Predicting epileptic seizures from scalp EEG based on attractor state analysis

M-NIG: mobile network information gain for EEG-based epileptic seizure prediction

Epilepsy is one of the most common cerebral diseases, the development of which can be divided into four states: interictal state, preictal state, ictal state and postictal state. Hunting for critical states is of great significance to predict seizures. This study seeks to establish a general-purpose method for epileptic seizure prediction by constructing individual-specific correlation networks between multi-channel EEG signals. In this paper, we present the mobile network information gain (M-NIG) method by transforming floating time series datasets into stable network information gain, which reduces the impact of data noise, thereby improving the robustness and effectiveness of the algorithm. The method not only efficiently predicts seizures but also detects their DNB channels. The proposed method attains an average of 97.40% accuracy, 94.32% sensitivity, 97.48% specificity, and FPR = 0.024/h on 22 patients from the public CHB-MIT scalp EEG database, which outperforms most state-of-the-art articles. Additionally, it achieves an average of 95.70% accuracy, 100.00% sensitivity, 95.56% specificity, and FPR = 0.044/h on a dataset collected at Taian Maternity and Child Health Hospital, which outperforms most state-of-the-art articles in terms of sensitivity, accuracy, and FPR. Our experiments show that the parameters of sliding window and the number of nearest neighbor of k-nearest neighbor (KNN) are important factors affecting prediction performance.

Pathogenesis, diagnosis, and treatment of epilepsy: electromagnetic stimulation-mediated neuromodulation therapy and new technologies

Epilepsy is a severe, relapsing, and multifactorial neurological disorder. Studies regarding the accurate diagnosis, prognosis, and in-depth pathogenesis are crucial for the precise and effective treatment of epilepsy. The pathogenesis of epilepsy is complex and involves alterations in variables such as gene expression, protein expression, ion channel activity, energy metabolites, and gut microbiota composition. Satisfactory results are lacking for conventional treatments for epilepsy. Surgical resection of lesions, drug therapy, and non-drug interventions are mainly used in clinical practice to treat pain associated with epilepsy. Non-pharmacological treatments, such as a ketogenic diet, gene therapy for nerve regeneration, and neural regulation, are currently areas of research focus. This review provides a comprehensive overview of the pathogenesis, diagnostic methods, and treatments of epilepsy. It also elaborates on the theoretical basis, treatment modes, and effects of invasive nerve stimulation in neurotherapy, including percutaneous vagus nerve stimulation, deep brain electrical stimulation, repetitive nerve electrical stimulation, in addition to non-invasive transcranial magnetic stimulation and transcranial direct current stimulation. Numerous studies have shown that electromagnetic stimulation-mediated neuromodulation therapy can markedly improve neurological function and reduce the frequency of epileptic seizures. Additionally, many new technologies for the diagnosis and treatment of epilepsy are being explored. However, current research is mainly focused on analyzing patients' clinical manifestations and exploring relevant diagnostic and treatment methods to study the pathogenesis at a molecular level, which has led to a lack of consensus regarding the mechanisms related to the disease.

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.

Heart rate variability as a preictal marker for determining the laterality of seizure onset zone in frontal lobe epilepsy

Determining the laterality of the seizure onset zone is challenging in frontal lobe epilepsy (FLE) due to the rapid propagation of epileptic discharges to the contralateral hemisphere. There is hemispheric lateralization of autonomic control, and heart rate is modulated by interactions between the sympathetic and parasympathetic nervous systems. Based on this notion, the laterality of seizure foci in FLE might be determined using heart rate variability (HRV) parameters. We explored preictal markers for differentiating the laterality of seizure foci in FLE using HRV parameters. Twelve patients with FLE (6 right FLE and 6 left FLE) were included in the analyzes. A total of 551 (460 left FLE and 91 right FLE) 1-min epoch electrocardiography data were used for HRV analysis. We found that most HRV parameters differed between the left and right FLE groups. Among the machine learning algorithms applied in this study, the light gradient boosting machine was the most accurate, with an AUC value of 0.983 and a classification accuracy of 0.961. Our findings suggest that HRV parameter-based laterality determination models can be convenient and effective tools in clinical settings. Considering that heart rate can be easily measured in real time with a wearable device, our proposed method can be applied to a closed-loop device as a real-time monitoring tool for determining the side of stimulation.

Epileptic seizure prediction based on features extracted from lagged Poincaré plots

OBJECTIVE

The present work proposes a new epileptic seizure prediction method based on lagged Poincaré plot analysis of heart rate (HR).

METHODS

In this article, the Poincaré plots with six different lags (1-6) were constructed for four episodes of heart rate variability (HRV) before the seizures. Moreover, two features were extracted based on lagged Poincare plots, which include the angle between the time series and the ellipse density fitted to the RR points.

RESULTS

The proposed method was applied to 16 epileptic patients with 170 seizures. The results included sensitivity of 80.42% for the angle feature and 75.19% for the density feature. The false-positive rate was 0.15/Hr, which indicates that the system has superiority over the random predictor.

CONCLUSION

The proposed HRV-based epileptic seizure prediction method has the potential to be used in daily life because HR can be measured easily by using a wearable sensor.

Response to photic stimulation as a measure of cortical excitability in epilepsy patients

Studying states and state transitions in the brain is challenging due to nonlinear, complex dynamics. In this research, we analyze the brain's response to non-invasive perturbations. Perturbation techniques offer a powerful method for studying complex dynamics, though their translation to human brain data is under-explored. This method involves applying small inputs, in this case via photic stimulation, to a system and measuring its response. Sensitivity to perturbations can forewarn a state transition. Therefore, biomarkers of the brain's perturbation response or "cortical excitability" could be used to indicate seizure transitions. However, perturbing the brain often involves invasive intracranial surgeries or expensive equipment such as transcranial magnetic stimulation (TMS) which is only accessible to a minority of patient groups, or animal model studies. Photic stimulation is a widely used diagnostic technique in epilepsy that can be used as a non-invasive perturbation paradigm to probe brain dynamics during routine electroencephalography (EEG) studies in humans. This involves changing the frequency of strobing light, sometimes triggering a photo-paroxysmal response (PPR), which is an electrographic event that can be studied as a state transition to a seizure state. We investigate alterations in the response to these perturbations in patients with genetic generalized epilepsy (GGE), with (n = 10) and without (n = 10) PPR, and patients with psychogenic non-epileptic seizures (PNES; n = 10), compared to resting controls (n = 10). Metrics of EEG time-series data were evaluated as biomarkers of the perturbation response including variance, autocorrelation, and phase-based synchrony measures. We observed considerable differences in all group biomarker distributions during stimulation compared to controls. In particular, variance and autocorrelation demonstrated greater changes in epochs close to PPR transitions compared to earlier stimulation epochs. Comparison of PPR and spontaneous seizure morphology found them indistinguishable, suggesting PPR is a valid proxy for seizure dynamics. Also, as expected, posterior channels demonstrated the greatest change in synchrony measures, possibly reflecting underlying PPR pathophysiologic mechanisms. We clearly demonstrate observable changes at a group level in cortical excitability in epilepsy patients as a response to perturbation in EEG data. Our work re-frames photic stimulation as a non-invasive perturbation paradigm capable of inducing measurable changes to brain dynamics.

Identification of epileptic networks with graph convolutional network incorporating oscillatory activities and evoked synaptic responses

Stereoelectroencephalography (SEEG) offers unique neural data from in-depth brain structures with fine temporal resolutions to better investigate the origin of epileptic brain activities. Although oscillatory patterns from different frequency bands and functional connectivity computed from the SEEG datasets are employed to study the epileptic zones, direct electrical stimulation-evoked electrophysiological recordings of synaptic responses, namely cortical-cortical evoked potentials (CCEPs), from the same SEEG electrodes are not explored for the localization of epileptic zones. Here we proposed a two-stream model with unsupervised learning and graph convolutional network tailored to the SEEG and CCEP datasets in individual patients to perform localization of epileptic zones. We compared our localization results with the clinically marked electrode sites determined for surgical resections. Our model had good classification capability when compared to other state-of-the-art methods. Furthermore, based on our prediction results we performed group-level brain-area mapping analysis for temporal, frontal and parietal epilepsy patients and found that epileptic and non-epileptic brain networks were distinct in patients with different types of focal epilepsy. Our unsupervised data-driven model provides personalized localization analysis for the epileptic zones. The epileptic and non-epileptic brain areas disclosed by the prediction model provide novel insights into the network-level pathological characteristics of epilepsy.

Automated diagnosis of EEG abnormalities with different classification techniques

Automatic seizure detection and prediction using clinical Electroencephalograms (EEGs) are challenging tasks due to factors such as low Signal-to-Noise Ratios (SNRs), high variance in epileptic seizures among patients, and limited clinical data constraints. To overcome these challenges, this paper presents two approaches for EEG signal classification. One of these approaches depends on Machine Learning (ML) tools. The used features are different types of entropy, higher-order statistics, and sub-band energies in the Hilbert Marginal Spectrum (HMS) domain. The classification is performed using Support Vector Machine (SVM), Logistic Regression (LR), and K-Nearest Neighbor (KNN) classifiers. Both seizure detection and prediction scenarios are considered. The second approach depends on spectrograms of EEG signal segments and a Convolutional Neural Network (CNN)-based residual learning model. We use 10000 spectrogram images for each class. In this approach, it is possible to perform both seizure detection and prediction in addition to a 3-state classification scenario. Both approaches are evaluated on the Children's Hospital Boston and the Massachusetts Institute of Technology (CHB-MIT) dataset, which contains 24 EEG recordings for 6 males and 18 females. The results obtained for the HMS-based model showed an accuracy of 100%. The CNN-based model achieved accuracies of 97.66%, 95.59%, and 94.51% for Seizure (S) versus Pre-Seizure (PS), Non-Seizure (NS) versus S, and NS versus S versus PS classes, respectively. These results demonstrate that the proposed approaches can be effectively used for seizure detection and prediction. They outperform the state-of-the-art techniques for automatic seizure detection and prediction. Block diagram of proposed epileptic seizure detection method using HMS with different classifiers.

An end-to-end seizure prediction approach using long short-term memory network

There are increasing epilepsy patients suffering from the pain of seizure onsets, and effective prediction of seizures could improve their quality of life. To obtain high sensitivity for epileptic seizure prediction, current studies generally need complex feature extraction operations, which heavily depends on the artificial experience (or domain knowledge) and is highly subjective. To address these issues, in this paper we propose an end-to-end epileptic seizure prediction approach based on the long short-term memory network (LSTM). In the new method, only the gamma band of raw electroencephalography (EEG) signals is extracted as network input directly for seizure prediction, thus avoiding subjective and expensive feature design process. Despite its simplicity, the proposed method achieves the mean sensitivity of 91.76% and false prediction rate (FPR) of 0.29/h on Children's Hospital Boston-MIT (CHB-MIT) scalp EEG Database, respectively, when identifying the preictal stage from the EEG signals. Furthermore, different from traditional methods that only consider the classification of preictal and interictal EEG, we introduce the postictal stage as an extra class in the proposed method. As a result, the performance of seizure prediction is further improved, obtaining a higher sensitivity of 92.17% and a low FPR of 0.27/h. The mean warning time is 44.46 min, which suggests that sufficient time is reserved for patients to take intervention measures by this prediction method.

Epileptic prediction using spatiotemporal information combined with optimal features strategy on EEG

Objective

Epilepsy is the second most common brain neurological disease after stroke, which has the characteristics of sudden and recurrence. Seizure prediction is seriously important for improving the quality of patients' lives.

Methods

From the perspective of multiple dimensions including time-frequency, entropy and brain network, this paper proposed a novel approach by constructing the optimal spatiotemporal feature set to predict seizures. Based on strong independence and large information capabilities, the two-dimensional feature screening algorithm is performed to eliminate unnecessary redundant features. In order to verify the effectiveness of the optimal feature set, support vector machine (SVM) was used to classify the preictal and interictal states on both the Kaggle intracranial EEG and CHB-MIT scalp EEG dataset.

Results

This model achieved an average accuracy of 98.01%, AUC of 0.96, F-Score of 98.3% and FPR of 0.0383/h on the Kaggle dataset; On the CHB-MIT dataset, the average accuracy, AUC, F-score and FPR were 95.93%, 0.92, 94.97% and 0.0473/h, respectively. Further ablation experiments have confirmed that the temporal and spatial features fusion has better performance than the individual temporal or spatial features.

Conclusion

Compared to the state-of-the-art methods, our approach outperforms most of these existing techniques. The results show that our approach can effectively extract the spatiotemporal information of epileptic EEG signals to predict epileptic seizures with high performance.

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.

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.

Epileptic seizure prediction in intracranial EEG using critical nucleus based on phase transition

BACKGROUND AND OBJECTIVE

Epilepsy is the second most prevalent neurological disorder of brain activity, affecting about seventy million people, or nearly 1% of the world population. Epileptic seizures prediction is extremely important for improving the epileptic patients' life. This paper proposed a novel method to predict seizures by detecting the critical transition of brain activities with intracranial EEG (iEEG) signals.

METHODS

This article used three key measures of fluctuation, correlation and percolation to quantify pre-ictal states of epilepsy. Based on these measures, a ritical nucleus of iEEG signals was constructed and a composite index was introduced to detect the likelihood of impending seizures. In addition, we analyzed the dynamical mechanism of seizures at the tipping point from the perspective of spatial diffusion and temporal fluctuation.

RESULTS

The empirical results supported that the seizures are self-initiated via a critical transition in pre-ictal state and showed that the proposed model can achieve a good prediction performance. The average accuracy, sensitivity, specificity and false-positive rate (FPR) attain 87.96%, 82.93%, 89.33% and 0.11/h respectively. The results also suggest that the temporal and spatial factors have strong synergistic effect on triggering seizures. For those seizures consistent with critical transition, the predictive performance was greatly improved with sensitivity up to 96.88%.

CONCLUSIONS

This article proposed a critical nucleus model combined with spatial and temporal features of iEEG signals capable of seizure prediction. The proposed model brings insight from phase transition into epileptic iEEG signals analysis and quantifies the transition of the state to predict epileptic seizures with high accuracy.

Classification of EEG Signals for Prediction of Epileptic Seizures

Epilepsy is a common brain disorder that causes patients to face multiple seizures in a single day. Around 65 million people are affected by epilepsy worldwide. Patients with focal epilepsy can be treated with surgery, whereas generalized epileptic seizures can be managed with medications. It has been noted that in more than 30% of cases, these medications fail to control epileptic seizures, resulting in accidents and limiting the patient’s life. Predicting epileptic seizures in such patients prior to the commencement of an oncoming seizure is critical so that the seizure can be treated with preventive medicines before it occurs. Electroencephalogram (EEG) signals of patients recorded to observe brain electrical activity during a seizure can be quite helpful in predicting seizures. Researchers have proposed methods that use machine and/or deep learning techniques to predict epileptic seizures using scalp EEG signals; however, prediction of seizures with increased accuracy is still a challenge. Therefore, we propose a three-step approach. It includes preprocessing of scalp EEG signals with PREP pipeline, which is a more sophisticated alternative to basic notch filtering. This method uses a regression-based technique to further enhance the SNR, with a combination of handcrafted, i.e., statistical features such as temporal mean, variance, and skewness, and automated features using CNN, followed by classification of interictal state and preictal state segments using LSTM to predict seizures. We train and validate our proposed technique on the CHB-MIT scalp EEG dataset and achieve accuracy of 94%, sensitivity of 93.8%, and 91.2% specificity. The proposed technique achieves better sensitivity and specificity than existing methods.

Epileptic electroencephalography classification using Embedded Dynamic Mode Decomposition

OBJECTIVE

Seizure prediction devices for drug-resistant epileptic patients could lead to improved quality of life and new treatment options, but current approaches to classification of electroencephalography (EEG) segments for early identification of the pre-seizure state typically require many features and complex classifiers. We therefore propose a novel spatio-temporal EEG feature set that significantly aids in separation and easy classification of the interictal and preictal states.

APPROACH

We derive key spectral features from the Embedded Dynamic Mode Decomposition (EmDMD) of the brain state system. This method linearizes the complex spatio-temporal dynamics of the system, describing the dynamics in terms of a spectral basis of modes and eigenvalues. The relative subband spectral power and mean phase locking values of these modes prove to be good indicators of the preictal state that precedes seizure onset.

MAIN RESULTS

We analyze the linear separability and classification of preictal and interictal states based on our proposed features using seizure data extracted from the CHB-MIT scalp EEG and Kaggle American Epilepsy Society Seizure Prediction Challenge intracranial EEG databases. With a light-weight support vector machine or random forest classifier trained on these features, we classify the preictal state with a sensitivity of up to 92% and specificity of up to 89%.

SIGNIFICANCE

The EmDMD-derived features separate the preictal and interictal states, improving classification accuracy and motivating further work to incorporate them into seizure prediction algorithms.

An effective convolutional neural network-based stacked long short-term memory approach for automated Alzheimer’s disease prediction

In today’s world, Alzheimer’s Disease (AD) is one of the prevalent neurological diseases where early disease prediction can significantly enhance the compatibility of patient treatment. Nevertheless, accurate diagnosis and optimal feature selection play a vital challenge in AD detection. Most of the existing diagnosis systems failed to attain superior prediction accuracy and precision rate. In order to mitigate these constraints, a new efficient Convolutional Neural Network-based Stacked Long Short-Term Memory (CNN-SLSTM) methodology has been proposed in this paper. The key objective of the proposed model is to examine the brain’s condition and evaluate the changes that occur throughout the interracial period. The proposed model includes multi-feature learning and categorization in which the raw Electroencephalography (EEG) data will be passed via the feature extractor to decrease the computing complexity and execution time. Afterward, the SLSTM network is constructed with completely linked layer and activation layers to record the temporal relationship between features and the next stage of AD. The proposed CNN-SLSTM model can be trained using real-time EEG sensor data. The performance results clearly apparent that the proposed model can efficiently predict the AD with superior accuracy of 98.67% and precision of 98.86% when compared with existing state-of-the-art techniques.

Epileptic seizure prediction using spectral width of the covariance matrix

Epilepsy is a common neurological disorder in which patients suffer from sudden and unpredictable seizures. Seizures are caused by excessive and abnormal neuronal activity. Different methods have been employed to investigate electroencephalogram (EEG) data in patients with epilepsy. This paper introduces a simple yet accurate array-based method to study and predict seizures. We use the CHB-MIT dataset (all 24 cases), which includes scalp EEG recordings. The proposed method is based on the random matrix theory. After applying wavelet decomposition to denoise the data, we analyze the spatial coherence of the epileptic recordings by looking at the width of the covariance matrix eigenvalue distribution at different time and frequency bins. We train patient-specific support vector machine (SVM) classifiers to distinguish between interictal and preictal data with high performance and a false prediction rate as low as 0.09/h. The proposed technique achieves an average accuracy, specificity, sensitivity, and area under the curve (AUC) of 99.05%, 93.56%, 99.09%, and 0.99, respectively. Our proposed method outperforms state-of-the-art works in terms of sensitivity while maintaining a low false prediction rate. Also, in contrast to neural networks, which may achieve high performance, this work provides high sensitivity without compromising interpretability.

Detection of preictal state in epileptic seizures using ensemble classifier

OBJECTIVE

Epilepsy affected patient experiences more than one frequency seizures which can not be treated with medication or surgical procedures in 30% of the cases. Therefore, an early prediction of these seizures is inevitable for these cases to control them with therapeutic interventions.

METHODS

In recent years, researchers have proposed multiple deep learning based methods for detection of preictal state in electroencephalogram (EEG) signals, however, accurate detection of start of preictal state remains a challenge. We propose a novel ensemble classifier based method that gets the comprehensive feature set as input and combines three different classifiers to detect the preictal state.

RESULTS

We have applied the proposed method on the publicly available scalp EEG dataset CHBMIT of 22 subjects. An average accuracy of 94.31% with sensitivity and specificity of 94.73% and 93.72% respectively has been achieved with the method proposed in this study.

CONCLUSIONS

Proposed study utilizes the preprocessing techniques for noise removal, combines deep learning based and handcrafted features and an ensemble classifier for detection of start of preictal state. Proposed method gives better results in terms of accuracy, sensitivity, and specificity.

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.

Automated Epileptic Seizure Detection in Pediatric Subjects of CHB-MIT EEG Database-A Survey

Epilepsy is a neurological disorder of the brain that causes frequent occurrence of seizures. Electroencephalography (EEG) is a tool that assists neurologists in detecting epileptic seizures caused by an unexpected flow of electrical activities in the brain. Automated detection of an epileptic seizure is a crucial task in diagnosing epilepsy which overcomes the drawback of a visual diagnosis. The dataset analyzed in this article, collected from Children's Hospital Boston (CHB) and the Massachusetts Institute of Technology (MIT), contains long-term EEG records from 24 pediatric patients. This review paper focuses on various patient-dependent and patient-independent personalized medicine approaches involved in the computer-aided diagnosis of epileptic seizures in pediatric subjects by analyzing EEG signals, thus summarizing the existing body of knowledge and opening up an enormous research area for biomedical engineers. This review paper focuses on the features of four domains, such as time, frequency, time-frequency, and nonlinear features, extracted from the EEG records, which were fed into several classifiers to classify between seizure and non-seizure EEG signals. Performance metrics such as classification accuracy, sensitivity, and specificity were examined, and challenges in automatic seizure detection using the CHB-MIT database were addressed.

An Effective Dual Self-Attention Residual Network for Seizure Prediction

As one of the most challenging data analysis tasks in chronic brain diseases, epileptic seizure prediction has attracted extensive attention from many researchers. Seizure prediction, can greatly improve patients' quality of life in many ways, such as preventing accidents and reducing harm that may occur during epileptic seizures. This work aims to develop a general method for predicting seizures in specific patients through exploring the time-frequency correlation of features obtained from multi-channel EEG signals. We convert the original EEG signals into spectrograms that represent time-frequency characteristics by applying short-time Fourier transform (STFT) to the EEG signals. For the first time, we propose a dual self-attention residual network (RDANet) that combines a spectrum attention module integrating local features with global features, with a channel attention module mining the interdependence between channel mappings to achieve better forecasting performance. Our proposed approach achieved a sensitivity of 89.33%, a specificity of 93.02%, an AUC of 91.26% and an accuracy of 92.07% on 13 patients from the public CHB-MIT scalp EEG dataset. Our experiments show that different EEG signal prediction segment lengths are an important factor affecting prediction performance. Our proposed method is competitive and achieves good robustness without patient-specific engineering.

A deep learning based ensemble learning method for epileptic seizure prediction

In epilepsy, patients suffer from seizures which cannot be controlled with medicines or surgical treatments in more than 30% of the cases. Prediction of epileptic seizures is extremely important so that they can be controlled with medication before they actually occur. Researchers have proposed multiple machine/deep learning based methods to predict epileptic seizures; however, accurate prediction of epileptic seizures with low false positive rate is still a challenge. In this research, we propose a deep learning based ensemble learning method to predict epileptic seizures. In the proposed method, EEG signals are preprocessed using empirical mode decomposition followed by bandpass filtering for noise removal. The class imbalance problem has been mitigated with synthetic preictal segments generated using generative adversarial networks. A three-layer customized convolutional neural network has been proposed to extract automated features from preprocessed EEG signals and combined them with handcrafted features to get a comprehensive feature set. The feature set is then used to train an ensemble classifier that combines the output of SVM, CNN and LSTM using Model agnostic meta learning. An average sensitivity of 96.28% and specificity of 95.65% with an average anticipation time of 33 min on all subjects of CHBMIT has been achieved by the proposed method, whereas, on American epilepsy society-Kaggle seizure prediction dataset, an average sensitivity of 94.2% and specificity of 95.8% has been achieved on all subjects.

Edge deep learning for neural implants: a case study of seizure detection and prediction

Objective.Implanted devices providing real-time neural activity classification and control are increasingly used to treat neurological disorders, such as epilepsy and Parkinson's disease. Classification performance is critical to identifying brain states appropriate for the therapeutic action (e.g. neural stimulation). However, advanced algorithms that have shown promise in offline studies, in particular deep learning (DL) methods, have not been deployed on resource-restrained neural implants. Here, we designed and optimized three DL models or edge deployment and evaluated their inference performance in a case study of seizure detection.Approach.A deep neural network (DNN), a convolutional neural network (CNN), and a long short-term memory (LSTM) network were designed and trained with TensorFlow to classify ictal, preictal, and interictal phases from the CHB-MIT scalp EEG database. A sliding window based weighted majority voting algorithm was developed to detect seizure events based on each DL model's classification results. After iterative model compression and coefficient quantization, the algorithms were deployed on a general-purpose, off-the-shelf microcontroller for real-time testing. Inference sensitivity, false positive rate (FPR), execution time, memory size, and power consumption were quantified.Main results.For seizure event detection, the sensitivity and FPR for the DNN, CNN, and LSTM models were 87.36%/0.169 h^-1, 96.70%/0.102 h^-1, and 97.61%/0.071 h^-1, respectively. Predicting seizures for early warnings was also feasible. The LSTM model achieved the best overall performance at the expense of the highest power. The DNN model achieved the shortest execution time. The CNN model showed advantages in balanced performance and power with minimum memory requirement. The implemented model compression and quantization achieved a significant saving of power and memory with an accuracy degradation of less than 0.5%.Significance.Inference with embedded DL models achieved performance comparable to many prior implementations that had no time or computational resource limitations. Generic microcontrollers can provide the required memory and computational resources, while model designs can be migrated to application-specific integrated circuits for further optimization and power saving. The results suggest that edge DL inference is a feasible option for future neural implants to improve classification performance and therapeutic outcomes.

Performance Evaluation of Epileptic Seizure Prediction Using Time, Frequency, and Time–Frequency Domain Measures

The prediction of epileptic seizures is crucial to aid patients in gaining early warning and taking effective intervention. Several features have been explored to predict the onset via electroencephalography signals, which are typically non-stationary, dynamic, and varying from person-to-person. In the former literature, features applied in the classification have shared similar contributions to all patients. Therefore, in this paper, we analyze the impact of the specific combination of feature and channel from time, frequency, and time–frequency domains on prediction performance of disparate patients. Based on the minimal-redundancy-maximal-relevance criterion, the proposed framework uses a sequential forward selection approach to individually find the optimal features and channels. Trained models could discriminate the pre-ictal and inter-ictal electroencephalography with a sensitivity of 90.2% and a false prediction rate of 0.096/h. We also present the comparison between the classification accuracy obtained by the optimal features, several features summarized from optimal features, and the complete set of features from three domains. The results indicate that various patient interpretations have a certain specificity in the selection of feature-channel. Furthermore, the detailed list of optimal features and summarized features are proffered for reference to those who research the corresponding database.

Seizure onset detection based on detection of changes in brain activity quantified by evolutionary game theory model

BACKGROUND AND OBJECTIVE

Epilepsy is one of the most common diseases of the nervous system, affecting about 1% of the world's population. The unpredictable nature of the epilepsy seizures deprives the patients and those around them of living a normal life. Therefore, the development of new methods that can help these patients will increase the life quality of these people and can bring a lot of economic savings in the health sector.

METHODS

In this study, we introduced a new framework for seizure onset detection. Our framework provides a new modelling for brain activity using evolutionary game theory and Kalman filter. If the patterns in the electroencephalogram (EEG) signal violate the predicted patterns by the proposed model, using a novel detection algorithm that has been also introduced in this paper, it can be determined whether the observed violation is the result of the onset of an epileptic seizure or not.

RESULTS

The proposed approach was able to detect the onset of all the seizures in CHB-MIT dataset with an average delay of -0.8 s and a false alarm of 0.39 per hour. Also, our proposed approach is about 20 times faster compared to recent studies.

CONCLUSIONS

The experimental results of applying the proposed framework on the CHB-MIT dataset show that our framework not only performed well with respect to the sensitivity, delay, and false alarm metrics but also performed much better in terms of run time compared to recent studies. This appropriate run time, along with other suitable metrics, makes it possible to use this framework in many cases where processing power or energy is limited and to think about creating new and inexpensive solutions for the treatment and care of people diagnosed with epilepsy.

Epilepsy control using a fixed time integral super twisting sliding mode control for Pinsky-Rinzel pyramidal model through ion channels with optogenetic method

BACKGROUND AND OBJECTIVE

Epilepsy is a dynamic disease of neuronal networks and epileptic activity in the brain should be suppressed quickly in the shortest possible time with minimum control signal. Thus, a closed-loop feedback control by using the fixed-time integral super-twisting sliding-mode controller via an optogenetic method is employed for suppressing seizures in the Pinsky-Rinzel (PR) model as a dynamic model of the hippocampus CA3 region where epileptic seizures occur. The control signal is applied to the PR model through the ChR2 channel model in the form of light photons using the optogenetic method. The present study aimed to determine the controller robustness against parameter changes and disturbances in order to reduce the control time, approach the zero tracking error of the normal desired state in a fixed time, and finally, converge the epileptic state to the normal desired state.

METHOD

In order to apply the control signal to the Pinsky-Rinzel model in the optogenetic method, the dynamic model of the ion current generated by channelrhodopsin 2 (ChR2) as a light-sensitive protein model in the optogenetic method was first applied to the PR model. Then, a fixed-time integral super-twisting sliding-mode controller was designed for the system, which is the combination of PR and ChR2 models.

RESULTS

After applying the proposed controller, the simulation results indicated that the control signal was -0.7 mV, the tracking error of the normal desired state could reach zero within 1.5 milliseconds, and the problems of singularity and chattering were solved.

CONCLUSIONS

A reduction occurred in the control signal reduced regarding the objectives of the study and comparing the proposed controller with the classical sliding-mode controller. Thus, this method can produce a safe control input for brain. In addition, both types of sliding mode controllers are robust against the parameters variations and external disturbances. Thus, they are superior to non-robust and simple controllers. Finally, based on the results, the validity of the fixed-time integral super-twisting sliding mode controller is confirmed for epilepsy control.

Comparison of Frontal-Temporal Channels in Epilepsy Seizure Prediction Based on EEMD-ReliefF and DNN

Epilepsy patients who do not have their seizures controlled with medication or surgery live in constant fear. The psychological burden of uncertainty surrounding the occurrence of random seizures is one of the most stressful and debilitating aspects of the disease. Despite the research progress in this field, there is a need for a non-invasive prediction system that helps disrupt the seizure epileptiform. Electroencephalogram (EEG) signals are non-stationary, nonlinear and vary with each patient and every recording. Full use of the non-invasive electrode channels is impractical for real-time use. We propose two frontal-temporal electrode channels based on ensemble empirical mode decomposition (EEMD) and Relief methods to address these challenges. The EEMD decomposes the segmented data frame in the ictal state into its intrinsic mode functions, and then we apply Relief to select the most relevant oscillatory components. A deep neural network (DNN) model learns these features to perform seizure prediction and early detection of patient-specific EEG recordings. The model yields an average sensitivity and specificity of 86.7% and 89.5%, respectively. The two-channel model shows the ability to capture patterns from brain locations for non-fontal-temporal seizures.

Detection of Focal and Non-Focal Electroencephalogram Signals Using Fast Walsh-Hadamard Transform and Artificial Neural Network

The discrimination of non-focal class (NFC) and focal class (FC), is vital in localizing the epileptogenic zone (EZ) during neurosurgery. In the conventional diagnosis method, the neurologist has to visually examine the long hour electroencephalogram (EEG) signals, which consumes time and is prone to error. Hence, in this present work, automated diagnosis of FC EEG signals from NFC EEG signals is developed using the Fast Walsh-Hadamard Transform (FWHT) method, entropies, and artificial neural network (ANN). The FWHT analyzes the EEG signals in the frequency domain and decomposes it into the Hadamard coefficients. Five different nonlinear features, namely approximate entropy (ApEn), log-energy entropy (LogEn), fuzzy entropy (FuzzyEn), sample entropy (SampEn), and permutation entropy (PermEn) are extracted from the decomposed Hadamard coefficients. The extracted features detail the nonlinearity in the NFC and the FC EEG signals. The judicious entropy features are supplied to the ANN classifier, with a 10-fold cross-validation method to classify the NFC and FC classes. Two publicly available datasets such as the University of Bonn and Bern-Barcelona dataset are used to evaluate the proposed approach. A maximum sensitivity of 99.70%, the accuracy of 99.50%, and specificity of 99.30% with the 3750 pairs of NFC and FC signal are achieved using the Bern-Barcelona dataset, while the accuracy of 92.80%, the sensitivity of 91%, and specificity of 94.60% is achieved using University of Bonn dataset. Compared to the existing technique, the proposed approach attained a maximum classification performance in both the dataset.

Deep Convolutional Neural Network-Based Epileptic Electroencephalogram (EEG) Signal Classification

Electroencephalogram (EEG) signals contain vital information on the electrical activities of the brain and are widely used to aid epilepsy analysis. A challenging element of epilepsy diagnosis, accurate classification of different epileptic states, is of particular interest and has been extensively investigated. A new deep learning-based classification methodology, namely epileptic EEG signal classification (EESC), is proposed in this paper. This methodology first transforms epileptic EEG signals to power spectrum density energy diagrams (PSDEDs), then applies deep convolutional neural networks (DCNNs) and transfer learning to automatically extract features from the PSDED, and finally classifies four categories of epileptic states (interictal, preictal duration to 30 min, preictal duration to 10 min, and seizure). It outperforms the existing epilepsy classification methods in terms of accuracy and efficiency. For instance, it achieves an average classification accuracy of over 90% in a case study with CHB-MIT epileptic EEG data.

Epileptic seizure prediction based on EEG spikes detection of ictal-preictal states

Epileptic seizures are known for their unpredictable nature. However, recent research provides that the transition to seizure event is not random but the result of evidence accumulations. Therefore, a reliable method capable to detect these indications can predict seizures and improve the life quality of epileptic patients. Seizures periods are generally characterized by epileptiform discharges with different changes including spike rate variation according to the shapes, spikes, and the amplitude. In this study, spike rate is used as the indicator to anticipate seizures in electroencephalogram (EEG) signal. Spikes detection step is used in EEG signal during interictal, preictal, and ictal periods followed by a mean filter to smooth the spike number. The maximum spike rate in interictal periods is used as an indicator to predict seizures. When the spike number in the preictal period exceeds the threshold, an alarm is triggered. Using the CHB-MIT database, the proposed approach has ensured 92% accuracy in seizure prediction for all patients.

Epilepsy Seizure Prediction on EEG Using Common Spatial Pattern and Convolutional Neural Network

Epilepsy seizure prediction paves the way of timely warning for patients to take more active and effective intervention measures. Compared to seizure detection that only identifies the inter-ictal state and the ictal state, far fewer researches have been conducted on seizure prediction because the high similarity makes it challenging to distinguish between the pre-ictal state and the inter-ictal state. In this paper, a novel solution on seizure prediction is proposed using common spatial pattern (CSP) and convolutional neural network (CNN). Firstly, artificial pre-ictal EEG signals based on the original ones are generated by combining the segmented pre-ictal signals to solve the trial imbalance problem between the two states. Secondly, a feature extractor employing wavelet packet decomposition and CSP is designed to extract the distinguishing features in both the time domain and the frequency domain. It can improve overall accuracy while reducing the training time. Finally, a shallow CNN is applied to discriminate between the pre-ictal state and the inter-ictal state. Our proposed solution is evaluated on 23 patients' data from Boston Children's Hospital-MIT scalp EEG dataset by employing a leave-one-out cross-validation, and it achieves a sensitivity of 92.2% and false prediction rate of 0.12/h. Experimental result demonstrates that the proposed approach outperforms most state-of-the-art methods.

Automated seizure prediction

In the past two decades, significant advances have been made on automated electroencephalogram (EEG)-based diagnosis of epilepsy and seizure detection. A number of innovative algorithms have been introduced that can aid in epilepsy diagnosis with a high degree of accuracy. In recent years, the frontiers of computational epilepsy research have moved to seizure prediction, a more challenging problem. While antiepileptic medication can result in complete seizure freedom in many patients with epilepsy, up to one-third of patients living with epilepsy will have medically intractable epilepsy, where medications reduce seizure frequency but do not completely control seizures. If a seizure can be predicted prior to its clinical manifestation, then there is potential for abortive treatment to be given, either self-administered or via an implanted device administering medication or electrical stimulation. This will have a far-reaching impact on the treatment of epilepsy and patient's quality of life. This paper presents a state-of-the-art review of recent efforts and journal articles on seizure prediction. The technologies developed for epilepsy diagnosis and seizure detection are being adapted and extended for seizure prediction. The paper ends with some novel ideas for seizure prediction using the increasingly ubiquitous machine learning technology, particularly deep neural network machine learning.

Predicting state transitions in brain dynamics through spectral difference of phase-space graphs

Networks are naturally occurring phenomena that are studied across many disciplines. The topological features of a network can provide insight into the dynamics of a system as it evolves, and can be used to predict changes in state. The brain is a complex network whose temporal and spatial behavior can be measured using electroencephalography (EEG). This data can be reconstructed to form a family of graphs that represent the state of the brain over time, and the evolution of these graphs can be used to predict changes in brain states, such as the transition from preictal to ictal in patients with epilepsy. This research proposes objective indications of seizure onset observed from minimally invasive scalp EEG. The approach considers the brain as a complex nonlinear dynamical system whose state can be derived through time-delay embedding of the EEG data and characterized to determine change in brain dynamics related to the preictal state. This method targets phase-space graph spectra as biomarkers for seizure prediction, correlates historical degrees of change in spectra, and makes accurate prediction of seizure onset. A significant trend of normalized dissimilarity over time indicates a departure from the norm, and thus a change in state. Our methods show high sensitivity (90-100%) and specificity (90%) on 241 h of scalp EEG training data, and sensitivity and specificity of 70%-90% on test data. Moreover, the algorithm was capable of processing 12.7 min of data per second on an Intel Core i3 CPU in Matlab, showing that real-time analysis is viable.

A Patient-Specific Approach for Short-Term Epileptic Seizures Prediction Through the Analysis of EEG Synchronization

Epilepsy is a neurological disorder arising from anomalies of the electrical activity in the brain, affecting about 65 millions individuals worldwide.

OBJECTIVE

This paper proposes a patient-specific approach for short-term prediction (i.e., within few minutes) of epileptic seizures.

METHODS

We use noninvasive EEG data, since the aim is exploring the possibility of developing a noninvasive monitoring/control device for the prediction of seizures. Our approach is based on finding synchronization patterns in the EEG that allow to distinguish in real time preictal from interictal states. In practice, we develop easily computable functions over a graph model to capture the variations in the synchronization, and employ a classifier for identifying the preictal state.

RESULTS

We compare two state-of-the-art classification algorithms and a simple and computationally inexpensive threshold-based classifier developed ad hoc. Results on publicly available scalp EEG database and on scalp data of the patients of the Unit of Neurology and Neurophysiology at University of Siena show that this simple and computationally viable processing is able to highlight the changes in synchronization when a seizure is approaching.

CONCLUSION AND SIGNIFICANCE

The proposed approach, characterized by low computational requirements and by the use of noninvasive techniques, is a step toward the development of portable and wearable devices for real-life use.