutively included in the study between January 2017 and December 2021, and followed up every three months for one year after hospital discharge. Clinical, laboratory and imaging data were collected, and predictors associated with relapse and death in CCI patients at six months and one year after discharge were analyzed using univariate and multivariate logistic regression methods, meanwhile established a new machine learning model based on the enhanced moth-flame optimization (FTSAMFO) and the fuzzy K-nearest neighbor (FKNN), called BITSAMFO-FKNN, which is practiced on the dataset related to patients with CCI. Specifically, this paper proposes the spatial transformation strategy to increase the exploitation capability of moth-flame optimization (MFO) and combines it with the tree seed algorithm (TSA) to increase the search capability of MFO. In the benchmark function experiments FTSAMFO beat 5 classical algorithms and 5 recent variants. In the feature selection experiment, ten times ten-fold cross-validation trials showed that the BITSAMFO-FKNN model proved actual medical importance and efficacy, with an accuracy value of 96.61%, sensitivity value of 0.8947, MCC value of 0.9231, and F-Measure of 0.9444. The results of the trial showed that hemorrhagic conversion and lower LVDD/LVSD were independent risk factors for recurrence and death in patients with CCI. The established BITSAMFO-FKNN method is helpful for CCI prognosis and deserves further clinical validation.

An efficient channel recurrent Criss-cross attention network for epileptic seizure prediction

Epilepsy is a chronic disease caused by repeated abnormal discharge of neurons in the brain. Accurately predicting the onset of epilepsy can effectively improve the quality of life for patients with the condition. While there are many methods for detecting epilepsy, EEG is currently considered one of the most effective analytical tools due to the abundant information it provides about brain activity. The aim of this study is to explore potential time-frequency and channel features from multi-channel epileptic EEG signals and to develop a patient-specific seizure prediction network. In this paper, an epilepsy EEG signal classification algorithm called Channel Recurrent Criss-cross Attention Network (CRCANet) is proposed. Firstly, the spectrograms processed by the short-time fourier transform is input into a Convolutional Neural Network (CNN). Then, the spectrogram feature map obtained in the previous step is input into the channel attention module to establish correlations between channels. Subsequently, the feature diagram containing channel attention characteristics is input into the recurrent criss-cross attention module to enhance the information content of each pixel. Finally, two fully connected layers are used for classification. We validated the method on 13 patients in the public CHB-MIT scalp EEG dataset, achieving an average accuracy of 93.8 %, sensitivity of 94.3 %, and specificity of 93.5 %. The experimental results indicate that CRCANet can effectively capture the time-frequency and channel characteristics of EEG signals while improving training efficiency.

Temporal information in the anterior cingulate cortex relates to accumulated experiences

Anterior cingulate cortex (ACC) activity is important for operations that require the ability to integrate multiple experiences over time, such as rule learning, cognitive flexibility, working memory, and long-term memory recall. To shed light on this, we analyzed neuronal activity while rats repeated the same behaviors during hour-long sessions to investigate how activity changed over time. We recorded neuronal ensembles as rats performed a decision-free operant task with varying reward likelihoods at three different response ports (n = 5). Neuronal state space analysis revealed that each repetition of a behavior was distinct, with more recent behaviors more similar than those further apart in time. ACC activity was dominated by a slow, gradual change in low-dimensional representations of neural state space aligning with the pace of behavior. Temporal progression, or drift, was apparent on the top principal component for every session and was driven by the accumulation of experiences and not an internal clock. Notably, these signals were consistent across subjects, allowing us to accurately predict trial numbers based on a model trained on data from a different animal. We observed that non-continuous ramping firing rates over extended durations (tens of minutes) drove the low-dimensional ensemble representations. 40% of ACC neurons' firing ramped over a range of trial lengths and combinations of shorter duration ramping neurons created ensembles that tracked longer durations. These findings provide valuable insights into how the ACC, at an ensemble level, conveys temporal information by reflecting the accumulation of experiences over extended periods.

Addressing data limitations in seizure prediction through transfer learning

According to the literature, seizure prediction models should be developed following a patient-specific approach. However, seizures are usually very rare events, meaning the number of events that may be used to optimise seizure prediction approaches is limited. To overcome such constraint, we analysed the possibility of using data from patients from an external database to improve patient-specific seizure prediction models. We present seizure prediction models trained using a transfer learning procedure. We trained a deep convolutional autoencoder using electroencephalogram data from 41 patients collected from the EPILEPSIAE database. Then, a bidirectional long short-term memory and a classifier layers were added on the top of the encoder part and were optimised for 24 patients from the Universitätsklinikum Freiburg individually. The encoder was used as a feature extraction module. Therefore, its weights were not changed during the patient-specific training. Experimental results showed that seizure prediction models optimised using pretrained weights present about four times fewer false alarms while maintaining the same ability to predict seizures and achieved more 13% validated patients. Therefore, results evidenced that the optimisation using transfer learning was more stable and faster, saving computational resources. In summary, adopting transfer learning for seizure prediction models represents a significant advancement. It addresses the data limitation seen in the seizure prediction field and offers more efficient and stable training, conserving computational resources. Additionally, despite the compact size, transfer learning allows to easily share data knowledge due to fewer ethical restrictions and lower storage requirements. The convolutional autoencoder developed in this study will be shared with the scientific community, promoting further research.

EEG power spectra parameterization and adaptive channel selection towards semi-supervised seizure prediction

BACKGROUND

The seizure prediction algorithms have demonstrated their potential in mitigating epilepsy risks by detecting the pre-ictal state using ongoing electroencephalogram (EEG) signals. However, most of them require high-density EEG, which is burdensome to the patients for daily monitoring. Moreover, prevailing seizure models require extensive training with significant labeled data which is very time-consuming and demanding for the epileptologists.

METHOD

To address these challenges, here we propose an adaptive channel selection strategy and a semi-supervised deep learning model respectively to reduce the number of EEG channels and to limit the amount of labeled data required for accurate seizure prediction. Our channel selection module is centered on features from EEG power spectra parameterization that precisely characterize the epileptic activities to identify the seizure-associated channels for each patient. The semi-supervised model integrates generative adversarial networks and bidirectional long short-term memory networks to enhance seizure prediction.

RESULTS

Our approach is evaluated on the CHB-MIT and Siena epilepsy datasets. With utilizing only 4 channels, the method demonstrates outstanding performance with an AUC of 93.15% on the CHB-MIT dataset and an AUC of 88.98% on the Siena dataset. Experimental results also demonstrate that our selection approach reduces the model parameters and training time.

CONCLUSIONS

Adaptive channel selection coupled with semi-supervised learning can offer the possible bases for a light weight and computationally efficient seizure prediction system, making the daily monitoring practical to improve patients' quality of life.

Parallel Dual-Branch Fusion Network for Epileptic Seizure Prediction

Epilepsy is a prevalent chronic disorder of the central nervous system. The timely and accurate seizure prediction using the scalp Electroencephalography (EEG) signal can make patients adopt reasonable preventive measures before seizures occur and thus reduce harm to patients. In recent years, deep learning-based methods have made significant progress in solving the problem of epileptic seizure prediction. However, most current methods mainly focus on modeling short- or long-term dependence in EEG, while neglecting to consider both. In this study, we propose a Parallel Dual-Branch Fusion Network (PDBFusNet) which aims to combine the complementary advantages of Convolutional Neural Network (CNN) and Transformer. Specifically, the features of the EEG signal are first extracted using Mel Frequency Cepstral Coefficients (MFCC). Then, the extracted features are delivered into the parallel dual-branches to simultaneously capture the short- and long-term dependencies of EEG signal. Further, regarding the Transformer branch, a novel feature fusion module is developed to enhance the ability of utilizing time, frequency, and channel information. To evaluate our proposal, we perform sufficient experiments on the public epileptic EEG dataset CHB-MIT, where the accuracy, sensitivity, specificity and precision are 95.76%, 95.81%, 95.71% and 95.71%, respectively. PDBFusNet shows superior performance compared to state-of-the-art competitors, which confirms the effectiveness of our proposal.

A hybrid multimodal machine learning model for Detecting Alzheimer's disease

Alzheimer's disease (AD) diagnosis utilizing single modality neuroimaging data has limitations. Multimodal fusion of complementary biomarkers may improve diagnostic performance. This study proposes a multimodal machine learning framework integrating magnetic resonance imaging (MRI), positron emission tomography (PET) and cerebrospinal fluid (CSF) assays for enhanced AD characterization. The model incorporates a hybrid algorithm combining enhanced Harris Hawks Optimization (HHO) algorithm referred to as ILHHO, with Kernel Extreme Learning Machine (KELM) classifier for simultaneous feature selection and classification. ILHHO enhances HHO's search efficiency by integrating iterative mapping (IM) to improve population diversity and local escaping operator (LEO) to balance exploration-exploitation. Comparative analysis with other improved HHO algorithms, classic meta-heuristic algorithms (MHAs), and state-of-the-art MHAs on IEEE CEC2014 benchmark functions indicates that ILHHO achieves superior optimization performance compared to other comparative algorithms. The synergistic ILHHO-KELM model is evaluated on 202 AD Neuroimaging Initiative (ADNI) subjects. Results demonstrate superior multimodal classification accuracy over single modalities, validating the importance of fusing heterogeneous biomarkers. MRI + PET + CSF achieves 99.2 % accuracy for AD vs. normal control (NC), outperforming conventional and proposed methods. Discriminative feature analysis provides further insights into differential AD-related neurodegeneration patterns detected by MRI and PET. The differential PET and MRI features demonstrate how the two modalities provide complementary biomarkers. The neuroanatomical relevance of selected features supports ILHHO-KELM's potential for extracting sensitive AD imaging signatures. Overall, the study showcases the advantages of capitalizing on complementary multimodal data through advanced feature learning techniques for improving AD diagnosis.

A Cross-Scale Transformer and Triple-View Attention Based Domain-Rectified Transfer Learning for EEG Classification in RSVP Tasks

Rapid serial visual presentation (RSVP)-based brain-computer interface (BCI) is a promising target detection technique by using electroencephalogram (EEG) signals. However, existing deep learning approaches seldom considered dependencies of multi-scale temporal features and discriminative multi-view spectral features simultaneously, which limits the representation learning ability of the model and undermine the EEG classification performance. In addition, recent transfer learning-based methods generally failed to obtain transferable cross-subject invariant representations and commonly ignore the individual-specific information, leading to the poor cross-subject transfer performance. In response to these limitations, we propose a cross-scale Transformer and triple-view attention based domain-rectified transfer learning (CST-TVA-DRTL) for the RSVP classification. Specially, we first develop a cross-scale Transformer (CST) to extract multi-scale temporal features and exploit the dependencies of different scales features. Then, a triple-view attention (TVA) is designed to capture spectral features from triple views of multi-channel time-frequency images. Finally, a domain-rectified transfer learning (DRTL) framework is proposed to simultaneously obtain transferable domain-invariant representations and untransferable domain-specific representations, then utilize domain-specific information to rectify domain-invariant representations to adapt to target data. Experimental results on two public RSVP datasets suggests that our CST-TVA-DRTL outperforms the state-of-the-art methods in the RSVP classification task. The source code of our model is publicly available in https://github.com/ljbuaa/CST_TVA_DRTL.

Time-Series Anomaly Detection Based on Dynamic Temporal Graph Convolutional Network for Epilepsy Diagnosis

Electroencephalography (EEG) is typical time-series data. Designing an automatic detection model for EEG is of great significance for disease diagnosis. For example, EEG stands as one of the most potent diagnostic tools for epilepsy detection. A myriad of studies have employed EEG to detect and classify epilepsy, yet these investigations harbor certain limitations. Firstly, most existing research concentrates on the labels of sliced EEG signals, neglecting epilepsy labels associated with each time step in the original EEG signal-what we term fine-grained labels. Secondly, a majority of these studies utilize static graphs to depict EEG's spatial characteristics, thereby disregarding the dynamic interplay among EEG channels. Consequently, the efficient nature of EEG structures may not be captured. In response to these challenges, we propose a novel seizure detection and classification framework-the dynamic temporal graph convolutional network (DTGCN). This method is specifically designed to model the interdependencies in temporal and spatial dimensions within EEG signals. The proposed DTGCN model includes a unique seizure attention layer conceived to capture the distribution and diffusion patterns of epilepsy. Additionally, the model incorporates a graph structure learning layer to represent the dynamically evolving graph structure inherent in the data. We rigorously evaluated the proposed DTGCN model using a substantial publicly available dataset, TUSZ, consisting of 5499 EEGs. The subsequent experimental results convincingly demonstrated that the DTGCN model outperformed the existing state-of-the-art methods in terms of efficiency and accuracy for both seizure detection and classification tasks.

Dynamical graph neural network with attention mechanism for epilepsy detection using single channel EEG

Epilepsy is a chronic brain disease, and identifying seizures based on electroencephalogram (EEG) signals would be conducive to implement interventions to help patients reduce impairment and improve quality of life. In this paper, we propose a classification algorithm to apply dynamical graph neural network with attention mechanism to single channel EEG signals. Empirical mode decomposition (EMD) are adopted to construct graphs and the optimal adjacency matrix is obtained by model optimization. A multilayer dynamic graph neural network with attention mechanism is proposed to learn more discriminative graph features. The MLP-pooling structure is proposed to fuse graph features. We performed 12 classification tasks on the epileptic EEG database of the University of Bonn, and experimental results showed that using 25 runs of ten-fold cross-validation produced the best classification results with an average of 99.83[Formula: see text] accuracy, 99.91[Formula: see text] specificity, 99.78[Formula: see text] sensitivity, 99.87[Formula: see text] precision, and 99.47[Formula: see text] [Formula: see text] score for the 12 classification tasks.

Automatic Seizure Detection Based on Stockwell Transform and Transformer

Epilepsy is a chronic neurological disease associated with abnormal neuronal activity in the brain. Seizure detection algorithms are essential in reducing the workload of medical staff reviewing electroencephalogram (EEG) records. In this work, we propose a novel automatic epileptic EEG detection method based on Stockwell transform and Transformer. First, the S-transform is applied to the original EEG segments, acquiring accurate time-frequency representations. Subsequently, the obtained time-frequency matrices are grouped into different EEG rhythm blocks and compressed as vectors in these EEG sub-bands. After that, these feature vectors are fed into the Transformer network for feature selection and classification. Moreover, a series of post-processing methods were introduced to enhance the efficiency of the system. When evaluating the public CHB-MIT database, the proposed algorithm achieved an accuracy of 96.15%, a sensitivity of 96.11%, a specificity of 96.38%, a precision of 96.33%, and an area under the curve (AUC) of 0.98 in segment-based experiments, along with a sensitivity of 96.57%, a false detection rate of 0.38/h, and a delay of 20.62 s in event-based experiments. These outstanding results demonstrate the feasibility of implementing this seizure detection method in future clinical applications.

Hybrid Network for Patient-Specific Seizure Prediction from EEG Data

Seizure prediction can improve the quality of life for patients with drug-resistant epilepsy. With the rapid development of deep learning, lots of seizure prediction methods have been proposed. However, seizure prediction based on single convolution models is limited by the inherent defects of convolution itself. Convolution pays attention to the local features while underestimates the global features. The long-term dependence of the electroencephalogram (EEG) data cannot be captured. In view of these defects, a hybrid model called STCNN based on Swin transformer (ST) and 2D convolutional neural network (2DCNN) is proposed. Time-frequency features extracted by short-term Fourier transform (STFT) are taken as the input of STCNN. ST blocks are used in STCNN to capture the global information and long-term dependencies of EEGs. Meanwhile, the 2DCNN blocks are adopted to capture the local information and short-term dependent features. The combination of the two blocks can fully exploit the seizure-related information thus improve the prediction performance. Comprehensive experiments are performed on the CHB-MIT scalp EEG dataset. The average seizure prediction sensitivity, the area under the ROC curve (AUC) and the false positive rate (FPR) are 92.94%, 95.56% and 0.073, respectively.

Dynamic Multi-Graph Convolution-Based Channel-Weighted Transformer Feature Fusion Network for Epileptic Seizure Prediction

Electroencephalogram (EEG) based seizure prediction plays an important role in the closed-loop neuromodulation system. However, most existing seizure prediction methods based on graph convolution network only focused on constructing the static graph, ignoring multi-domain dynamic changes in deep graph structure. Moreover, the existing feature fusion strategies generally concatenated coarse-grained epileptic EEG features directly, leading to the suboptimal seizure prediction performance. To address these issues, we propose a novel multi-branch dynamic multi-graph convolution based channel-weighted transformer feature fusion network (MB-dMGC-CWTFFNet) for the patient-specific seizure prediction with the superior performance. Specifically, a multi-branch (MB) feature extractor is first applied to capture the temporal, spatial and spectral representations fromthe epileptic EEG jointly. Then, we design a point-wise dynamic multi-graph convolution network (dMGCN) to dynamically learn deep graph structures, which can effectively extract high-level features from the multi-domain graph. Finally, by integrating the local and global channel-weighted strategies with the multi-head self-attention mechanism, a channel-weighted transformer feature fusion network (CWTFFNet) is adopted to efficiently fuse the multi-domain graph features. The proposed MB-dMGC-CWTFFNet is evaluated on the public CHB-MIT EEG and a private intracranial sEEG datasets, and the experimental results demonstrate that our proposed method achieves outstanding prediction performance compared with the state-of-the-art methods, indicating an effective tool for patient-specific seizure warning. Our code will be available at: https://github.com/Rockingsnow/MB-dMGC-CWTFFNet.

CLEP: Contrastive Learning for Epileptic Seizure Prediction Using a Spatio-Temporal-Spectral Network

Seizure prediction of epileptic preictal period through electroencephalogram (EEG) signals is important for clinical epilepsy diagnosis. However, recent deep learning-based methods commonly employ intra-subject training strategy and need sufficient data, which are laborious and time-consuming for a practical system and pose a great challenge for seizure predicting. Besides, multi-domain characterizations, including spatio-temporal-spectral dependencies in an epileptic brain are generally neglected or not considered simultaneously in current approaches, and this insufficiency commonly leads to suboptimal seizure prediction performance. To tackle the above issues, in this paper, we propose Contrastive Learning for Epileptic seizure Prediction (CLEP) using a Spatio-Temporal-Spectral Network (STS-Net). Specifically, the CLEP learns intrinsic epileptic EEG patterns across subjects by contrastive learning. The STS-Net extracts multi-scale temporal and spectral representations under different rhythms from raw EEG signals. Then, a novel triple attention layer (TAL) is employed to construct inter-dimensional interaction among multi-domain features. Moreover, a spatio dynamic graph convolution network (sdGCN) is proposed to dynamically model the spatial relationships between electrodes and aggregate spatial information. The proposed CLEP-STS-Net achieves a sensitivity of 96.7% and a false prediction rate of 0.072/h on the CHB-MIT scalp EEG database. We also validate the proposed method on clinical intracranial EEG (iEEG) database from our Xuanwu Hospital of Capital Medical University, and the predicting system yielded a sensitivity of 95%, a false prediction rate of 0.087/h. The experimental results outperform the state-of-the-art studies which validate the efficacy of our method. Our code is available at https://github.com/LianghuiGuo/CLEP-STS-Net.

Enhancing Performance of Convolutional Neural Network-Based Epileptic Electroencephalogram Diagnosis by Asymmetric Stochastic Resonance

Epilepsy is a chronic disorder that leads to transient neurological dysfunction and is clinically diagnosed primarily by electroencephalography. Several intelligent systems have been proposed to automatically detect seizures, among which deep convolutional neural networks (CNNs) have shown better performance than traditional machine-learning algorithms. Owing to artifacts and noise, the raw electroencephalogram (EEG) must be preprocessed to improve the signal-to-noise ratio prior to being fed into the CNN classifier. However, because of the spectrum overlapping of uncontrollable noise with EEG, traditional filters cause information loss in EEG; thus, the potential of classifiers cannot be fully exploited. In this study, we propose a stochastic resonance-effect-based EEG preprocessing module composed of three asymmetrical overdamped bistable systems in parallel. By setting different asymmetries for the three parallel units, the inherent noise can be transferred to the different spectral components of the EEG through the asymmetric stochastic resonance effect. In this process, the proposed preprocessing module not only avoids the loss of information of EEG but also provides a CNN with high-quality EEG of diversified frequency information to enhance its performance. By combining the proposed preprocessing module with a residual neural network, we developed an intelligent diagnostic system for predicting seizure onset. The developed system achieved an average sensitivity of 98.96% on the CHB-MIT dataset and 95.45% on the Siena dataset, with a false prediction rate of 0.048/h and 0.033/h, respectively. In addition, a comparative analysis demonstrated the superiority of the developed diagnostic system with the proposed preprocessing module over other existing methods.

Temporal transformer-spatial graph convolutional network: an intelligent classification model for anti N-methyl-D-aspartate receptor encephalitis based on electroencephalogram signal

Encephalitis is a disease typically caused by viral infections or autoimmunity. The most common type of autoimmune encephalitis is anti-N-methyl-D-aspartate receptor (NMDAR) antibody-mediated, known as anti-NMDA receptor encephalitis, which is a rare disease. Specific EEG patterns, including "extreme delta brush" (EDB), have been reported in patients with anti-NMDA receptor encephalitis. The aim of this study was to develop an intelligent diagnostic model for encephalitis based on EEG signals. A total of 131 Participants were selected based on reasonable inclusion criteria and divided into three groups: health control (35 participants), viral encephalitis (58 participants), and anti NMDAR receptor encephalitis (55 participants). Due to the low prevalence of anti-NMDAR receptor encephalitis, it took several years to collect participants' EEG signals while they were in an awake state. EEG signals were collected and analyzed following the international 10-20 system layout. We proposed a model called Temporal Transformer-Spatial Graph Convolutional Network (TT-SGCN), which consists of a Preprocess Module, a Temporal Transformer Module (TTM), and a Spatial Graph Convolutional Module (SGCM). The raw EEG signal was preprocessed according to traditional procedures, including filtering, averaging, and Independent Component Analysis (ICA) method. The EEG signal was then segmented and transformed using short-time Fourier transform (STFT) to produce concatenated power density (CPD) maps, which served as inputs for the proposed model. TTM extracted the time-frequency features of each channel, and SGCM fused these features using graph convolutional methods based on the location of electrodes. The model was evaluated in two experiments: classification of the three groups and pairwise classification among the three groups. The model was trained using two stages and achieved the performance, with an accuracy of 82.23%, recall of 80.75%, precision of 82.51%, and F1 score of 81.23% in the classification of the three groups. The proposed model has the potential to become an intelligent auxiliary diagnostic tool for encephalitis.

Epileptic seizures detection and the analysis of optimal seizure prediction horizon based on frequency and phase analysis

Changes in the frequency composition of the human electroencephalogram are associated with the transitions to epileptic seizures. Cross-frequency coupling (CFC) is a measure of neural oscillations in different frequency bands and brain areas, and specifically phase-amplitude coupling (PAC), a form of CFC, can be used to characterize these dynamic transitions. In this study, we propose a method for seizure detection and prediction based on frequency domain analysis and PAC combined with machine learning. We analyzed two databases, the Siena Scalp EEG database and the CHB-MIT database, and used the frequency features and modulation index (MI) for time-dependent quantification. The extracted features were fed to a random forest classifier for classification and prediction. The seizure prediction horizon (SPH) was also analyzed based on the highest-performing band to maximize the time for intervention and treatment while ensuring the accuracy of the prediction. Under comprehensive consideration, the results demonstrate that better performance could be achieved at an interval length of 5 min with an average accuracy of 85.71% and 95.87% for the Siena Scalp EEG database and the CHB-MIT database, respectively. As for the adult database, the combination of PAC analysis and classification can be of significant help for seizure detection and prediction. It suggests that the rarely used SPH also has a major impact on seizure detection and prediction and further explorations for the application of PAC are needed.

Removing artefacts and periodically retraining improve performance of neural network-based seizure prediction models

The development of seizure prediction models is often based on long-term scalp electroencephalograms (EEGs) since they capture brain electrical activity, are non-invasive, and come at a relatively low-cost. However, they suffer from major shortcomings. First, long-term EEG is usually highly contaminated with artefacts. Second, changes in the EEG signal over long intervals, known as concept drift, are often neglected. We evaluate the influence of these problems on deep neural networks using EEG time series and on shallow neural networks using widely-used EEG features. Our patient-specific prediction models were tested in 1577 hours of continuous EEG, containing 91 seizures from 41 patients with temporal lobe epilepsy who were undergoing pre-surgical monitoring. Our results showed that cleaning EEG data, using a previously developed artefact removal method based on deep convolutional neural networks, improved prediction performance. We also found that retraining the models over time reduced false predictions. Furthermore, the results show that although deep neural networks processing EEG time series are less susceptible to false alarms, they may need more data to surpass feature-based methods. These findings highlight the importance of robust data denoising and periodic adaptation of seizure prediction models.

The performance evaluation of the state-of-the-art EEG-based seizure prediction models

The recurrent and unpredictable nature of seizures can lead to unintentional injuries and even death. The rapid development of electroencephalogram (EEG) and Artificial Intelligence (AI) technologies has made it possible to predict seizures in real-time through brain-machine interfaces (BCI), allowing advanced intervention. To date, there is still much room for improvement in predictive seizure models constructed by EEG using machine learning (ML) and deep learning (DL). But, the most critical issue is how to improve the performance and generalization of the model, which involves some confusing conceptual and methodological issues. This review focuses on analyzing several factors affecting the performance of seizure prediction models, focusing on the aspects of post-processing, seizure occurrence period (SOP), seizure prediction horizon (SPH), and algorithms. Furthermore, this study presents some new directions and suggestions for building high-performance prediction models in the future. We aimed to clarify the concept for future research in related fields and improve the performance of prediction models to provide a theoretical basis for future applications of wearable seizure detection devices.

On the Intelligent Computing Model of Diagnosis Teaching in Preschool Education in Colleges and Universities under the Background of Big Data

In order to infer the cognitive state of students and provide teachers with the potential learning state of students, a diagnostic teaching model for preschool education in colleges and universities under the background of big data is proposed. By increasing students' programming ability and modeling students' theoretical and practical abilities at the same time, the cognitive diagnosis is introduced into the field of computer teaching, so as to make it applicable to computer classrooms and provide students' cognitive information needed for teaching. The experimental results show that the advantages of the CDF-CSE approach gradually emerge as the training data become sparse (the proportion of training data decreases from 80% to 20%). In the combined questions of the three datasets, when the training set is 20% and MAE is used as the criterion, the CDF-CSE model improves by 47.8%, 65.8%, and 49.8%, respectively, compared with the other methods that perform best on the training set. When the number of questions is small, the CDF-CSE model improves by 37.8%, 42.5%, and 27.7% on RMSE on three datasets, respectively, compared with the best-performing other methods. When there are more questions, it has 32.3%, 36.5%, and 45.6% improvement, respectively. It is concluded that this model can accurately predict students' performance in computer courses and provide detailed and rich cognitive reports.

Dual Encoder-Based Dynamic-Channel Graph Convolutional Network With Edge Enhancement for Retinal Vessel Segmentation

Retinal vessel segmentation with deep learning technology is a crucial auxiliary method for clinicians to diagnose fundus diseases. However, the deep learning approaches inevitably lose the edge information, which contains spatial features of vessels while performing down-sampling, leading to the limited segmentation performance of fine blood vessels. Furthermore, the existing methods ignore the dynamic topological correlations among feature maps in the deep learning framework, resulting in the inefficient capture of the channel characterization. To address these limitations, we propose a novel dual encoder-based dynamic-channel graph convolutional network with edge enhancement (DE-DCGCN-EE) for retinal vessel segmentation. Specifically, we first design an edge detection-based dual encoder to preserve the edge of vessels in down-sampling. Secondly, we investigate a dynamic-channel graph convolutional network to map the image channels to the topological space and synthesize the features of each channel on the topological map, which solves the limitation of insufficient channel information utilization. Finally, we study an edge enhancement block, aiming to fuse the edge and spatial features in the dual encoder, which is beneficial to improve the accuracy of fine blood vessel segmentation. Competitive experimental results on five retinal image datasets validate the efficacy of the proposed DE-DCGCN-EE, which achieves more remarkable segmentation results against the other state-of-the-art methods, indicating its potential clinical application.

Efficient graph convolutional networks for seizure prediction using scalp EEG

Epilepsy is a chronic brain disease that causes persistent and severe damage to the physical and mental health of patients. Daily effective prediction of epileptic seizures is crucial for epilepsy patients especially those with refractory epilepsy. At present, a large number of deep learning algorithms such as Convolutional Neural Networks and Recurrent Neural Networks have been used to predict epileptic seizures and have obtained better performance than traditional machine learning methods. However, these methods usually transform the Electroencephalogram (EEG) signal into a Euclidean grid structure. The conversion suffers from loss of adjacent spatial information, which results in deep learning models requiring more storage and computational consumption in the process of information fusion after information extraction. This study proposes a general Graph Convolutional Networks (GCN) model architecture for predicting seizures to solve the problem of oversized seizure prediction models based on exploring the graph structure of EEG signals. As a graph classification task, the network architecture includes graph convolution layers that extract node features with one-hop neighbors, pooling layers that summarize abstract node features; and fully connected layers that implement classification, resulting in superior prediction performance and smaller network size. The experiment shows that the model has an average sensitivity of 96.51%, an average AUC of 0.92, and a model size of 15.5 k on 18 patients in the CHB-MIT scalp EEG dataset. Compared with traditional deep learning methods, which require a large number of parameters and computational effort and are demanding in terms of storage space and energy consumption, this method is more suitable for implementation on compact, low-power wearable devices as a standard process for building a generic low-consumption graph network model on similar biomedical signals. Furthermore, the edge features of graphs can be used to make a preliminary determination of locations and types of discharge, making it more clinically interpretable.

A prediction model integrating synchronization biomarkers and clinical features to identify responders to vagus nerve stimulation among pediatric patients with drug-resistant epilepsy

Aims

Vagus nerve stimulation (VNS) is a neuromodulation therapy for children with drug‐resistant epilepsy (DRE). The efficacy of VNS is heterogeneous. A prediction model is needed to predict the efficacy before implantation.

Methods

We collected data from children with DRE who underwent VNS implantation and received regular programming for at least 1 year. Preoperative clinical information and scalp video electroencephalography (EEG) were available in 88 children. Synchronization features, including phase lag index (PLI), weighted phase lag index (wPLI), and phase‐locking value (PLV), were compared between responders and non‐responders. We further adapted a support vector machine (SVM) classifier selected from 25 clinical and 18 synchronization features to build a prediction model for efficacy in a discovery cohort (n = 70) and was tested in an independent validation cohort (n = 18).

Results

In the discovery cohort, the average interictal awake PLI in the high beta band was significantly higher in responders than non‐responders (p < 0.05). The SVM classifier generated from integrating both clinical and synchronization features had the best prediction efficacy, demonstrating an accuracy of 75.7%, precision of 80.8% and area under the receiver operating characteristic (AUC) of 0.766 on 10‐fold cross‐validation. In the validation cohort, the prediction model demonstrated an accuracy of 61.1%.

Conclusion

This study established the first prediction model integrating clinical and baseline synchronization features for preoperative VNS responder screening among children with DRE. With further optimization of the model, we hope to provide an effective and convenient method for identifying responders before VNS implantation.

Multi-Channel Vision Transformer for Epileptic Seizure Prediction

Epilepsy is a neurological disorder that causes recurrent seizures and sometimes loss of awareness. Around 30% of epileptic patients continue to have seizures despite taking anti-seizure medication. The ability to predict the future occurrence of seizures would enable the patients to take precautions against probable injuries and administer timely treatment to abort or control impending seizures. In this study, we introduce a Transformer-based approach called Multi-channel Vision Transformer (MViT) for automated and simultaneous learning of the spatio-temporal-spectral features in multi-channel EEG data. Continuous wavelet transform, a simple yet efficient pre-processing approach, is first used for turning the time-series EEG signals into image-like time-frequency representations named Scalograms. Each scalogram is split into a sequence of fixed-size non-overlapping patches, which are then fed as inputs to the MViT for EEG classification. Extensive experiments on three benchmark EEG datasets demonstrate the superiority of the proposed MViT algorithm over the state-of-the-art seizure prediction methods, achieving an average prediction sensitivity of 99.80% for surface EEG and 90.28-91.15% for invasive EEG data.

Patient-Specific Seizure Prediction via Adder Network and Supervised Contrastive Learning

Deep learning (DL) methods have been widely used in the field of seizure prediction from electroencephalogram (EEG) in recent years. However, DL methods usually have numerous multiplication operations resulting in high computational complexity. In addtion, most of the current approaches in this field focus on designing models with special architectures to learn representations, ignoring the use of intrinsic patterns in the data. In this study, we propose a simple and effective end-to-end adder network and supervised contrastive learning (AddNet-SCL). The method uses addition instead of the massive multiplication in the convolution process to reduce the computational cost. Besides, contrastive learning is employed to effectively use label information, points of the same class are clustered together in the projection space, and points of different class are pushed apart at the same time. Moreover, the proposed model is trained by combining the supervised contrastive loss from the projection layer and the cross-entropy loss from the classification layer. Since the adder networks uses the ℓ1-norm distance as the similarity measure between the input feature and the filters, the gradient function of the network changes, an adaptive learning rate strategy is employed to ensure the convergence of AddNet-CL. Experimental results show that the proposed method achieves 94.9% sensitivity, an area under curve (AUC) of 94.2%, and a false positive rate of (FPR) 0.077/h on 19 patients in the CHB-MIT database and 89.1% sensitivity, an AUC of 83.1%, and an FPR of 0.120/h in the Kaggle database. Competitive results show that this method has broad prospects in clinical practice.

Virtual Adversarial Training-Based Deep Feature Aggregation Network From Dynamic Effective Connectivity for MCI Identification

Dynamic functional connectivity (dFC) network inferred from resting-state fMRI reveals macroscopic dynamic neural activity patterns for brain disease identification. However, dFC methods ignore the causal influence between the brain regions. Furthermore, due to the complex non-Euclidean structure of brain networks, advanced deep neural networks are difficult to be applied for learning high-dimensional representations from brain networks. In this paper, a group constrained Kalman filter (gKF) algorithm is proposed to construct dynamic effective connectivity (dEC), where the gKF provides a more comprehensive understanding of the directional interaction within the dynamic brain networks than the dFC methods. Then, a novel virtual adversarial training convolutional neural network (VAT-CNN) is employed to extract the local features of dEC. The VAT strategy improves the robustness of the model to adversarial perturbations, and therefore avoids the overfitting problem effectively. Finally, we propose the high-order connectivity weight-guided graph attention networks (cwGAT) to aggregate features of dEC. By injecting the weight information of high-order connectivity into the attention mechanism, the cwGAT provides more effective high-level feature representations than the conventional GAT. The high-level features generated from the cwGAT are applied for binary classification and multiclass classification tasks of mild cognitive impairment (MCI). Experimental results indicate that the proposed framework achieves the classification accuracy of 90.9%, 89.8%, and 82.7% for normal control (NC) vs. early MCI (EMCI), EMCI vs. late MCI (LMCI), and NC vs. EMCI vs. LMCI classification respectively, outperforming the state-of-the-art methods significantly.

An Overview of EEG-based Machine Learning Methods in Seizure Prediction and Opportunities for Neurologists in this Field

The unpredictability of epileptic seizures is one of the most problematic aspects of the field of epilepsy. Methods or devices capable of detecting seizures minutes before they occur may help prevent injury or even death and significantly improve the quality of life. Machine learning (ML) is an emerging technology that can markedly enhance algorithm performance by interpreting data. ML has gained increasing attention from medical researchers in recent years. Its epilepsy applications range from the localization of the epileptic region, predicting the medical or surgical outcome of epilepsy, and automated electroencephalography (EEG) analysis to seizure prediction. While ML has good prospects with regard to detecting epileptic seizures via EEG signals, many clinicians are still unfamiliar with this field. This work briefly summarizes the history and recent significant progress made in this field and clarifies the essential components of the automatic seizure detection system using ML methodologies for clinicians. This review also proposes how neurologists can actively contribute to ensure improvements in seizure prediction using EEG-based ML.