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.

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.

Artificial intelligence in epilepsy - applications and pathways to the clinic

Artificial intelligence (AI) is rapidly transforming health care, and its applications in epilepsy have increased exponentially over the past decade. Integration of AI into epilepsy management promises to revolutionize the diagnosis and treatment of this complex disorder. However, translation of AI into neurology clinical practice has not yet been successful, emphasizing the need to consider progress to date and assess challenges and limitations of AI. In this Review, we provide an overview of AI applications that have been developed in epilepsy using a variety of data modalities: neuroimaging, electroencephalography, electronic health records, medical devices and multimodal data integration. For each, we consider potential applications, including seizure detection and prediction, seizure lateralization, localization of the seizure-onset zone and assessment for surgical or neurostimulation interventions, and review the performance of AI tools developed to date. We also discuss methodological considerations and challenges that must be addressed to successfully integrate AI into clinical practice. Our goal is to provide an overview of the current state of the field and provide guidance for leveraging AI in future to improve management of epilepsy.

Dynamic temporal neural patterns based on multichannel LFPs Identify different brain states during anesthesia in pigeons: comparison of three anesthetics

Anesthetic-induced brain activity study is crucial in avian cognitive-, consciousness-, and sleep-related research. However, the neurobiological mechanisms underlying the generation of brain rhythms and specific connectivity of birds during anesthesia are poorly understood. Although different kinds of anesthetics can be used to induce an anesthesia state, a comparison study of these drugs focusing on the neural pattern evolution during anesthesia is lacking. Here, we recorded local field potentials (LFPs) using a multi-channel micro-electrode array inserted into the nidopallium caudolateral (NCL) of adult pigeons (Columba livia) anesthetized with chloral hydrate, pelltobarbitalum natricum or urethane. Power spectral density (PSD) and functional connectivity analyses were used to measure the dynamic temporal neural patterns in NCL during anesthesia. Neural decoding analysis was adopted to calculate the probability of the pigeon's brain state and the kind of injected anesthetic. In the NCL during anesthesia, we found elevated power activity and functional connectivity at low-frequency bands and depressed power activity and connectivity at high-frequency bands. Decoding results based on the spectral and functional connectivity features indicated that the pigeon's brain states during anesthesia and the injected anesthetics can be effectively decoded. These findings provide an important foundation for future investigations on how different anesthetics induce the generation of specific neural patterns.

A Novel Prognostic Model Using Chaotic CNN with Hybridized Spoofing for Enhancing Diagnostic Accuracy in Epileptic Seizure Prediction

Epileptic seizure detection has undergone progressive advancements since its conception in the 1970s. From proof-of-concept experiments in the latter part of that decade, it has now become a vibrant area of clinical and laboratory research. In an effort to bring this technology closer to practical application in human patients, this study introduces a customized approach to selecting electroencephalogram (EEG) features and electrode positions for seizure prediction. The focus is on identifying precursors that occur within 10 min of the onset of abnormal electrical activity during a seizure. However, there are security concerns related to safeguarding patient EEG recordings against unauthorized access and network-based attacks. Therefore, there is an urgent need for an efficient prediction and classification method for encrypted EEG data. This paper presents an effective system for analyzing and recognizing encrypted EEG information using Arnold transform algorithms, chaotic mapping, and convolutional neural networks (CNNs). In this system, the EEG time series from each channel is converted into a 2D spectrogram image, which is then encrypted using chaotic algorithms. The encrypted data is subsequently processed by CNNs coupled with transfer learning (TL) frameworks. To optimize the fusion parameters of the ensemble learning classifiers, a hybridized spoofing optimization method is developed by combining the characteristics of corvid and gregarious-seeking agents. The evaluation of the model's effectiveness yielded the following results: 98.9 ± 0.3% accuracy, 98.2 ± 0.7% sensitivity, 98.6 ± 0.6% specificity, 98.6 ± 0.6% precision, and an F1 measure of 98.9 ± 0.6%. When compared with other state-of-the-art techniques applied to the same dataset, this novel strategy demonstrated one of the most effective seizure detection systems, as evidenced by these results.

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.

Investigation of global brain dynamics depending on emotion regulation strategies indicated by graph theoretical brain network measures at system level

In the present study, new findings reveal the close association between graph theoretic global brain connectivity measures and cognitive abilities the ability to manage and regulate negative emotions in healthy adults. Functional brain connectivity measures have been estimated from both eyes-opened and eyes-closed resting-state EEG recordings in four groups including individuals who use opposite Emotion Regulation Strategies (ERS) as follow: While 20 individuals who frequently use two opposing strategies, such as rumination and cognitive distraction, are included in 1st group, 20 individuals who don't use these cognitive strategies are included in 2nd group. In 3rd and 4th groups, there are matched individuals who use both Expressive Suppression and Cognitive Reappraisal strategies together frequently and never use them, respectively. EEG measurements and psychometric scores of individuals were both downloaded from a public dataset LEMON. Since it is not sensitive to volume conduction, Directed Transfer Function has been applied to 62-channel recordings to obtain cortical connectivity estimations across the whole cortex. Regarding well defined threshold, connectivity estimations have been transformed into binary numbers for implementation of Brain Connectivity Toolbox. The groups are compared to each other through both statistical logistic regression models and deep learning models driven by frequency band specific network measures referring segregation, integration and modularity of the brain. Overall results show that high classification accuracies of 96.05% (1st vs 2nd) and 89.66% (3rd vs 4th) are obtained in analyzing full-band ( 0.5 - 45 H z ) EEG. In conclusion, negative strategies may upset the balance between segregation and integration. In particular, graphical results show that frequent use of rumination induces the decrease in assortativity referring network resilience. The psychometric scores are found to be highly correlated with brain network measures of global efficiency, local efficiency, clustering coefficient, transitivity and assortativity in even resting-state.

Machine learning seizure prediction: one problematic but accepted practice

Objective.Epilepsy is one of the most common neurological disorders and can have a devastating effect on a person's quality of life. As such, the search for markers which indicate an upcoming seizure is a critically important area of research which would allow either on-demand treatment or early warning for people suffering with these disorders. There is a growing body of work which uses machine learning methods to detect pre-seizure biomarkers from electroencephalography (EEG), however the high prediction rates published do not translate into the clinical setting. Our objective is to investigate a potential reason for this.Approach.We conduct an empirical study of a commonly used data labelling method for EEG seizure prediction which relies on labelling small windows of EEG data in temporal groups then selecting randomly from those windows to validate results. We investigate a confound for this approach for seizure prediction and demonstrate the ease at which it can be inadvertently learned by a machine learning system.Main results.We find that non-seizure signals can create decision surfaces for machine learning approaches which can result in false high prediction accuracy on validation datasets. We prove this by training an artificial neural network to learn fake seizures (fully decoupled from biology) in real EEG.Significance.The significance of our findings is that many existing works may be reporting results based on this confound and that future work should adhere to stricter requirements in mitigating this confound. The problematic, but commonly accepted approach in the literature for seizure prediction labelling is potentially preventing real advances in developing solutions for these sufferers. By adhering to the guidelines in this paper future work in machine learning seizure prediction is more likely to be clinically relevant.

Epileptic Seizure Prediction Based on Hybrid Seek Optimization Tuned Ensemble Classifier Using EEG Signals

Visual analysis of an electroencephalogram (EEG) by medical professionals is highly time-consuming and the information is difficult to process. To overcome these limitations, several automated seizure detection strategies have been introduced by combining signal processing and machine learning. This paper proposes a hybrid optimization-controlled ensemble classifier comprising the AdaBoost classifier, random forest (RF) classifier, and the decision tree (DT) classifier for the automatic analysis of an EEG signal dataset to predict an epileptic seizure. The EEG signal is pre-processed initially to make it suitable for feature selection. The feature selection process receives the alpha, beta, delta, theta, and gamma wave data from the EEG, where the significant features, such as statistical features, wavelet features, and entropy-based features, are extracted by the proposed hybrid seek optimization algorithm. These extracted features are fed forward to the proposed ensemble classifier that produces the predicted output. By the combination of corvid and gregarious search agent characteristics, the proposed hybrid seek optimization technique has been developed, and is used to evaluate the fusion parameters of the ensemble classifier. The suggested technique's accuracy, sensitivity, and specificity are determined to be 96.6120%, 94.6736%, and 91.3684%, respectively, for the CHB-MIT database. This demonstrates the effectiveness of the suggested technique for early seizure prediction. The accuracy, sensitivity, and specificity of the proposed technique are 95.3090%, 93.1766%, and 90.0654%, respectively, for the Siena Scalp database, again demonstrating its efficacy in the early seizure prediction process.

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.

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.

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.

Characteristics of EEG Microstate Sequences During Propofol-Induced Alterations of Brain Consciousness States

Monitoring the consciousness states of patients and ensuring the appropriate depth of anesthesia (DOA) is critical for the safe implementation of surgery. In this study, a high-density electroencephalogram (EEG) combined with blood drug concentration and behavioral response indicators was used to monitor propofol-induced sedation and evaluate the alterations in consciousness states. Microstate analysis, which can reflect the semi-stable state of the sub-second activation of the brain functional network, can be used to assess the brain's consciousness states. In this research, the EEG microstate sequences were constructed to compare the characteristics of corresponding sequences. Compared with the baseline (BS) state, the microstate sequences in the moderate sedation (MD) state exhibited higher complexity indexes of the multiscale sample entropy. With respect to the transition probability (TP) of microstates, most microstates tended to be converted into microstate C in the BS state. In contrast, they tended to be converted into microstate F in the MD state. The significant difference between the expected TP and observed TP could lead to the conclusion that hidden layers were present when there were changes in the consciousness states. According to the hidden Markov model, the accuracy of distinguishing the BS and MD states was 80.16%. The characteristics of microstate sequence revealed the variations in the brain states caused by alterations in consciousness states during anesthesia from a new perspective and presented a new idea for monitoring the DOA.

Pediatric Seizure Prediction in Scalp EEG Using a Multi-Scale Neural Network With Dilated Convolutions

Objective: Epileptic seizure prediction based on scalp electroencephalogram (EEG) is of great significance for improving the quality of life of patients with epilepsy. In recent years, a number of studies based on deep learning methods have been proposed to address this issue and achieve excellent performance. However, most studies on epileptic seizure prediction by EEG fail to take full advantage of temporal-spatial multi-scale features of EEG signals, while EEG signals carry information in multiple temporal and spatial scales. To this end, in this study, we proposed an end-to-end framework by using a temporal-spatial multi-scale convolutional neural network with dilated convolutions for patient-specific seizure prediction. Methods: Specifically, the model divides the EEG processing pipeline into two stages: the temporal multi-scale stage and the spatial multi-scale stage. In each stage, we firstly extract the multi-scale features along the corresponding dimension. A dilated convolution block is then conducted on these features to expand our model's receptive fields further and systematically aggregate global information. Furthermore, we adopt a feature-weighted fusion strategy based on an attention mechanism to achieve better feature fusion and eliminate redundancy in the dilated convolution block. Results: The proposed model obtains an average sensitivity of 93.3%, an average false prediction rate of 0.007 per hour, and an average proportion of time-in-warning of 6.3% testing in 16 patients from the CHB-MIT dataset with the leave-one-out method. Conclusion: Our model achieves superior performance in comparison to state-of-the-art methods, providing a promising solution for EEG-based seizure prediction.

Semisupervised Seizure Prediction in Scalp EEG Using Consistency Regularization

Early prediction of epilepsy seizures can warn the patients to take precautions and improve their lives significantly. In recent years, deep learning has become increasingly predominant in seizure prediction. However, existing deep learning-based approaches in this field require a great deal of labeled data to guarantee performance. At the same time, labeling EEG signals does require the expertise of an experienced pathologist and is incredibly time-consuming. To address this issue, we propose a novel Consistency-based Semisupervised Seizure Prediction Model (CSSPM), where only a fraction of training data is labeled. Our method is based on the principle of consistency regularization, which underlines that a robust model should maintain consistent results for the same input under extra perturbations. Specifically, by using stochastic augmentation and dropout, we consider the entire neural network as a stochastic model and apply a consistency constraint to penalize the difference between the current prediction and previous predictions. In this way, unlabeled data could be fully utilized to improve the decision boundary and enhance prediction performance. Compared with existing studies requiring all training data to be labeled, the proposed method only needs a small portion of data to be labeled while still achieving satisfactory results. Our method provides a promising solution to alleviate the labeling cost for real-world applications.

Automatic Detection of High-Frequency Oscillations Based on an End-to-End Bi-Branch Neural Network and Clinical Cross-Validation

Accurate identification of high-frequency oscillation (HFO) is an important prerequisite for precise localization of epileptic foci and good prognosis of drug-refractory epilepsy. Exploring a high-performance automatic detection method for HFOs can effectively help clinicians reduce the error rate and reduce manpower. Due to the limited analysis perspective and simple model design, it is difficult to meet the requirements of clinical application by the existing methods. Therefore, an end-to-end bi-branch fusion model is proposed to automatically detect HFOs. With the filtered band-pass signal (signal branch) and time-frequency image (TFpic branch) as the input of the model, two backbone networks for deep feature extraction are established, respectively. Specifically, a hybrid model based on ResNet1d and long short-term memory (LSTM) is designed for signal branch, which can focus on both the features in time and space dimension, while a ResNet2d with a Convolutional Block Attention Module (CBAM) is constructed for TFpic branch, by which more attention is paid to useful information of TF images. Then the outputs of two branches are fused to realize end-to-end automatic identification of HFOs. Our method is verified on 5 patients with intractable epilepsy. In intravalidation, the proposed method obtained high sensitivity of 94.62%, specificity of 92.7%, and F1-score of 93.33%, and in cross-validation, our method achieved high sensitivity of 92.00%, specificity of 88.26%, and F1-score of 89.11% on average. The results show that the proposed method outperforms the existing detection paradigms of either single signal or single time-frequency diagram strategy. In addition, the average kappa coefficient of visual analysis and automatic detection results is 0.795. The method shows strong generalization ability and high degree of consistency with the gold standard meanwhile. Therefore, it has great potential to be a clinical assistant tool.

Effect of BCI-Controlled Pedaling Training System With Multiple Modalities of Feedback on Motor and Cognitive Function Rehabilitation of Early Subacute Stroke Patients

Brain-computer interfaces (BCIs) are currently integrated into traditional rehabilitation interventions after stroke. Although BCIs bring many benefits to the rehabilitation process, their effects are limited since many patients cannot concentrate during training. Despite this outcome post-stroke motor-attention dual-task training using BCIs has remained mostly unexplored. This study was a randomized placebo-controlled blinded-endpoint clinical trial to investigate the effects of a BCI-controlled pedaling training system (BCI-PT) on the motor and cognitive function of stroke patients during rehabilitation. A total of 30 early subacute ischemic stroke patients with hemiplegia and cognitive impairment were randomly assigned to the BCI-PT or traditional pedaling training. We used single-channel Fp1 to collect electroencephalography data and analyze the attention index. The BCI-PT system timely provided visual, auditory, and somatosensory feedback to enhance the patient's participation to pedaling based on the real-time attention index. After 24 training sessions, the attention index of the experimental group was significantly higher than that of the control group. The lower limbs motor function (FMA-L) increased by an average of 4.5 points in the BCI-PT group and 2.1 points in the control group (P = 0.022) after treatments. The difference was still significant after adjusting for the baseline indicators ( β = 2.41 , 95%CI: 0.48-4.34, P = 0.024). We found that BCI-PT significantly improved the patient's lower limb motor function by increasing the patient's participation. (clinicaltrials.gov: NCT04612426).

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.

A Novel Method Based on Combination of Independent Component Analysis and Ensemble Empirical Mode Decomposition for Removing Electrooculogram Artifacts From Multichannel Electroencephalogram Signals

Electrooculogram (EOG) is one of common artifacts in recorded electroencephalogram (EEG) signals. Many existing methods including independent component analysis (ICA) and wavelet transform were applied to eliminate EOG artifacts but ignored the possible impact of the nature of EEG signal. Therefore, the removal of EOG artifacts still faces a major challenge in EEG research. In this paper, the ensemble empirical mode decomposition (EEMD) and ICA algorithms were combined to propose a novel EEMD-based ICA method (EICA) for removing EOG artifacts from multichannel EEG signals. First, the ICA method was used to decompose original EEG signals into multiple independent components (ICs), and the EOG-related ICs were automatically identified through the kurtosis method. Then, by performing the EEMD algorithm on EOG-related ICs, the intrinsic mode functions (IMFs) linked to EOG were discriminated and eliminated. Finally, artifact-free IMFs were projected to obtain the ICs without EOG artifacts, and the clean EEG signals were ultimately reconstructed by the inversion of ICA. Both EOGs correction from simulated EEG signals and real EEG data were studied, which verified that the proposed method could achieve an improved performance in EOG artifacts rejection. By comparing with other existing approaches, the EICA obtained the optimal performance with the highest increase in signal-to-noise ratio and decrease in root mean square error and correlation coefficient after EOG artifacts removal, which demonstrated that the proposed method could more effectively eliminate blink artifacts from multichannel EEG signals with less error influence. This study provided a novel promising method to eliminate EOG artifacts with high performance, which is of great importance for EEG signals processing and analysis.

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

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

HFO Detection in Epilepsy: A Stacked Denoising Autoencoder and Sample Weight Adjusting Factors-Based Method

High-frequency oscillations (HFOs) recorded by the intracranial electroencephalography (iEEG) are the promising biomarkers of epileptogenic zones. Accurate detection of HFOs is the key to pre-operative assessment for epilepsy. Due to the subjective bias caused by manual features and the class imbalance between HFOs and false HFOs, it is difficult to obtain satisfactory detection performance by the existing methods. To solve these problems, we put forward a novel method to accurately detect HFOs based on the stacked denoising autoencoder (SDAE) and the ensemble classifier with sample weight adjusting factors. First, the adjustable threshold of Hilbert envelopes is proposed to isolate the events of interest (EoIs) from background activities. Then, the SDAE network is utilized to automatically extract features of EoIs in the time-frequency domain. Finally, the AdaBoost-based support vector machine ensemble classifier with sample weight adjusting factors is devised to separate HFOs from EoIs by using the extracted features. These adjusting factors are used to solve the class imbalance problem by adjusting sample weights when learning the base classifiers. Our HFO detection method is evaluated by using clinical iEEG data recorded from 20 patients with medically refractory epilepsy. The experimental results show that our detection method outperforms some existing methods in terms of sensitivity and false discovery rate. In addition, the HFOs detected by our method are effective for localizing seizure onset zones.

A channel independent generalized seizure detection method for pediatric epileptic seizures

BACKGROUND AND OBJECTIVE

Epilepsy the disorder of the central nervous system has its worldwide presence in roughly 50 million people as estimated by the World Health Organization. Electroencephalogram (EEG) is one of the most common and non-invasive ways of analyzing and studying the subtle changes in neuronal activity of the brain during an epileptic seizure attack. These changes can be analyzed for developing an automated system that would assert the chances of an impending seizure. As changeable nature of seizure affects the patients from having a normal life, hence progress in developing new methods will improve the quality of life and also provide assistance in the medical sector. Objective of the proposed method is to avoid EEG channel selection and use all input EEG channel features to design a generalized epileptic seizure detection framework.

METHOD

In this work, a long short-term memory network has been proposed that is not complex and has the capability of effectively detecting epileptic seizures from both non-invasive and invasive electroencephalogram recordings. The proposed framework is simple and effective and designed in such capacity that raw electroencephalogram signals can be used to detect seizures. Also, a generalized approach has been followed that is channel independent such that EEG signals belonging to any hemisphere of the brain can be detected effectively by the proposed architecture.

RESULTS

The automated seizure detection system achieved high seizure detection sensitivity of 99.9%, and a low false-positive rate of 0.003 per hour for the Children's Hospital Boston-Massachusetts Institute of Technology dataset. While for the Sleep-Wake-Epilepsy-Center of the University Department of Neurology at the Inselspital Bern dataset, the sensitivity is 99.4% and false-positive rate of 0.006 per hour. Convergence analysis of the proposed model provides a significant amount of reliability and correctness in the efficient detection of epileptic seizures.

CONCLUSION

Assessment of the proposed framework on non-invasive as well as invasive EEG signals showed that the framework worked well for different type of EEG recordings as different metrics gave satisfactory results. As the framework is simple and did not require any additional parameter optimization techniques, it reduced the processing overheads without affecting the accuracy. Hence, it can be used as an efficient method for monitoring epileptic seizures.

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

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

Improvement in EEG Source Imaging Accuracy by Means of Wavelet Packet Transform and Subspace Component Selection

The electroencephalograph (EEG) source imaging (ESI) method is a non-invasive method that provides high temporal resolution imaging of brain electrical activity on the cortex. However, because the accuracy of EEG source imaging is often affected by unwanted signals such as noise or other source-irrelevant signals, the results of ESI are often incongruous with the real sources of brain activities. This study presents a novel ESI method (WPESI) that is based on wavelet packet transform (WPT) and subspace component selection to image the cerebral activities of EEG signals on the cortex. First, the original EEG signals are decomposed into several subspace components by WPT. Second, the subspaces associated with brain sources are selected and the relevant signals are reconstructed by WPT. Finally, the current density distribution in the cerebral cortex is obtained by establishing a boundary element model (BEM) from head MRI and applying the appropriate inverse calculation. In this study, the localization results obtained by this proposed approach were better than those of the original sLORETA approach (OESI) in the computer simulations and visual evoked potential (VEP) experiments. For epilepsy patients, the activity sources estimated by this proposed algorithm conformed to the seizure onset zones. The WPESI approach is easy to implement achieved favorable accuracy in terms of EEG source imaging. This demonstrates the potential for use of the WPESI algorithm to localize epileptogenic foci from scalp EEG signals.