Cross-patient seizure prediction via continuous domain adaptation and similar sample replay

Seizure prediction based on electroencephalogram (EEG) for people with epilepsy, a common brain disorder worldwide, has great potential for life quality improvement. To alleviate the high degree of heterogeneity among patients, several works have attempted to learn common seizure feature distributions based on the idea of domain adaptation to enhance the generalization ability of the model. However, existing methods ignore the inherent inter-patient discrepancy within the source patients, resulting in disjointed distributions that impede effective domain alignment. To eliminate this effect, we introduce the concept of multi-source domain adaptation (MSDA), considering each source patient as a separate domain. To avoid additional model complexity from MSDA, we propose a continuous domain adaptation approach for seizure prediction based on the convolutional neural network (CNN), which performs sequential training on multiple source domains. To relieve the model catastrophic forgetting during sequential training, we replay similar samples from each source domain, while learning common feature representations based on subdomain alignment. Evaluated on a publicly available epilepsy dataset, our proposed method attains a sensitivity of 85.0% and a false alarm rate (FPR) of 0.224/h. Compared to the prevailing domain adaptation paradigm and existing domain adaptation works in the field, the proposed method can efficiently capture the knowledge of different patients, extract better common seizure representations, and achieve state-of-the-art performance.

FusionXNet: enhancing EEG-based seizure prediction with integrated convolutional and Transformer architectures

Objective. Effective seizure prediction can reduce patient burden, improve clinical treatment accuracy, and lower healthcare costs. However, existing deep learning-based seizure prediction methods primarily rely on single models, which have limitations in feature extraction. This study aims to develop a hybrid model that integrates the advantages of convolutional neural networks (CNNs) and Transformer to enhance seizure prediction performance.Approach. We propose FusionXNet, a hybrid model inspired by CNNs and Transformer architectures, for seizure prediction. Specifically, we design a token synthesis unit to extract local features using convolution operations and capture global electroencephalography (EEG) representations via attention mechanisms. By merging local and global features extracted from the EEG segments, FusionXNet enhances feature representations, which are subsequently fed into a classifier for final seizure prediction.Main results. We evaluate the model on the publicly available Boston Children's Hospital and the Massachusetts Institute of Technology dataset, conducting segment-based and event-based experiments in both patient-specific and cross-patient settings. In event-based patient-specific experiments, FusionXNet achieves a sensitivity of 97.602% and a false positive rate (FPR) of 0.059 h-1. The results demonstrate that the proposed model effectively predicts seizures with high sensitivity and a low FPR, outperforming existing methods.Significance. The proposed FusionXNet model provides a robust and efficient approach for seizure prediction by leveraging both local and global feature extraction. The high sensitivity and low FPR indicate its potential for real-world clinical applications, improving patient management and reducing healthcare costs.

EEG detection and recognition model for epilepsy based on dual attention mechanism

In the field of clinical neurology, automated detection of epileptic seizures based on electroencephalogram (EEG) signals has the potential to significantly accelerate the diagnosis of epilepsy. This rapid and accurate diagnosis enables doctors to provide timely and effective treatment for patients, significantly reducing the frequency of future epileptic seizures and the risk of related complications, which is crucial for safeguarding patients' long-term health and quality of life. Presently, deep learning techniques, particularly Convolutional Neural Networks (CNNs) and Long Short-Term Memory networks (LSTMs), have demonstrated remarkable accuracy improvements across various domains. Consequently, researchers have utilized these methodologies in studies focused on recognizing epileptic signals through EEG analysis. However, current models based on CNN and LSTM still heavily rely on data preprocessing and feature extraction steps. Additionally, CNNs exhibit limitations in perceiving global dependencies, while LSTMs encounter challenges such as gradient vanishing in long sequences. This paper introduced an innovative EEG recognition model, that is the Spatio-temporal feature fusion epilepsy EEG recognition model with dual attention mechanism (STFFDA). STFFDA is comprised of a multi-channel framework that directly interprets epileptic states from raw EEG signals, thereby eliminating the need for extensive data preprocessing and feature extraction. Notably, our method demonstrates impressive accuracy results, achieving 95.18% and 77.65% on single-validation tests conducted on the datasets of CHB-MIT and Bonn University, respectively. Additionally, in the 10-fold cross-validation tests, their accuracy rates were 92.42% and 67.24%, respectively. In summary, it is demonstrated that the seizure detection method STFFD based on EEG signals has significant potential in accelerating diagnosis and improving patient prognosis, especially since it can achieve high accuracy rates without extensive data preprocessing or feature extraction.

Predicting Epileptic Seizures Using EfficientNet-B0 and SVMs: A Deep Learning Methodology for EEG Analysis

Seizure prediction is a critical challenge in epilepsy management, offering the potential to improve patient outcomes through timely interventions. This study proposes a novel framework combining a convolutional neural network (CNN) based on EfficientNet-B0 and an ensemble of six Support Vector Machines (SVMs) with a voting mechanism for robust seizure prediction. The framework leverages normalized Short-Time Fourier Transform (STFT) and channel correlation features extracted from EEG signals to capture both spectral and spatial information. The methodology was validated on the CHB-MIT dataset across preictal windows of 10, 20, and 30 min, achieving accuracies of 96.12%, 94.89%, and 94.21%, and sensitivities of 95.21%, 93.98%, and 93.55%, respectively. Comparing the results with state-of-the-art methods, we highlight the framework's robustness and adaptability. The EfficientNet-B0 backbone ensures high accuracy with computational efficiency, while the SVM ensemble enhances prediction reliability by mitigating noise and variability in EEG data.

Epilepsy Prediction and Detection Using Attention-CssCDBN with Dual-Task Learning

Epilepsy is a group of neurological disorders characterized by epileptic seizures, and it affects tens of millions of people worldwide. Currently, the most effective diagnostic method employs the monitoring of brain activity through electroencephalogram (EEG). However, it is critical to predict epileptic seizures in patients prior to their onset, allowing for the administration of preventive medications before the seizure occurs. As a pivotal application of artificial intelligence in medical treatment, learning the features of EEGs for epilepsy prediction and detection remains a challenging problem, primarily due to the presence of intra-class and inter-class variations in EEG signals. In this study, we propose the spatio-temporal EEGNet, which integrates contractive slab and spike convolutional deep belief network (CssCDBN) with a self-attention architecture, augmented by dual-task learning to address this issue. Initially, our model was designed to extract high-order and deep representations from EEG spectrum images, enabling the simultaneous capture of spatial and temporal information. Furthermore, EEG-based verification aids in reducing intra-class variation by considering the time correlation of the EEG during the fine-tuning stage, resulting in easier inference and training. The results demonstrate the notable efficacy of our proposed method. Our method achieved a sensitivity of 98.5%, a false-positive rate (FPR) of 0.041, a prediction time of 50.92 min during the epilepsy prediction task, and an accuracy of 94.1% during the epilepsy detection task, demonstrating significant improvements over current state-of-the-art methods.

An interpretable and generalizable deep learning model for iEEG-based seizure prediction using prototype learning and contrastive learning

Epileptic seizure prediction plays a crucial role in enhancing the quality of life for individuals with epilepsy. Over recent years, a multitude of deep learning-based approaches have emerged to tackle this challenging task, leading to significant advancements. However, the 'black-box' nature of deep learning models and the considerable interpatient variability significantly impede their interpretability and generalization, thereby severely hampering their efficacy in real-world clinical applications. To address these issues, our study aims to establish an interpretable and generalizable seizure prediction model that meets the demands of clinical diagnosis. Our method extends self-interpretable prototype learning networks into a novel domain adaptation framework designed specifically for cross-patient seizure prediction. The proposed framework enables patient-level interpretability by tracing the origins of significant prototypes. For instance, it could provide information about the seizure type of the patient to which the prototype belongs. This surpasses the existing sample-level interpretability, which is limited to individual patient samples. To further improve the model's generalization capability, we introduce a contrastive semantic alignment loss constraint to the embedding space, enhancing the robustness of the learned prototypes. We evaluate our proposed model using the Freiburg intracranial electroencephalography (iEEG) dataset, which consists of 20 patients and a total of 82 seizures. The experimental results demonstrated a high sensitivity of 79.0%, a low false prediction rate of 0.183, and a high area under the receiver operating characteristic curve (AUC) value of 0.804, achieving state-of-the-art performance with self-interpretable evidence in contrast to the current cross-patient seizure prediction methods. Our study represents a significant step forward in developing an interpretable and generalizable model for seizure prediction, thereby facilitating the application of deep learning models in clinical diagnosis.

A Lightweight Convolutional Neural Network-Reformer Model for Efficient Epileptic Seizure Detection

A real-time and reliable automatic detection system for epileptic seizures holds significant value in assisting physicians with rapid diagnosis and treatment of epilepsy. Aiming to address this issue, a novel lightweight model called Convolutional Neural Network-Reformer (CNN-Reformer) is proposed for seizure detection on long-term EEG. The CNN-Reformer consists of two main parts: the Data Reshaping (DR) module and the Efficient Attention and Concentration (EAC) module. This framework reduces network parameters while retaining effective feature extraction of multi-channel EEGs, thereby improving model computational efficiency and real-time performance. Initially, the raw EEG signals undergo Discrete Wavelet Transform (DWT) for signal filtering, and then fed into the DR module for data compression and reshaping while preserving local features. Subsequently, these local features are sent to the EAC module to extract global features and perform categorization. Post-processing involving sliding window averaging, thresholding, and collar techniques is further deployed to reduce the false detection rate (FDR) and improve detection performance. On the CHB-MIT scalp EEG dataset, our method achieves an average sensitivity of 97.57%, accuracy of 98.09%, and specificity of 98.11% at segment-based level, and a sensitivity of 96.81%, along with FDR of 0.27/h, and latency of 17.81 s at the event-based level. On the SH-SDU dataset we collected, our method yielded segment-based sensitivity of 94.51%, specificity of 92.83%, and accuracy of 92.81%, along with event-based sensitivity of 94.11%. The average testing time for 1[Formula: see text]h of multi-channel EEG signals is 1.92[Formula: see text]s. The excellent results and fast computational speed of the CNN-Reformer model demonstrate its potential for efficient seizure detection.

Anchoring temporal convolutional networks for epileptic seizure prediction

Objective. Accurate and timely prediction of epileptic seizures is crucial for empowering patients to mitigate their impact or prevent them altogether. Current studies predominantly focus on short-term seizure predictions, which causes the prediction time to be shorter than the onset of antiepileptic, thus failing to prevent seizures. However, longer epilepsy prediction faces the problem that as the preictal period lengthens, it increasingly resembles the interictal period, complicating differentiation.Approach. To address these issues, we employ the sample entropy method for feature extraction from electroencephalography (EEG) signals. Subsequently, we introduce the anchoring temporal convolutional networks (ATCN) model for longer-term, patient-specific epilepsy prediction. ATCN utilizes dilated causal convolutional networks to learn time-dependent features from previous data, capturing temporal causal correlations within and between samples. Additionally, the model also incorporates anchoring data to enhance the performance of epilepsy prediction further. Finally, we proposed a multilayer sliding window prediction algorithm for seizure alarms.Main results. Evaluation on the Freiburg intracranial EEG dataset shows our approach achieves 100% sensitivity, a false prediction rate (FPR) of 0.09 per hour, and an average prediction time (APT) of 98.92 min. Using the CHB-MIT scalp EEG dataset, we achieve 97.44% sensitivity, a FPR of 0.12 per hour, and an APT of 93.54 min.Significance. These results demonstrate that our approach is adequate for seizure prediction over a more extended prediction range on intracranial and scalp EEG datasets. The APT of our approach exceeds the typical onset time of antiepileptic. This approach is particularly beneficial for patients who need to take medication at regular intervals, as they may only need to take their medication when our method issues an alarm. This capability has the potential to prevent seizures, which will greatly improve patients' quality of life.

An Efficient Epilepsy Prediction Model on European Dataset With Model Evaluation Considering Seizure Types

This paper develops a computationally efficient model for automatic patient-specific seizure prediction using a two-layer LSTM from multichannel intracranial electroencephalogram time-series data. We decrease the number of parameters by employing a smaller input size and fewer electrodes, thereby making the model a viable option for wearable and implantable devices. We test the proposed prediction model on 26 patients from the European iEEG dataset, which is the largest epileptic seizure dataset. We also apply an automatic preprocessing technique based on a common average reference to remove artifacts from this dataset. The simulation results show that the model with its simple structure in conjunction with the mean post-processing procedure performed the best, with an average AUC of 0.885. This study is the first that utilizes the European database for epilepsy prediction application and the first that analyzes the effect of the seizure type on the system performance and demonstrates that the seizure type has a considerable impact.

Research progress of epileptic seizure prediction methods based on EEG

At present, at least 30% of refractory epilepsy patients in the world cannot be effectively controlled and treated. The suddenness and unpredictability of seizures greatly affect the physical and mental health and even the life safety of patients, and the realization of early prediction of seizures and the adoption of interventions are of great significance to the improvement of patients' quality of life. In this paper, we firstly introduce the design process of EEG-based seizure prediction methods, introduce several databases commonly used in the research, and summarize the commonly used methods in pre-processing, feature extraction, classification and identification, and post-processing. Then, based on scalp EEG and intracranial EEG respectively, we reviewed the current status of epileptic seizure prediction research from five commonly used feature analysis methods, and make a comprehensive evaluation of both. Finally, this paper describes the reasons why the current algorithms cannot be applied to the clinic, summarizes their limitations, and gives corresponding suggestions, aiming to provide improvement directions for subsequent research. In addition, deep learning algorithms have emerged in recent years, and this paper also compares the advantages and disadvantages of deep learning algorithms with traditional machine learning methods, in the hope of providing researchers with new technologies and new ideas and making significant breakthroughs in the field of epileptic seizure prediction.

EEG-Based Seizure Prediction Using Hybrid DenseNet-ViT Network with Attention Fusion

Epilepsy seizure prediction is vital for enhancing the quality of life for individuals with epilepsy. In this study, we introduce a novel hybrid deep learning architecture, merging DenseNet and Vision Transformer (ViT) with an attention fusion layer for seizure prediction. DenseNet captures hierarchical features and ensures efficient parameter usage, while ViT offers self-attention mechanisms and global feature representation. The attention fusion layer effectively amalgamates features from both networks, guaranteeing the most relevant information is harnessed for seizure prediction. The raw EEG signals were preprocessed using the short-time Fourier transform (STFT) to implement time-frequency analysis and convert EEG signals into time-frequency matrices. Then, they were fed into the proposed hybrid DenseNet-ViT network model to achieve end-to-end seizure prediction. The CHB-MIT dataset, including data from 24 patients, was used for evaluation and the leave-one-out cross-validation method was utilized to evaluate the performance of the proposed model. Our results demonstrate superior performance in seizure prediction, exhibiting high accuracy and low redundancy, which suggests that combining DenseNet, ViT, and the attention mechanism can significantly enhance prediction capabilities and facilitate more precise therapeutic interventions.

Epileptic Seizure Prediction Using Spatiotemporal Feature Fusion on EEG

Electroencephalography (EEG) plays a crucial role in epilepsy analysis, and epileptic seizure prediction has significant value for clinical treatment of epilepsy. Currently, prediction methods using Convolutional Neural Network (CNN) primarily focus on local features of EEG, making it challenging to simultaneously capture the spatial and temporal features from multi-channel EEGs to identify the preictal state effectively. In order to extract inherent spatial relationships among multi-channel EEGs while obtaining their temporal correlations, this study proposed an end-to-end model for the prediction of epileptic seizures by incorporating Graph Attention Network (GAT) and Temporal Convolutional Network (TCN). Low-pass filtered EEG signals were fed into the GAT module for EEG spatial feature extraction, and followed by TCN to capture temporal features, allowing the end-to-end model to acquire the spatiotemporal correlations of multi-channel EEGs. The system was evaluated on the publicly available CHB-MIT database, yielding segment-based accuracy of 98.71%, specificity of 98.35%, sensitivity of 99.07%, and F1-score of 98.71%, respectively. Event-based sensitivity of 97.03% and False Positive Rate (FPR) of 0.03/h was also achieved. Experimental results demonstrated this system can achieve superior performance for seizure prediction by leveraging the fusion of EEG spatiotemporal features without the need of feature engineering.

Resource-Efficient Continual Learning for Personalized Online Seizure Detection

Epilepsy, a major neurological disease, requires careful diagnosis and treatment. However, the detection of epileptic seizures remains a significant challenge. Current clinical practice relies on expert analysis of EEG signals, a process that is time-consuming and requires specialized knowledge. This paper explores the potential for automated epileptic seizure detection using deep learning techniques, with a particular focus on personalized models based on continual learning. We highlight the importance of adapting these models to each patient's unique EEG signal features, which evolve over time. Our approach addresses the fundamental challenge of integrating new data into existing models without losing previously acquired information, a common issue in static deep learning models when applied in dynamic environments. In this study, we propose a novel continual learning algorithm for seizure detection, which integrates a replay buffer mechanism. This mechanism is key to retaining relevant information on past data while acquiring new one, thus effectively enhancing the model's performance over time. Our methodology is designed to be resource-efficient, making it suitable for implementation in embedded systems. We demonstrate the effectiveness of our approach using the CHB-MIT dataset, achieving an improvement of 35.34% in the F1 score with respect to a fine-tuning approach that does not consider catastrophic forgetting. Furthermore, we show that a small 1-hour data replay buffer suffices to achieve F1 scores comparable to that of a resource-unlimited scenario, while also decreasing the False Alarm Rate in 24 hours by 33% compared to a resource-unconstrained method.

Supervised and Unsupervised Deep Learning Approaches for EEG Seizure Prediction

Epilepsy affects more than 50 million people worldwide, making it one of the world's most prevalent neurological diseases. The main symptom of epilepsy is seizures, which occur abruptly and can cause serious injury or death. The ability to predict the occurrence of an epileptic seizure could alleviate many risks and stresses people with epilepsy face. We formulate the problem of detecting preictal (or pre-seizure) with reference to normal EEG as a precursor to incoming seizure. To this end, we developed several supervised deep learning approaches model to identify preictal EEG from normal EEG. We further develop novel unsupervised deep learning approaches to train the models on only normal EEG, and detecting pre-seizure EEG as an anomalous event. These deep learning models were trained and evaluated on two large EEG seizure datasets in a person-specific manner. We found that both supervised and unsupervised approaches are feasible; however, their performance varies depending on the patient, approach and architecture. This new line of research has the potential to develop therapeutic interventions and save human lives.

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.

Attention-based deep convolutional neural network for classification of generalized and focal epileptic seizures

Epilepsy affects over 50 million people globally. Electroencephalography is critical for epilepsy diagnosis, but manual seizure classification is time-consuming and requires extensive expertise. This paper presents an automated multi-class seizure classification model using EEG signals from the Temple University Hospital Seizure Corpus ver. 1.5.2. 11 features including time-based correlation, time-based eigenvalues, power spectral density, frequency-based correlation, frequency-based eigenvalues, sample entropy, spectral entropy, logarithmic sum, standard deviation, absolute mean, and ratio of Daubechies D4 wavelet transformed coefficients were extracted from 10-second sliding windows across channels. The model combines multi-head self-attention mechanism with a deep convolutional neural network (CNN) to classify seven subtypes of generalized and focal epileptic seizures. The model achieved 0.921 weighted accuracy and 0.902 weighted F1 score in classifying focal onset non-motor, generalized onset non-motor, simple partial, complex partial, absence, tonic, and tonic-clonic seizures. In comparison, a CNN model without multi-head attention achieved 0.767 weighted accuracy. Ablation studies were conducted to validate the importance of transformer encoders and attention. The promising classification results demonstrate the potential of deep learning for handling EEG complexity and improving epilepsy diagnosis. This seizure classification model could enable timely interventions when translated into clinical practice.

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.

Data leakage in deep learning studies of translational EEG

A growing number of studies apply deep neural networks (DNNs) to recordings of human electroencephalography (EEG) to identify a range of disorders. In many studies, EEG recordings are split into segments, and each segment is randomly assigned to the training or test set. As a consequence, data from individual subjects appears in both the training and the test set. Could high test-set accuracy reflect data leakage from subject-specific patterns in the data, rather than patterns that identify a disease? We address this question by testing the performance of DNN classifiers using segment-based holdout (in which segments from one subject can appear in both the training and test set), and comparing this to their performance using subject-based holdout (where all segments from one subject appear exclusively in either the training set or the test set). In two datasets (one classifying Alzheimer's disease, and the other classifying epileptic seizures), we find that performance on previously-unseen subjects is strongly overestimated when models are trained using segment-based holdout. Finally, we survey the literature and find that the majority of translational DNN-EEG studies use segment-based holdout. Most published DNN-EEG studies may dramatically overestimate their classification performance on new subjects.

A hybrid 1D CNN-BiLSTM model for epileptic seizure detection using multichannel EEG feature fusion

Epilepsy, a chronic non-communicable disease is characterized by repeated unprovoked seizures, which are transient episodes of abnormal electrical activity in the brain. While Electroencephalography (EEG) is considered as the gold standard for diagnosis in current clinical practice, manual inspection of EEG is time consuming and biased. This paper presents a novel hybrid 1D CNN-Bi LSTM feature fusion model for automatically detecting seizures. The proposed model leverages spatial features extracted by one dimensional convolutional neural network and temporal features extracted by bi directional long short-term memory network. Ictal and inter ictal data is first acquired from the long multichannel EEG record. The acquired data is segmented and labelled using small fixed windows. Signal features are then extracted from the segments concurrently by the parallel combination of CNN and Bi-LSTM. The spatial and temporal features thus captured are then fused to enhance classification accuracy of model. The approach is validated using benchmark CHB-MIT dataset and 5-fold cross validation which resulted in an average accuracy of 95.90%, with precision 94.78%, F1 score 95.95%. Notably model achieved average sensitivity of 97.18% with false positivity rate at 0.05/hr. The significantly lower false positivity and false negativity rates indicate that the proposed model is a promising tool for detecting seizures in epilepsy patients. The employed parallel path network benefits from memory function of Bi-LSTM and strong feature extraction capabilities of CNN. Moreover, eliminating the need for any domain transformation or additional preprocessing steps, model effectively reduces complexity and enhances efficiency, making it suitable for use by clinicians during the epilepsy diagnostic process.

Concept-drifts adaptation for machine learning EEG epilepsy seizure prediction

Seizure prediction remains a challenge, with approximately 30% of patients unresponsive to conventional treatments. Addressing this issue is crucial for improving patients' quality of life, as timely intervention can mitigate the impact of seizures. In this research field, it is critical to identify the preictal interval, the transition from regular brain activity to a seizure. While previous studies have explored various Electroencephalogram (EEG) based methodologies for prediction, few have been clinically applicable. Recent studies have underlined the dynamic nature of EEG data, characterised by data changes with time, known as concept drifts, highlighting the need for automated methods to detect and adapt to these changes. In this study, we investigate the effectiveness of automatic concept drift adaptation methods in seizure prediction. Three patient-specific seizure prediction approaches with a 10-minute prediction horizon are compared: a seizure prediction algorithm incorporating a window adjustment method by optimising performance with Support Vector Machines (Backwards-Landmark Window), a seizure prediction algorithm incorporating a data-batch (seizures) selection method using a logistic regression (Seizure-batch Regression), and a seizure prediction algorithm with a dynamic integration of classifiers (Dynamic Weighted Ensemble). These methods incorporate a retraining process after each seizure and use a combination of univariate linear features and SVM classifiers. The Firing Power was used as a post-processing technique to generate alarms before seizures. These methodologies were compared with a control approach based on the typical machine learning pipeline, considering a group of 37 patients with Temporal Lobe Epilepsy from the EPILEPSIAE database. The best-performing approach (Backwards-Landmark Window) achieved results of 0.75 ± 0.33 for sensitivity and 1.03 ± 1.00 for false positive rate per hour. This new strategy performed above chance for 89% of patients with the surrogate predictor, whereas the control approach only validated 46%.

Seizure prediction based on improved vision transformer model for EEG channel optimization

Epileptic seizures are unpredictable events caused by abnormal discharges of a patient's brain cells. Extensive research has been conducted to develop seizure prediction algorithms based on long-term continuous electroencephalogram (EEG) signals. This paper describes a patient-specific seizure prediction method that can serve as a basis for the design of lightweight, wearable and effective seizure-prediction devices. We aim to achieve two objectives using this method. The first aim is to extract robust feature representations from multichannel EEG signals, and the second aim is to reduce the number of channels used for prediction by selecting an optimal set of channels from multichannel EEG signals while ensuring good prediction performance. We design a seizure-prediction algorithm based on a vision transformer (ViT) model. The algorithm selects channels that play a key role in seizure prediction from 22 channels of EEG signals. First, we perform a time-frequency analysis of processed time-series signals to obtain EEG spectrograms. We then segment the spectrograms of multiple channels into many non-overlapping patches of the same size, which are input into the channel selection layer of the proposed model, named Sel-JPM-ViT, enabling it to select channels. Application of the Sel-JPM-ViT model to the Boston Children's Hospital-Massachusetts Institute of Technology scalp EEG dataset yields results using only three to six channels of EEG signals that are slightly better that the results obtained using 22 channels of EEG signals. Overall, the Sel-JPM-ViT model exhibits an average classification accuracy of 93.65%, an average sensitivity of 94.70% and an average specificity of 92.78%.

Domain adaptation for EEG-based, cross-subject epileptic seizure prediction

The ability to predict the occurrence of an epileptic seizure is a safeguard against patient injury and health complications. However, a major challenge in seizure prediction arises from the significant variability observed in patient data. Common patient-specific approaches, which apply to each patient independently, often perform poorly for other patients due to the data variability. The aim of this study is to propose deep learning models which can handle this variability and generalize across various patients. This study addresses this challenge by introducing a novel cross-subject and multi-subject prediction models. Multiple-subject modeling broadens the scope of patient-specific modeling to account for the data from a dedicated ensemble of patients, thereby providing some useful, though relatively modest, level of generalization. The basic neural network architecture of this model is then adapted to cross-subject prediction, thereby providing a broader, more realistic, context of application. For accrued performance, and generalization ability, cross-subject modeling is enhanced by domain adaptation. Experimental evaluation using the publicly available CHB-MIT and SIENA data datasets shows that our multiple-subject model achieved better performance compared to existing works. However, the cross-subject faces challenges when applied to different patients. Finally, through investigating three domain adaptation methods, the model accuracy has been notably improved by 10.30% and 7.4% for the CHB-MIT and SIENA datasets, respectively.

A ResNet-LSTM hybrid model for predicting epileptic seizures using a pretrained model with supervised contrastive learning

In this paper, we propose a method for predicting epileptic seizures using a pre-trained model utilizing supervised contrastive learning and a hybrid model combining residual networks (ResNet) and long short-term memory (LSTM). The proposed training approach encompasses three key phases: pre-processing, pre-training as a pretext task, and training as a downstream task. In the pre-processing phase, the data is transformed into a spectrogram image using short time Fourier transform (STFT), which extracts both time and frequency information. This step compensates for the inherent complexity and irregularity of electroencephalography (EEG) data, which often hampers effective data analysis. During the pre-training phase, augmented data is generated from the original dataset using techniques such as band-stop filtering and temporal cutout. Subsequently, a ResNet model is pre-trained alongside a supervised contrastive loss model, learning the representation of the spectrogram image. In the training phase, a hybrid model is constructed by combining ResNet, initialized with weight values from the pre-trained model, and LSTM. This hybrid model extracts image features and time information to enhance prediction accuracy. The proposed method's effectiveness is validated using datasets from CHB-MIT and Seoul National University Hospital (SNUH). The method's generalization ability is confirmed through Leave-one-out cross-validation. From the experimental results measuring accuracy, sensitivity, and false positive rate (FPR), CHB-MIT was 91.90%, 89.64%, 0.058 and SNUH was 83.37%, 79.89%, and 0.131. The experimental results demonstrate that the proposed method outperforms the conventional methods.

B2-ViT Net: Broad Vision Transformer Network With Broad Attention for Seizure Prediction

Seizure prediction are necessary for epileptic patients. The global spatial interactions among channels, and long-range temporal dependencies play a crucial role in seizure onset prediction. In addition, it is necessary to search for seizure prediction features in a vast space to learn new generalized feature representations. Many previous deep learning algorithms have achieved some results in automatic seizure prediction. However, most of them do not consider global spatial interactions among channels and long-range temporal dependencies together, and only learn the feature representation in the deep space. To tackle these issues, in this study, an novel bi-level programming seizure prediction model, B2-ViT Net, is proposed for learning the new generalized spatio-temporal long-range correlation features, which can characterize the global interactions among channels in spatial, and long-range dependencies in temporal required for seizure prediction. In addition, the proposed model can comprehensively learn generalized seizure prediction features in a vast space due to its strong deep and broad feature search capabilities. Sufficient experiments are conducted on two public datasets, CHB-MIT and Kaggle datasets. Compared with other existing methods, our proposed model has shown promising results in automatic seizure prediction tasks, and provides a certain degree of interpretability.

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.

Patient-specific warning of epileptic seizure upon shapelets features

Epilepsy is an intractable chronic neurological disease attached to extensive attention. Due to the fact that unpredictable seizure attacks result in serious physical injuries, early warning before seizure occurrence can help patients to get timely treatment and intervention. This paper presents a novel patient-specific method to predict epileptic seizures by learning shapelets of scalp electroencephalogram (EEG) signals recorded from different channels. In the proposed method, EEG signals are preprocessed to raise the Signal to Noise Rate (SNR). Multichannel shapelets space is constructed by the learning-near-to-optimal shapelets method. EEG signals are converted to distance matrices by projecting them on the shapelets' space. Bi-LSTM, SVM, CNN, and an ensemble of them are used to classify the feature set. Based on the prediction results then raise alarms. The proposed methodology is applied to the CHB-MIT scalp EEG dataset of 10 cases. The proposed method achieves a sensitivity of 91.33% and a false prediction rate of 0.16 h-1.

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.

DeepSOZ: A Robust Deep Model for Joint Temporal and Spatial Seizure Onset Localization from Multichannel EEG Data

We propose a robust deep learning framework to simultaneously detect and localize seizure activity from multichannel scalp EEG. Our model, called DeepSOZ, consists of a transformer encoder to generate global and channel-wise encodings. The global branch is combined with an LSTM for temporal seizure detection. In parallel, we employ attention-weighted multi-instance pooling of channel-wise encodings to predict the seizure onset zone. DeepSOZ is trained in a supervised fashion and generates high-resolution predictions on the order of each second (temporal) and EEG channel (spatial). We validate DeepSOZ via bootstrapped nested cross-validation on a large dataset of 120 patients curated from the Temple University Hospital corpus. As compared to baseline approaches, DeepSOZ provides robust overall performance in our multi-task learning setup. We also evaluate the intra-seizure and intra-patient consistency of DeepSOZ as a first step to establishing its trustworthiness for integration into the clinical workflow for epilepsy.

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.

Deep extreme learning machine with knowledge augmentation for EEG seizure signal recognition

Introduction

Intelligent recognition of electroencephalogram (EEG) signals can remarkably improve the accuracy of epileptic seizure prediction, which is essential for epileptic diagnosis. Extreme learning machine (ELM) has been applied to EEG signals recognition, however, the artifacts and noises in EEG signals have a serious effect on recognition efficiency. Deep learning is capable of noise resistance, contributing to removing the noise in raw EEG signals. But traditional deep networks suffer from time-consuming training and slow convergence.

Methods

Therefore, a novel deep learning based ELM (denoted as DELM) motivated by stacking generalization principle is proposed in this paper. Deep extreme learning machine (DELM) is a hierarchical network composed of several independent ELM modules. Augmented EEG knowledge is taken as complementary component, which will then be mapped into next module. This learning process is so simple and fast, meanwhile, it can excavate the implicit knowledge in raw data to a greater extent. Additionally, the proposed method is operated in a single-direction manner, so there is no need to perform parameters fine-tuning, which saves the expense of time.

Results

Extensive experiments are conducted on the public Bonn EEG dataset. The experimental results demonstrate that compared with the commonly-used seizure prediction methods, the proposed DELM wins the best average accuracies in 13 out of the 22 data and the best average F-measure scores in 10 out of the 22 data. And the running time of DELM is more than two times quickly than deep learning methods.

Discussion

Therefore, DELM is superior to traditional and some state-of-the-art machine learning methods. The proposed architecture demonstrates its feasibility and superiority in epileptic EEG signal recognition. The proposed less computationally intensive deep classifier enables faster seizure onset detection, which is showing great potential on the application of real-time EEG signal classification.

An Epileptic Seizure Prediction Method Based on CBAM-3D CNN-LSTM Model

Epilepsy as a common disease of the nervous system, with high incidence, sudden and recurrent characteristics. Therefore, timely prediction of seizures and intervention treatment can significantly reduce the accidental injury of patients and protect the life and health of patients. Epilepsy seizures is the result of temporal and spatial evolution, Existing deep learning methods often ignore its spatial features, in order to make better use of the temporal and spatial characteristics of epileptic EEG signals. We propose a CBAM-3D CNN-LSTM model to predict epilepsy seizures. First, we apply short-time Fourier transform(STFT) to preprocess EEG signals. Secondly, the 3D CNN model was used to extract the features of preictal stage and interictal stage from the preprocessed signals. Thirdly, Bi-LSTM is connected to 3D CNN for classification. Finally CBAM is introduced into the model. Different attention is given to the data channel and space to extract key information, so that the model can accurately extract interictal and pre-ictal features. Our proposed approach achieved an accuracy of 97.95%, a sensitivity of 98.40%, and a false alarm rate of 0.017 h-1 on 11 patients from the public CHB-MIT scalp EEG dataset. Clinical and Translational Impact Statement-Timely prediction of epileptic seizures and intervention treatment can significantly reduce the accidental injury of patients and protect the life and health of patients.

Patient-specific approach using data fusion and adversarial training for epileptic seizure prediction

Epilepsy is the second common neurological disorder after headache, accurate and reliable prediction of seizures is of great clinical value. Most epileptic seizure prediction methods consider only the EEG signal or extract and classify the features of EEG and ECG signals separately, the improvement of prediction performance from multimodal data is not fully considered. In addition, epilepsy data are time-varying, with differences between each episode in a patient, making it difficult for traditional curve-fitting models to achieve high accuracy and reliability. In order to improve the accuracy and reliability of the prediction system, we propose a novel personalized approach based on data fusion and domain adversarial training to predict epileptic seizures using leave-one-out cross-validation, which achieves an average accuracy, sensitivity and specificity of 99.70, 99.76, and 99.61%, respectively, with an average error alarm rate (FAR) of 0.001. Finally, the advantage of this approach is demonstrated by comparison with recent relevant literature. This method will be incorporated into clinical practice to provide personalized reference information for epileptic seizure prediction.

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.

Predicting epileptic seizures based on EEG signals using spatial depth features of a 3D-2D hybrid CNN

Epilepsy is a recurrent chronic brain disease that affects nearly 75 million people around the world. Therefore, the ability to reliably predict epileptic seizures would be instrumental for implementing interventions to reduce brain injury and improve patients' quality of life. In addition to classical machine learning algorithms and feature engineering methods, the use of electroencephalography (EEG) to predict seizures has gradually become a mainstream trend. Here, we propose a patient-specific method to predict epileptic seizures based on EEG data acquired using spatial depth features of a three-dimensional-two-dimensional hybrid convolutional neural network (3D-2D HyCNN) model. This method facilitates the acquisition of abundant and reliable deep features from multi-channel EEG signals. We first developed a reliable data preprocessing method to reconstruct time-series EEG signals into 3D feature images. Then, the 3D-2D HyCNN model was used to extract correlation features between multiple channels of EEG signals, which are automatically exploited by the network to improve seizure prediction. The method achieved accuracy of 98.43% and 93.11%, sensitivity of 98.58% and 90.98%, and specificity of 96.86% and 92.39% on the CHB-MIT Scalp EEG dataset and the American Epilepsy Society Epilepsy Prediction Challenge dataset, respectively. The results revealed that the new algorithm is reliable. Graphical Abstract A new patient-specific epilepsy prediction approach.

EPViz: A flexible and lightweight visualizer to facilitate predictive modeling for multi-channel EEG

Scalp Electroencephalography (EEG) is one of the most popular noninvasive modalities for studying real-time neural phenomena. While traditional EEG studies have focused on identifying group-level statistical effects, the rise of machine learning has prompted a shift in computational neuroscience towards spatio-temporal predictive analyses. We introduce a novel open-source viewer, the EEG Prediction Visualizer (EPViz), to aid researchers in developing, validating, and reporting their predictive modeling outputs. EPViz is a lightweight and standalone software package developed in Python. Beyond viewing and manipulating the EEG data, EPViz allows researchers to load a PyTorch deep learning model, apply it to EEG features, and overlay the output channel-wise or subject-level temporal predictions on top of the original time series. These results can be saved as high-resolution images for use in manuscripts and presentations. EPViz also provides valuable tools for clinician-scientists, including spectrum visualization, computation of basic data statistics, and annotation editing. Finally, we have included a built-in EDF anonymization module to facilitate sharing of clinical data. Taken together, EPViz fills a much needed gap in EEG visualization. Our user-friendly interface and rich collection of features may also help to promote collaboration between engineers and clinicians.

Generalizable epileptic seizures prediction based on deep transfer learning

Predicting seizures before they happen can help prevent them through medication. In this research, first, a total of 22 features were extracted from 5-s segmented EEG signals. Second, tensors were developed as inputs for different deep transfer learning models to find the best model for predicting epileptic seizures. The effect of Pre-ictal state duration was also investigated by selecting four different intervals of 10, 20, 30, and 40 min. Then, nine models were created by combining three ImageNet convolutional networks with three classifiers and were examined for predicting seizures patient-dependently. The Xception convolutional network with a Fully Connected (FC) classifier achieved an average sensitivity of 98.47% and a False Prediction Rate (FPR) of 0.031 h-1 in a 40-min Pre-ictal state for ten patients from the European database. The most promising result of this study was the patient-independent prediction of epileptic seizures; the MobileNet-V2 model with an FC classifier was trained with one patient's data and tested on six other patients, achieving a sensitivity rate of 98.39% and an FPR of 0.029 h-1 for a 40-min Pre-ictal scheme.

Automatic prediction of epileptic seizure using hybrid deep ResNet-LSTM model

Numerous advanced data processing and machine learning techniques for identifying epileptic seizures have been developed in the last two decades. Nonetheless, many of these solutions need massive data sets and intricate computations. Our approach transforms electroencephalogram (EEG) data into the time-frequency domain by utilizing a short-time fourier transform (STFT) and the spectrogram (t-f) images as the input stage of the deep learning model. Using EEG data, we have constructed a hybrid model comprising of a Deep Convolution Network (ResNet50) and a Long Short-Term Memory (LSTM) for predicting epileptic seizures. Spectrogram images are used to train the proposed hybrid model for feature extraction and classification. We analyzed the CHB-MIT scalp EEG dataset. For each preictal period of 5, 15, and 30 minutes, experiments are conducted to evaluate the performance of the proposed model. The experimental results indicate that the proposed model produced the optimum performance with a 5-minute preictal duration. We achieved an average accuracy of 94.5%, the average sensitivity of 93.7%, the f1-score of 0.9376, and the average false positive rate (FPR) of 0.055. Our proposed technique surpassed the random predictor and other current algorithms used for seizure prediction for all patients’ data in the dataset. One can use the effectiveness of our proposed model to help in the early diagnosis of epilepsy and provide early treatment.

Supervised Machine Learning and Deep Learning Techniques for Epileptic Seizure Recognition Using EEG Signals-A Systematic Literature Review

Electroencephalography (EEG) is a complicated, non-stationary signal that requires extensive preprocessing and feature extraction approaches to be accurately analyzed. In recent times, Deep learning (DL) has shown great promise in exploiting the characteristics of EEG signals as it can learn relevant features from raw data autonomously. Although studies involving DL have become more common in the last two years, the topic of whether DL truly delivers advantages over conventional Machine learning (ML) methodologies remains unsettled. This study aims to present a detailed overview of the main challenges in the field of seizure detection, prediction, and classification utilizing EEG data, and the approaches taken to solve them using ML and DL methods. A systematic review was conducted surveying peer-reviewed publications published between 2017 and 16 July 2022 using two scientific databases (Web of Science and Scopus) totaling 6822 references after discarding duplicate publications. Whereas 2262 articles were screened based on the title, abstract, and keywords, only 214 were eligible for full-text assessment. A total of 91 papers have been included in this survey after meeting the eligible inclusion and exclusion criteria. The most significant findings from the review are summarized, and several important concepts involving ML and DL for seizure detection, prediction, and classification are discussed in further depth. This review aims to learn more about the different approaches for identifying different types and stages of epileptic seizures, which may then be employed to enhance the lives of epileptic patients in the future, as well as aid experts in the field.

Epilepsy seizure prediction with few-shot learning method

Epileptic seizures prediction and timely alarms allow the patient to take effective and preventive actions. In this paper, a convolutional neural network (CNN) is proposed to diagnose the preictal period. Our goal is for those epileptic patients in whom seizures occur late and it is very challenging to record the preictal signal for them. In the previous works, generalized methods were inevitably used for this group of patients which were not very accurate. Our approach to solve this problem is to provide a few-shot learning method. This method, having the previous knowledge, is trained with only a small number of samples, learns new tasks and reduces the efforts to collect more data. Evaluation results for three patients from the CHB–MIT database, for a 10-min seizure prediction horizon (SPH) and a 20-min seizure occurrence period (SOP), averaged sensitivity of 95.70% and a false prediction rate (FPR) of 0.057/h and for the 5-min prediction horizon and the 25-min seizure occurrence period averaged sensitivity of 98.52% and a false prediction rate of (FPR) of 0.045/h. The proposed few-shot learning method, based on previous knowledge gained from the generalizable method, is regulated with a few new patient samples for the patient. Our results show that the accuracy obtained in this method is higher than the generalizable methods.

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.

A multi-frame network model for predicting seizure based on sEEG and iEEG data

Introduction

Analysis and prediction of seizures by processing the EEG signals could assist doctors in accurate diagnosis and improve the quality of the patient's life with epilepsy. Nowadays, seizure prediction models based on deep learning have become one of the most popular topics in seizure studies, and many models have been presented. However, the prediction results are strongly related to the various complicated pre-processing strategies of models, and cannot be directly applied to raw data in real-time applications. Moreover, due to the inherent deficiencies in single-frame models and the non-stationary nature of EEG signals, the generalization ability of the existing model frameworks is generally poor.

Methods

Therefore, we proposed an end-to-end seizure prediction model in this paper, where we designed a multi-frame network for automatic feature extraction and classification. Instance and sequence-based frames are proposed in our approach, which can help us simultaneously extract features of different modes for further classification. Moreover, complicated pre-processing steps are not included in our model, and the novel frames can be directly applied to the raw data. It should be noted that the approaches proposed in the paper can be easily used as the general model which has been validated and compared with existing model frames.

Results

The experimental results showed that the multi-frame network proposed in this paper was superior to the existing model frame in accuracy, sensitivity, specificity, F1-score, and AUC in the classification performance of EEG signals.

Discussion

Our results provided a new research idea for this field. Researchers can further integrate the idea of the multi-frame network into the state-of-the-art single-frame seizure prediction models and then achieve better results.

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

Graph theory analysis using electroencephalogram (EEG) signals is currently an advanced technique for seizure prediction. Recent deep learning approaches, which fail to fully explore both the characterizations in EEGs themselves and correlations among different electrodes simultaneously, generally neglect the spatial or temporal dependencies in an epileptic brain and, thus, produce suboptimal seizure prediction performance consequently. To tackle this issue, in this article, a patient-specific EEG seizure predictor is proposed by using a novel spatio-temporal-spectral hierarchical graph convolutional network with an active preictal interval learning scheme (STS-HGCN-AL). Specifically, since the epileptic activities in different brain regions may be of different frequencies, the proposed STS-HGCN-AL framework first infers a hierarchical graph to concurrently characterize an epileptic cortex under different rhythms, whose temporal dependencies and spatial couplings are extracted by a spectral-temporal convolutional neural network and a variant self-gating mechanism, respectively. Critical intrarhythm spatiotemporal properties are then captured and integrated jointly and further mapped to the final recognition results by using a hierarchical graph convolutional network. Particularly, since the preictal transition may be diverse from seconds to hours prior to a seizure onset among different patients, our STS-HGCN-AL scheme estimates an optimal preictal interval patient dependently via a semisupervised active learning strategy, which further enhances the robustness of the proposed patient-specific EEG seizure predictor. Competitive experimental results validate the efficacy of the proposed method in extracting critical preictal biomarkers, indicating its promising abilities in automatic seizure prediction.

A general sample-weighted framework for epileptic seizure prediction

OBJECTIVE

Effective epileptic seizure prediction can make the patients know the onset of the seizure in advance to take timely preventive measures. Many studies based on machine learning methods have been proposed to tackle this problem and achieve significant progress in recent years. However, most studies treat each EEG training sample's contribution to the model as equal, while different samples have different predictive effects on epileptic seizures (e.g., preictal samples from different times). To this end, in this paper, we propose a general sample-weighted framework for patient-specific epileptic seizure prediction.

METHODS

Specifically, we define the mapping from the sample weights of training sets to the performance of the validation sets as the fitness function to be optimized. Then, the genetic algorithm is employed to optimize this fitness function and obtain the optimal sample weights. Finally, we obtain the final model by using the training sets with optimized sample weights.

RESULTS

To evaluate the effectiveness of our framework, we conduct extensive experiments on both traditional machine learning methods and prevalent deep learning methods. Our framework can significantly improve performance based on these methods. Among them, our framework based on Transformer achieves an average sensitivity of 94.6%, an average false prediction rate of 0.06/h, and an average AUC of 0.939 in 12 pediatric patients from the CHB-MIT database with the leave-one-out method, which outperforms the state-of-the-art methods.

CONCLUSION

This study provides new insights into the field of epileptic seizure prediction by considering the discrepancies between EEG samples. Moreover, we develop a general sample-weighted framework, which applies to almost all classical classification methods and can significantly improve performance based on these methods.

An Intelligent Epileptic Prediction System Based on Synchrosqueezed Wavelet Transform and Multi-Level Feature CNN for Smart Healthcare IoT

Epilepsy is a common neurological disease worldwide, characterized by recurrent seizures. There is currently no cure for epilepsy. However, seizures can be controlled by drugs and surgeries in about 70% of epileptic patients. A timely and accurate prediction of seizures can prevent injuries during seizures and improve the patients' quality of life. In this paper, we proposed an intelligent epileptic prediction system based on Synchrosqueezed Wavelet Transform (SWT) and Multi-Level Feature Convolutional Neural Network (MLF-CNN) for smart healthcare IoT network. In this system, we used SWT to map EEG signals to the frequency domain, which was able to measure the energy changes in EEG signals caused by seizures within a well-defined Time-Frequency (TF) plane. MLF-CNN was then applied to extract multi-level features from the processed EEG signals and classify the different seizure segments. The performance of our proposed system was evaluated with the publicly available CHB-MIT dataset and our private ZJU4H dataset. The system achieved an accuracy of 96.99% and 94.25%, a sensitivity of 96.48% and 97.76%, a specificity of 97.46% and 94.07% and a false prediction rate (FPR/h) of 0.031 and 0.049 FPR/h on the CHB-MIT dataset and the ZJU4H dataset, respectively.

Effective Evaluation of Medical Images Using Artificial Intelligence Techniques

This work is implemented for the management of patients with epilepsy, and methods based on electroencephalography (EEG) analysis have been proposed for the timely prediction of its occurrence. The proposed system is used for crisis detection and prediction system; it is useful for both patients and medical staff to know their status easily and more accurately. In the treatment of Parkinson's disease, the affected patients with Parkinson's disease can assess the prognostic risk factors, and the symptoms are evaluated to predict rapid progression in the early stages after diagnosis. The presented seizure prediction system introduces deep learning algorithms into EEG score analysis. This proposed work long short-term memory (LSTM) network model is mainly implemented for the identification and classification of qualitative patterns in the EEG of patients. While compared with other techniques like deep learning models such as convolutional neural networks (CNNs) and traditional machine learning algorithms, the proposed LSTM model plays a significant role in predicting impending crises over 4 different qualifying intervals from 10 minutes to 1.5 hours with very few wrong predictions.