Preictal EEG Research Articles

Nonictal electroencephalographic measures for the diagnosis of functional seizures.

Functional seizures (FS) look like epileptic seizures but are characterized by a lack of epileptic activity in the brain. Approximately one in five referrals to epilepsy clinics are diagnosed with this condition. FS are diagnosed by recording a seizure using video-electroencephalography (EEG), from which an expert inspects the semiology and the EEG. However, this method can be expensive and inaccessible and can present significant patient burden. No single biomarker has been found to diagnose FS. However, the current limitations in FS diagnosis could be improved with machine learning to classify signal features extracted from EEG, thus providing a potentially very useful aid to clinicians. The current study has investigated the use of seizure-free EEG signals with machine learning to identify subjects with FS from those with epilepsy. The dataset included interictal and preictal EEG recordings from 48 subjects with FS (mean age = 34.76 ± 10.55 years, 14 males) and 29 subjects with epilepsy (mean age = 38.95 ± 13.93 years, 18 males) from which various statistical, temporal, and spectral features from the five EEG frequency bands were extracted then analyzed with threshold accuracy, five machine learning classifiers, and two feature importance approaches. The highest classification accuracy reported from thresholding was 60.67%. However, the temporal features were the best performing, with the highest balanced accuracy reported by the machine learning models: 95.71% with all frequency bands combined and a support vector machine classifier. Machine learning was much more effective than using individual features and could be a powerful aid in FS diagnosis. Furthermore, combining the frequency bands improved the accuracy of the classifiers in most cases, and the lowest performing EEG bands were consistently delta and gamma.

Supervised and Unsupervised Deep Learning Approaches for EEG Seizure Prediction.

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

Prediction of Seizure Onset with Machine Learning: A Treatment Option for Landau Kleffner Syndrome

Landau Kleffner Syndrome (LKS) is a rare genetic disorder that presents in the form of auditory verbal agnosia and aphasia (loss of ability to interpret and express language) as well as electroencephalographic abnormalities, which present in children from the ages of 2 to 8. The disorder is classified as developmental/epileptic encephalopathy with spike wave activation on sleep (DEE-SWAS), with 70% of affected patients having epileptic seizures. The disorder is diagnosed based on language regression in addition to severe EEG abnormalities during non-REM sleep. Sometimes patients with epileptiform disorders can sense when a seizure is imminent and alert caretakers of the situation so they can be safely situated when the seizure occurs. This period is called the preictal period or prodrome in which patients can sometimes detect changes in mood and behavior. However, in disorders such as LKS, the loss of verbal expression proves difficult for expression of needs, and could lead to dangerous situations along with a constant need for such patients to be monitored. In this study, machine learning techniques are utilized to analyze several hours of ictal and preictal EEG data from 23 patients in order to predict the onset of a seizure. This study aims to promote patient safety and reduce need for constant monitoring by predicting when a seizure will occur. Several machine learning models have been constructed and their accuracies have been analyzed and compared to those of other studies to create an optimized program which can accurately interpret EEG data.

Epileptic Seizure Prediction Using Attention Augmented Convolutional Network.

Early seizure prediction is crucial for epilepsy patients to reduce accidental injuries and improve their quality of life. Identifying pre-ictal EEG from the inter-ictal state is particularly challenging due to their nonictal nature and remarkable similarities. In this study, a novel epileptic seizure prediction method is proposed based on multi-head attention (MHA) augmented convolutional neural network (CNN) to address the issue of CNN's limit of capturing global information of input signals. First, data enhancement is performed on original EEG recordings to balance the pre-ictal and inter-ictal EEG data, and the EEG recordings are sliced into 6-second-long EEG segments. Subsequently, EEG time-frequency distribution is obtained using Stockwell transform (ST), and the attention augmented convolutional network is employed for feature extraction and classification. Finally, post-processing is utilized to reduce the false prediction rate (FPR). The CHB-MIT EEG database was used to evaluate the system. The validation results showed a segment-based sensitivity of 98.24% and an event-based sensitivity of 94.78% with a FPR of 0.05/h were yielded, respectively. The satisfying results of the proposed method demonstrate its possible potential for clinical applications.

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.

Convolutional neural network-based lightweight hardware IP core design for EEG epilepsy prediction

Epilepsy is one of the most common neurological disorders. In order to realize a portable and wearable epilepsy prediction device, a lightweight hardware IP core is proposed for EEG epilepsy prediction. The scheme first analyzes the epileptic EEG signal and extracts the time-frequency feature maps of interictal and preictal EEG signals. Then it reduces the network parameters using the single-channel approach to reduce the number of neurons and network complexity, and trains the lightweight epilepsy prediction convolutional neural network by combining the time-frequency feature maps. Finally, a hardware convolutional layer is designed with pipeline function, and it connect 8 layers with feature map buffer to realizes the lightweight EEG epilepsy prediction hardware IP core. Using TSMC 65 nm process, the hardware IP core is functionally verified with 87.9% prediction accuracy. The area is 2.55 mm2 and the power is 4.45 mW. Under 1V & 20 MHz operating conditions, single prediction latency is 3.29 ms and energy efficiency is 0.146 μJ/class.

EEG Analysis of Eye Movement Artifact in Parietal and Occipital Lobe Seizures: A Search for Epileptic Nystagmus (P10-1.011)

<h3>Objective:</h3> To report a method of eye movement artifact analysis on EEG without EOG electrodes, and to identify a characteristic eye movement artifact in parietal and occipital lobe seizures, consistent with Epileptic nystagmus (EN). <h3>Background:</h3> EN is a rarely reported seizure semiology, most commonly associated with seizures originating in the posterior cortical regions. EN is often easily missed in long-term video-EEG (vEEG) recordings because of multiple reasons such as poor camera resolution or camera not focused on the eyes. <h3>Design/Methods:</h3> We performed a retrospective vEEG analysis of three patients with occipital and parietal lobe seizures. The eyes were not clearly visible in any of the patients. We analyzed 30 seconds of pre-ictal EEG for any unusual eye movements, followed by the ictal EEG. We identified epochs of unilaterally directed repetitive saccadic eye movement artifacts (≥5 saccades) during the ictus. We analyzed these eye movements in a longitudinal bipolar montage with increased time constant (TC) of ≥2 seconds. <h3>Results:</h3> In all three patients, there was no specific pattern of repetitive saccadic eye movement artifact in the pre-ictal period. During the ictus, all of the patients showed repetitive contralaterally directed saccadic eye movements. When analyzed with TC≥2 seconds, the saccades were alternating with linear slow phases directed ipsilateral to the seizure focus. In one patient, there was a clear prolonged slow drift ipsilateral to the seizure focus before the onset of nystagmus, consistent with type II EN. <h3>Conclusions:</h3> EN is likely under-reported because of either lack of video evidence or lack of special EOG electrodes. Our study demonstrates a specific pattern of eye movement artifact seen on EEG in parietal and occipital seizures, consistent with EN. We also report a method to identify the slow and fast phases of EN on EEG, which can also delineate the underlying mechanism of EN (type I v type II). <b>Disclosure:</b> Dr. Acar has nothing to disclose. Dr. Zampino has nothing to disclose. Dr. Kirsch has nothing to disclose. Dr. Fotedar has nothing to disclose.

An Enhanced Automated Epileptic Seizure Detection Using ANFIS, FFA and EPSO Algorithms

Objectives: Electroencephalogram (EEG) signal gives a viable perception about the neurological action of the human brain that aids the detection of epilepsy. The objective of this study is to build an accurate automated hybrid model for epileptic seizure detection. Methods: This work develops a computer-aided diagnosis (CAD) machine learning model which can spontaneously classify pre-ictal and ictal EEG signals. In the proposed method two most effective nature inspired algorithms, Firefly algorithm (FFA) and Efficient Particle Swarm Optimization (EPSO) are used to determine the optimum parameters of Adaptive Neuro Fuzzy Inference System (ANFIS) network. Results: Compared to the FFA and EPSO algorithm separately, the composite (ANFIS+FFA+EPSO) optimization algorithm outperforms in all respects. The proposed technique achieved accuracy, specificity, and sensitivity of 99.87%, 98.71% and 100% respectively. Conclusion: The ANFIS-FFA-EPSO method is able to enhance the seizure detection outcomes for demand forecast in hospital.

Compact Convolutional Neural Network with Multi-Headed Attention Mechanism for Seizure Prediction.

Epilepsy is a neurological disorder related to frequent seizures. Automatic seizure prediction is crucial for the prevention and treatment of epilepsy. In this paper, we propose a novel model for seizure prediction that incorporates a convolutional neural network (CNN) with multi-head attention mechanism. In this model, the shallow CNN automatically captures the EEG features, and the multi-headed attention focuses on discriminating the effective information among these features for identifying pre-ictal EEG segments. Compared with current CNN models for seizure prediction, the embedded multi-headed attention empowers the shallow CNN to be more flexible, and enables improvement of the training efficiency. Hence, this compact model is more resistant to being trapped in overfitting. The proposed method was evaluated over the scalp EEG data from the two publicly available epileptic EEG databases, and achieved outperforming values of event-level sensitivity, false prediction rate (FPR), and epoch-level F1. Furthermore, our method achieved the stable length of seizure prediction time that was between 14 and 15 min. The experimental comparisons showed that our method outperformed other prediction methods in terms of prediction and generalization performance.

Classification of Epileptic Brain Signals of College Students Based on Deep Learning

Epilepsy, as a common nervous system disease in the world, urgently needs effective methods for diagnosis and treatment. Scalp electroencephalogram (EEG) contains a lot of physiological and pathological information, which plays a very important role in the diagnosis of brain diseases such as epilepsy. At present, the clinical analysis of EEG signal is mainly based on the clinician’s visual analysis, which makes the clinician’s task heavy, and there is no quantitative standard for the analysis results. Therefore, the automatic classification of epileptic EEG signals has great potential in current clinical application. Based on the deep learning VGG16 convolutional neural network model, a method for automatic detection of seizure signals is proposed in this paper. Firstly, the samples are preprocessed, then enter the VGG16 convolutional neural network model for training, and finally input the validation set for validation. The experimental results indicate that this model can distinguish the pre-ictal EEG, interictal EEG and ictal EEG.

Seizure forecasting using minimally invasive, ultra-long-term subcutaneous electroencephalography: Individualized intrapatient models.

One of the most disabling aspects of living with chronic epilepsy is the unpredictability of seizures. Cumulative research in the past decades has advanced our understanding of the dynamics of seizure risk. Technological advances have recently made it possible to record pertinent biological signals, including electroencephalogram (EEG), continuously. We aimed to assess whether patient-specific seizure forecasting is possible using remote, minimally invasive ultra-long-term subcutaneous EEG. We analyzed a two-center cohort of ultra-long-term subcutaneous EEG recordings, including six patients with drug-resistant focal epilepsy monitored for 46-230days with median 18h/day of recorded data, totaling >11000h of EEG. Total electrographic seizures identified by visual review ranged from 12 to 36 per patient. Three candidate subject-specific long short-term memory network deep learning classifiers were trained offline and pseudoprospectively on preictal (1 h before) and interictal (>1 day from seizures) EEG segments. Performance was assessed relative to a random predictor. Periodicity of the final forecasts was also investigated with autocorrelation. Depending on each architecture, significant forecasting performance was achieved in three to five of six patients, with overall mean area under the receiver operating characteristic curve of .65-.74. Significant forecasts showed sensitivity ranging from 64% to 80% and time in warning from 10.9% to 44.4%. Overall, the output of the forecasts closely followed patient-specific circadian patterns of seizure occurrence. This study demonstrates proof-of-principle for the possibility of subject-specific seizure forecasting using a minimally invasive subcutaneous EEG device capable of ultra-long-term at-home recordings. These results are encouraging for the development of a prospective seizure forecasting trial with minimally invasive EEG.

Ictal Occurrence of High-Frequency Oscillations Correlates With Seizure Severity in a Rat Model of Temporal Lobe Epilepsy.

High-frequency oscillations (HFOs, ripples 80–250 Hz, fast ripples 250–500 Hz) are biomarkers of epileptic tissue. They are most commonly observed over areas generating seizures and increase in occurrence during the ictal compared to the interictal period. It has been hypothesized that their rate correlates with the severity of epilepsy and seizure in affected individuals. In the present study, it was aimed to investigate whether the HFO count mirrors the observed behavioral seizure severity using a kainate rat model for temporal lobe epilepsy. Seizures were selected during the chronic epilepsy phase of this model and classified by behavioral severity according to the Racine scale. Seizures with Racine scale 5&6 were considered generalized and severe. HFOs were marked in 24 seizures during a preictal, ictal, and postictal EEG segment. The duration covered by the HFO during these different segments was analyzed and compared between mild and severe seizures. HFOs were significantly increased during ictal periods (p < 0.001) and significantly decreased during postictal periods (p < 0.03) compared to the ictal segment. Ictal ripples (p = 0.04) as well as fast ripples (p = 0.02) were significantly higher in severe seizures compared to mild seizures. The present study demonstrates that ictal HFO occurrence mirrors seizure severity in a chronic focal epilepsy model in rats. This is similar to recent observations in patients with refractory mesio-temporal lobe epilepsy. Moreover, postictal HFO decrease might reflect postictal inhibition of epileptic activity. Overall results provide additional evidence that HFOs can be used as biomarkers for measuring seizure severity in epilepsy.

Wavelet Time Scattering Based Classification of Interictal and Preictal EEG Signals

If it were possible to reliably identify the preictal brain state from dynamical changes in EEG data of epilepsy patients, then the age long problem of actualizing a fully automated closed-loop seizure – warning or seizure-prevention system that is clinically deployable would have been resolved. Accordingly, through feature engineering, a great deal of effort has been invested over the discovery of EEG features or measures that are always indicative of the preictal brain state. However, this has proven to be difficult, time consuming and apparently unsuccessful. Therefore, lately, attention has shifted to feature learning-methods that automatically learn and extracts useful discriminatory features from raw data. This paper studies the efficacy of wavelet time scattering learned EEG features for interictal and preictal EEG classification. Wavelet time scattering network developed in Matlab and two different EEG datasets: CHB-MIT scalp EEG and AES intracranial EEG datasets were used for the study. The learned interictal and preictal EEG features were used to train and evaluate a simple binary support vector machine classifier. Three different classification accuracy results namely ordinary cross validation, true cross validation and test classification accuracy results were reported for the analysis. Mean classification accuracy values of 93.15%, 97.57% and 91.33% were obtained respectively for the scalp EEG while mean classification accuracy values of 98.33%, 100% and 96.73% were obtained respectively for the intracranial EEG. A general comparison showed that the combination of wavelet time scattering learned EEG features and a simple binary support vector machine classifier performed equally or even better than deep convolutional neural networks in EEG classification tasks. Finally, wavelet time scattering has proven to be a very good EEG feature learner and may greatly improve the sensitivity and specificity of seizure prediction algorithms.

Automatic recognition of preictal and interictal EEG signals using 1D-capsule networks

Epilepsy is the most common neurological disorder affecting people of all ages. Seizure prediction can be achieved by separating the preictal state in which the changes in the brain activities begin to occur from the interictal state. Therefore, in this study, a novel method for preictal/interictal recognition, the most important step in seizure prediction from scalp electroencephalogram signals, is proposed. In the proposed method, one-dimensional capsule networks, a novel neural network model, is used. The best classification accuracy for preictal/interictal recognition was achieved with 97.74% in F3-C3 channel pairs. Compared to other methods, our 1D-CapsNet model achieved the best performance. Moreover, the results indicated that the interval that ended 30 min before the onset of seizures contained important information about preictal/interictal recognition. We believe that the proposed method will bring a new perspective to the seizure prediction studies of capsule networks.

Roughness-Length-Based Characteristic Analysis of Intracranial EEG and Epileptic Seizure Prediction.

To identify precursors of epileptic seizures, an EEG characteristic analysis is carried out based on a roughness-length method, where fractal dimensions and intercept values are extracted to measure the structure complexity and the amplitude roughness of EEG signals in different phases. Using the significant changes of the fractal dimension and intercept in the preictal phase with respect to those in the interictal phase, a patient-specific seizure prediction algorithm is then proposed by combining with a gradient boosting classifier. The probabilistic outputs of the trained gradient boosting classifier are further processed by threshold comparison and rule-based judgment to distinguish preictal EEG from interictal EEG and to generate seizure alerts. The prediction algorithm was evaluated on 20 patients' intracranial EEG recordings from the Freiburg EEG database, which contains the preictal periods of 65 seizures and 499[Formula: see text]h interictal EEG. Setting the seizure prediction horizon as 2[Formula: see text]min, averaged sensitivity values of 90.42% and 91.67% with averaged false prediction rates of 0.12/h and 0.10/h were achieved for seizure occurrence periods of 30 and 50[Formula: see text]min, respectively. These results demonstrate the ability of fractal dimension and intercept metrics in predicting the occurrence of seizures.

Automated Epileptic Seizure Detection Model using WPT, CFS and KNN based Multiclass TSVM

The main aim of the proposed work is to generate an accurate automated seizure detection model for the performance evaluation of the improvement on epileptic patients in an improved manner. Long data sets of EEG signals are recorded for a long duration of time which has taken from PhysioNet CHB-MIT EEG datset for this experimental work. Six types of elements are excerpted from EEG signals by using WPT method and which is then classified by using CFS method. Then, all the features are combinely inputted to the rule based twin- support vector machines (TSVMs ) to detect normal, ictal and pre-ictal EEG segments. The developed seizure detection WPT-KWMTSVM method achieved excellent performance with the average Accuracy, specificity, sensitivity, G-mean, positive predictive value, and Mathews correlation coefficients are 97.14%, 97.33%, 97.00%, 97.31%, 96.85%, 95.96% respectively The average area under curve (AUC) is approximately 1. The proposed method is able to enhance the seizure detection outcomes for proper clinical diagnosis in medical applications.

A Hybrid and Automated Epileptic Seizure Detection Model using Improved PSO and Extreme Learning ANFIS Network

The main aim of the proposed work is to generate an accurate automated seizure detection model for the performance evaluation of the improvement on epileptic patients in an improved manner. Long data sets of EEG signals are recorded for a long duration of time which has taken from PhysioNet CHB-MIT EEG datset for this experimental work. Six types of elements are excerpted from EEG signals by using WPT method and which is then classified by using CFS method. Then, all the features are combinely inputted to the rule based twin- support vector machines (TSVMs) to detect normal, ictal and pre-ictal EEG segments. The developed seizure detection WPT-KWMTSVM method achieved excellent performance with the average Accuracy, specificity, sensitivity, G-mean, positive predictive value, and Mathews correlation coefficients are 97.14%, 97.33%, 97.00%, 97.31%, 96.85%, 95.96% respectively The average area under curve (AUC) is approximately 1. The proposed method is able to enhance the seizure detection outcomes for proper clinical diagnosis in medical applications.

A phase entropy based novel machine learning structure conditioned for classifying ictal and non-ictal signal aimed at proper clinical diagnosis

Proposed scheme is based on the detection and classification of ictal and pre-ictal electro-encephalogram (EEG) signal of a partially affected epileptic patients. This work helps for the detection of ictal EEG signal as compared to pre-ictal EEG signal. In this work a conceptual method is used for the perfect detection of seizures. Here phase entropies (PEnS1 and PEnS2) are followed for feature extraction ictal and pre-ictal EEG signals. Again, extracted features are classified through multi-layer perception neural network (MLPNN) classifier tool. To train and test the classifier, map reduce quantum PSO (MRQPSO) is used. By considering various statistical parameters like Accuracy, Sensitivity, Specificity, positive predictive value, negative predictive value and Matthew's correlation coefficient, the performance of the proposed scheme has evaluated.

Semi-supervised training data selection improves seizure forecasting in canines with epilepsy

ObjectiveConventional selection of pre-ictal EEG epochs for seizure prediction algorithm training data typically assumes a continuous pre-ictal brain state preceding a seizure. This is carried out by defining a fixed duration, pre-ictal time period before seizures from which pre-ictal training data epochs are uniformly sampled. However, stochastic physiological and pathological fluctuations in EEG data characteristics and underlying brain states suggest that pre-ictal state dynamics may be more complex, and selection of pre-ictal training data segments to reflect this could improve algorithm performance. MethodsWe propose a semi-supervised technique to select pre-ictal training data most distinguishable from interictal EEG according to pre-specified data characteristics. The proposed method uses hierarchical clustering to identify optimal pre-ictal data epochs. ResultsIn this paper we compare the performance of a seizure forecasting algorithm with and without hierarchical clustering of pre-ictal periods in chronic iEEG recordings from six canines with naturally occurring epilepsy. Hierarchical clustering of training data improved results for Time In Warning (TIW) (0.18 vs. 0.23) and False Positive Rate (FPR) (0.5 vs. 0.59) when evaluated across all subjects (p < 0.001, n = 6). Results were mixed when evaluating TIW, FPR, and Sensitivity for individual dogs. ConclusionHierarchical clustering is a helpful method for training data selection overall, but should be evaluated on a subject-wise basis. SignificanceThe clustering method can be used to optimize results of forecasting towards sensitivity or TIW or FPR, and therefore can be useful for epilepsy management.

Epileptic seizure detection and prediction using stacked bidirectional long short term memory

Epilepsy is a not a disease but a neurological disorder. But people with epilepsy cannot lead a social life like others. Proper diagnosis and advance prediction of epileptic seizures definitely improves the life of epilepsy patients. In this paper an effort is made to develop a seizure detection and prediction method using stacked bidirectional long short term memory technique. This is the most suitable technique for the analysis of time series datasets as it overcomes the vanishing gradient problem identified in recurrent neural network. The dataset for detection and prediction experiments was taken from Bonn University. Our model could perform the seizure detection with the highest accuracy of 99.08% with 98% precision, 99.5% recall and ROC AUC: 0.984346. A binary classification method with AUC more than 0.9 is considered to be outstanding. Seizure prediction was conducted using the same dataset by classifying preictal states of EEG from interictal and ictal states. For the case of prediction our model could identify preictal states with the overall sensitivity: 89.21% and false prediction rate: 0.06. In future the model could be used to program the wearable devices like wrist watch which can be used by epileptic patients for seizure prediction. The device could be programmed to fire alarm during the detection of the preictal EEG signal before the onset of the seizure.