Seizure prediction for therapeutic devices: A review

Epileptic seizure forecasting with wearable-based nocturnal sleep features

OBJECTIVE

Non-invasive biomarkers have recently shown promise for seizure forecasting in people with epilepsy. In this work, we developed a seizure-day forecasting algorithm based on nocturnal sleep features acquired using a smart shirt.

METHODS

Seventy-eight individuals with epilepsy admitted to the Centre hospitalier de l'Université de Montréal epilepsy monitoring unit wore the Hexoskin biometric smart shirt during their stay. The shirt continuously measures electrocardiography, respiratory, and accelerometry activity. Ten sleep features, including sleep efficiency, sleep latency, sleep duration, time spent in non-rapid eye movement sleep (NREM) and rapid eye movement sleep (REM), wakefulness after sleep onset, average heart and breathing rates, high-frequency heart rate variability, and the number of position changes, were automatically computed using the Hexoskin sleep algorithm. Each night's features were then normalized using a reference night for each patient. A support vector machine classifier was trained for pseudo-prospective seizure-day forecasting, with forecasting horizons of 16- and 24-h to include both diurnal and nocturnal seizures (24-h) or diurnal seizures only (16-h). The algorithm's performance was assessed using a nested leave-one-patient-out cross-validation approach.

RESULTS

Improvement over chance (IoC) performances were achieved for 48.7% and 40% of patients with the 16- and 24-h forecasting horizons, respectively. For patients with IoC performances, the proposed algorithm reached mean IoC, sensitivity and time in warning of 34.3%, 86.0%, and 51.7%, respectively for the 16-h horizon, and 34.2%, 64.4% and 30.2%, respectively, for the 24-h horizon.

SIGNIFICANCE

Smart shirt-based nocturnal sleep analysis holds promise as a non-invasive approach for seizure-day forecasting in a subset of people with epilepsy. Further investigations, particularly in a residential setting with long-term recordings, could pave the way for the development of innovative and practical seizure forecasting devices.

PLAIN LANGUAGE SUMMARY

Seizure forecasting with wearable devices may improve the quality of life of people living with epilepsy who experience unpredictable, recurrent seizures. In this study, we have developed a seizure forecasting algorithm using sleep characteristics obtained from a smart shirt worn at night by a large number of hospitalized patients with epilepsy (78). A daily seizure forecast was generated following each night using machine learning methods. Our results show that around half of people with epilepsy may benefit from such an approach.

Single-trial detection of auditory cues from the rat brain using memristors

Implantable devices hold the potential to address conditions currently lacking effective treatments, such as drug-resistant neural impairments and prosthetic control. Medical devices need to be biologically compatible while providing enhanced performance metrics of low-power consumption, high accuracy, small size, and minimal latency to enable ongoing intervention in brain function. Here, we demonstrate a memristor-based processing system for single-trial detection of behaviorally meaningful brain signals within a timeframe that supports real-time closed-loop intervention. We record neural activity from the reward center of the brain, the ventral tegmental area, in rats trained to associate a musical tone with a reward, and we use the memristors built-in thresholding properties to detect nontrivial biomarkers in local field potentials. This approach yields consistent and accurate detection of biomarkers >98% while maintaining power consumption as low as 4.14 nanowatt per channel. The efficacy of our system's capabilities to process real-time in vivo neural data paves the way for low-power chronic neural activity monitoring and biomedical implants.

Online continual decoding of streaming EEG signal with a balanced and informative memory buffer

Electroencephalography (EEG) based Brain Computer Interface (BCI) systems play a significant role in facilitating how individuals with neurological impairments effectively interact with their environment. In real world applications of BCI system for clinical assistance and rehabilitation training, the EEG classifier often needs to learn on sequentially arriving subjects in an online manner. As patterns of EEG signals can be significantly different for different subjects, the EEG classifier can easily erase knowledge of learnt subjects after learning on later ones as it performs decoding in online streaming scenario, namely catastrophic forgetting. In this work, we tackle this problem with a memory-based approach, which considers the following conditions: (1) subjects arrive sequentially in an online manner, with no large scale dataset available for joint training beforehand, (2) data volume from the different subjects could be imbalanced, (3) decoding difficulty of the sequential streaming signal vary, (4) continual classification for a long time is required. This online sequential EEG decoding problem is more challenging than classic cross subject EEG decoding as there is no large-scale training data from the different subjects available beforehand. The proposed model keeps a small balanced memory buffer during sequential learning, with memory data dynamically selected based on joint consideration of data volume and informativeness. Furthermore, for the more general scenarios where subject identity is unknown to the EEG decoder, aka. subject agnostic scenario, we propose a kernel based subject shift detection method that identifies underlying subject changes on the fly in a computationally efficient manner. We develop challenging benchmarks of streaming EEG data from sequentially arriving subjects with both balanced and imbalanced data volumes, and performed extensive experiments with a detailed ablation study on the proposed model. The results show the effectiveness of our proposed approach, enabling the decoder to maintain performance on all previously seen subjects over a long period of sequential decoding. The model demonstrates the potential for real-world applications.

Seizure Detection, Prediction, and Forecasting

SUMMARY

Among the many fears associated with seizures, patients with epilepsy are greatly frustrated and distressed over seizure's apparent unpredictable occurrence. However, increasing evidence have emerged over the years to support that seizure occurrence is not a random phenomenon as previously presumed; it has a cyclic rhythm that oscillates over multiple timescales. The pattern in rises and falls of seizure rate that varies over 24 hours, weeks, months, and years has become a target for the development of innovative devices that intend to detect, predict, and forecast seizures. This article will review the different tools and devices available or that have been previously studied for seizure detection, prediction, and forecasting, as well as the associated challenges and limitations with the utilization of these devices. Although there is strong evidence for rhythmicity in seizure occurrence, very little is known about the mechanism behind this oscillation. This article concludes with early insights into the regulations that may potentially drive this cyclical variability and future directions.

The role of trained and untrained dogs in the detection and warning of seizures

Seizure unpredictability plays a major role in disability and decreased quality of life in people with epilepsy. Dogs have been used to assist people with disabilities and have shown promise in detecting seizures. There have been reports of trained seizure-alerting dogs (SADs) successfully detecting when a seizure is occurring or indicating imminent seizures, allowing patients to take preventative measures. Untrained pet dogs have also shown the ability to detect seizures and provide comfort and protection during and after seizures. Dogs' exceptional olfactory abilities and sensitivity to human cues could contribute to their seizure-detection capabilities. This has been supported by studies in which dogs have distinguished between epileptic seizure and non-seizure sweat samples, probably though the detection of volatile organic compounds (VOCs). However, the existing literature has limitations, with a lack of well-controlled, prospective studies and inconsistencies in reported timings of alerting behaviours. More research is needed to standardize reporting and validate the results. Advances in VOC profiling could aid in distinguishing seizure types and developing rapid and unbiased seizure detection methods. In conclusion, using dogs in epilepsy management shows considerable promise, but further research is needed to fully validate their effectiveness and potential as valuable companions for people with epilepsy.

A robust seizure detection and prediction method with feature selection and spatio-temporal casual neural network model

Objective.Epilepsy is a fairly common condition that affects the brain and causes frequent seizures. The sudden and recurring epilepsy brings a series of safety hazards to patients, which seriously affects the quality of their life. Therefore, real-time diagnosis of electroencephalogram (EEG) in epilepsy patients is of great significance. However, the conventional methods take in a tremendous amount of features to train the models, resulting in high computation cost and low portability. Our objective is to propose an efficient, light and robust seizure detecting and predicting algorithm.Approach.The algorithm is based on an interpretative feature selection method and spatial-temporal causal neural network (STCNN). The feature selection method eliminates the interference factors between different features and reduces the model size and training difficulties. The STCNN model takes both temporal and spatial information to accurately and dynamically track and diagnose the changing of the features. Considering the differences between medical application scenarios and patients, leave-one-out cross validation (LOOCV) and cross-patient validation (CPV) methods are used to conduct experiments on the dataset collected at the Children's Hospital Boston (CHB-MIT), Siena and Kaggle competition datasets.Main results.In LOOCV-based method, the detection accuracy and prediction sensitivity have been improved. A significant improvement is also achieved in the CPV-based method.Significance.The experimental results show that our proposed algorithm exhibits superior performance and robustness in seizure detection and prediction, which indicates it has higher capability to deal with different and complicated clinical situations.

Personalized dynamic network models of the human brain as a future tool for planning and optimizing epilepsy therapy

Epilepsy is a common neurological disorder, with one third of patients not responding to currently available antiepileptic drugs. The proportion of pharmacoresistant epilepsies has remained unchanged for many decades. To cure epilepsy and control seizures requires a paradigm shift in the development of new approaches to epilepsy diagnosis and treatment. Contemporary medicine has benefited from the exponential growth of computational modeling, and the application of network dynamics theory to understanding and treating human brain disorders. In epilepsy, the introduction of these approaches has led to personalized epileptic network modeling that can explore the patient's seizure genesis and predict the functional impact of resection on its individual network's propensity to seize. The application of the dynamic systems approach to neurostimulation therapy of epilepsy allows designing stimulation strategies that consider the patient's seizure dynamics and long-term fluctuations in the stability of their epileptic networks. In this article, we review, in a nontechnical fashion suitable for a broad neuroscientific audience, recent progress in personalized dynamic brain network modeling that is shaping the future approach to the diagnosis and treatment of epilepsy.

Quantitative approaches to guide epilepsy surgery from intracranial EEG

Over the past 10 years, the drive to improve outcomes from epilepsy surgery has stimulated widespread interest in methods to quantitatively guide epilepsy surgery from intracranial EEG (iEEG). Many patients fail to achieve seizure freedom, in part due to the challenges in subjective iEEG interpretation. To address this clinical need, quantitative iEEG analytics have been developed using a variety of approaches, spanning studies of seizures, interictal periods, and their transitions, and encompass a range of techniques including electrographic signal analysis, dynamical systems modeling, machine learning and graph theory. Unfortunately, many methods fail to generalize to new data and are sensitive to differences in pathology and electrode placement. Here, we critically review selected literature on computational methods of identifying the epileptogenic zone from iEEG. We highlight shared methodological challenges common to many studies in this field and propose ways that they can be addressed. One fundamental common pitfall is a lack of open-source, high-quality data, which we specifically address by sharing a centralized high-quality, well-annotated, multicentre dataset consisting of >100 patients to support larger and more rigorous studies. Ultimately, we provide a road map to help these tools reach clinical trials and hope to improve the lives of future patients.

General and patient-specific seizure classification using deep neural networks

Seizure prediction algorithms have been central in the field of data analysis for the improvement of epileptic patients’ lives. The most recent advancements of which include the use of deep neural networks to present an optimized, accurate seizure prediction system. This work puts forth deep learning methods to automate the process of epileptic seizure detection with electroencephalogram (EEG) signals as input; both a patient-specific and general approach are followed. EEG signals are time structure series motivating the use of sequence algorithms such as temporal convolutional neural networks (TCNNs), and long short-term memory networks. We then compare this methodology to other prior pre-implemented structures, including our previous work for seizure prediction using machine learning approaches support vector machine and random under-sampling boost. Moreover, patient-specific and general seizure prediction approaches are used to evaluate the performance of the best algorithms. Area under curve (AUC) is used to select the best performing algorithm to account for the imbalanced dataset. The presented TCNN model showed the best patient-specific results than that of the general approach with, AUC of 0.73, while ML model had the best results for general classification with AUC of 0.75.

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

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

Epileptic-network-based prediction and control of seizures in humans

Epilepsy is now conceptualized as a network disease. The epileptic brain network comprises structurally and functionally connected cortical and subcortical brain regions - spanning lobes and hemispheres -, whose connections and dynamics evolve in time. With this concept, focal and generalized seizures as well as other related pathophysiological phenomena are thought to emerge from, spread via, and be terminated by network vertices and edges that also generate and sustain normal, physiological brain dynamics. Research over the last years has advanced concepts and techniques to identify and characterize the evolving epileptic brain network and its constituents on various spatial and temporal scales. Network-based approaches further our understanding of how seizures emerge from the evolving epileptic brain network, and they provide both novel insights into pre-seizure dynamics and important clues for success or failure of measures for network-based seizure control and prevention. In this review, we summarize the current state of knowledge and address several important challenges that would need to be addressed to move network-based prediction and control of seizures closer to clinical translation.

EEG datasets for seizure detection and prediction- A review

Electroencephalogram (EEG) datasets from epilepsy patients have been used to develop seizure detection and prediction algorithms using machine learning (ML) techniques with the aim of implementing the learned model in a device. However, the format and structure of publicly available datasets are different from each other, and there is a lack of guidelines on the use of these datasets. This impacts the generatability, generalizability, and reproducibility of the results and findings produced by the studies. In this narrative review, we compiled and compared the different characteristics of the publicly available EEG datasets that are commonly used to develop seizure detection and prediction algorithms. We investigated the advantages and limitations of the characteristics of the EEG datasets. Based on our study, we identified 17 characteristics that make the EEG datasets unique from each other. We also briefly looked into how certain characteristics of the publicly available datasets affect the performance and outcome of a study, as well as the influences it has on the choice of ML techniques and preprocessing steps required to develop seizure detection and prediction algorithms. In conclusion, this study provides a guideline on the choice of publicly available EEG datasets to both clinicians and scientists working to develop a reproducible, generalizable, and effective seizure detection and prediction algorithm.

Diverse nature of interictal oscillations: EEG-based biomarkers in epilepsy

Interictal electroencephalogram (EEG) patterns, including high-frequency oscillations (HFOs), interictal spikes (ISs), and slow wave activities (SWAs), are defined as specific oscillations between seizure events. These interictal oscillations reflect specific dynamic changes in network excitability and play various roles in epilepsy. In this review, we briefly describe the electrographic characteristics of HFOs, ISs, and SWAs in the interictal state, and discuss the underlying cellular and network mechanisms. We also summarize representative evidence from experimental and clinical epilepsy to address their critical roles in ictogenesis and epileptogenesis, indicating their potential as electrophysiological biomarkers of epilepsy. Importantly, we put forwards some perspectives for further research in the field.

Closed-Loop Neuromodulation and Self-Perception in Clinical Treatment of Refractory Epilepsy

Background: Newer "closed-loop" neurostimulation devices in development could, in theory, induce changes to patients' personalities and self-perceptions. Empirically, however, only limited data of patient and family experiences exist. Responsive neurostimulation (RNS) as a treatment for refractory epilepsy is the first approved and commercially available closed-loop brain stimulation system in clinical practice, presenting an opportunity to observe how conceptual neuroethical concerns manifest in clinical treatment.Methods: We conducted ethnographic research at a single academic medical center with an active RNS treatment program and collected data via direct observation of clinic visits and in-depth interviews with 12 patients and their caregivers. We used deductive and inductive analyses to identify the relationship between these devices and patient changes in personality and self-perception.Results: Participants generally did not attribute changes in patients' personalities or self-perception to implantation of or stimulation using RNS. They did report that RNS affected patients' experiences and conceptions of illness. In particular, the capacity to store and display electrophysiological data produced a common frame of reference and a shared vocabulary among patients and clinicians.Discussion: Empirical experiences of a clinical population being treated with closed-loop neuromodulation do not corroborate theoretical concerns about RNS devices described by neuroethicists and technology developers. However, closed-loop devices demonstrated an ability to change illness experiences. Even without altering identify and self-perception, they provided new cultural tools and metaphors for conceiving of epilepsy as an illness and of the process of diagnosis and treatment. These findings call attention to the need to situate neuroethical concerns in the broader contexts of patients' illness experiences and social circumstances.

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

Introduction

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

Methods

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

Results

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

Discussion

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

Animal models for epileptic foci localization, seizure detection, and prediction by electrical impedance tomography

Surgical resection of lesions and closed-loop suppression are the two main treatment options for patients with refractory epilepsy whose symptoms cannot be managed with medicines. Unfortunately, failures in foci localization and seizure prediction are constraining these treatments. Electrical impedance tomography (EIT), sensitive to impedance changes caused by blood flow or cell swelling, is a potential new way to locate epileptic foci and predict seizures. Animal validation is a necessary research process before EIT can be used in clinical practice, but it is unclear which among the many animal epilepsy models is most suited to this task. The selection of an animal model of epilepsy that is similar to human seizures and can be adapted to EIT is important for the accuracy and reliability of EIT research results. This study provides an overview of the animal models of epilepsy that have been used in research on the use of EIT to locate the foci or predict seizures; discusses the advantages and disadvantages of these models regarding inducement by chemical convulsant and electrical stimulation; and finally proposes optimal animal models of epilepsy to obtain more convincing research results for foci localization and seizure prediction by EIT. The ultimate goal of this study is to facilitate the development of new treatments for patients with refractory epilepsy. This article is categorized under: Neuroscience > Clinical Neuroscience Psychology > Brain Function and Dysfunction.

Effective Evaluation of Medical Images Using Artificial Intelligence Techniques

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

Weak self-supervised learning for seizure forecasting: a feasibility study

This paper proposes an artificial intelligence system that continuously improves over time at event prediction using initially unlabelled data by using self-supervised learning. Time-series data are inherently autocorrelated. By using a detection model to generate weak labels on the fly, which are concurrently used as targets to train a prediction model on a time-shifted input data stream, this autocorrelation can effectively be harnessed to reduce the burden of manual labelling. This is critical in medical patient monitoring, as it enables the development of personalized forecasting models without demanding the annotation of long sequences of physiological signal recordings. We perform a feasibility study on seizure prediction, which is identified as an ideal test case, as pre-ictal brainwaves are patient-specific, and tailoring models to individual patients is known to improve forecasting performance significantly. Our self-supervised approach is used to train individualized forecasting models for 10 patients, showing an average relative improvement in sensitivity by 14.30% and a reduction in false alarms by 19.61% in early seizure forecasting. This proof-of-concept on the feasibility of using a continuous stream of time-series neurophysiological data paves the way towards a low-power neuromorphic neuromodulation system.

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.

On the clinical acceptance of black-box systems for EEG seizure prediction

Seizure prediction may be the solution for epileptic patients whose drugs and surgery do not control seizures. Despite 46 years of research, few devices/systems underwent clinical trials and/or are commercialized, where the most recent state-of-the-art approaches, as neural networks models, are not used to their full potential. The latter demonstrates the existence of social barriers to new methodologies due to data bias, patient safety, and legislation compliance. In the form of literature review, we performed a qualitative study to analyze the seizure prediction ecosystem to find these social barriers. With the Grounded Theory, we draw hypotheses from data, while with the Actor-Network Theory we considered that technology shapes social configurations and interests, being fundamental in healthcare. We obtained a social network that describes the ecosystem and propose research guidelines aiming at clinical acceptance. Our most relevant conclusion is the need for model explainability, but not necessarily intrinsically interpretable models, for the case of seizure prediction. Accordingly, we argue that it is possible to develop robust prediction models, including black-box systems to some extent, while avoiding data bias, ensuring patient safety, and still complying with legislation, if they can deliver human- comprehensible explanations. Due to skepticism and patient safety reasons, many authors advocate the use of transparent models which may limit their performance and potential. Our study highlights a possible path, by using model explainability, on how to overcome these barriers while allowing the use of more computationally robust models.

Interpretable EEG seizure prediction using a multiobjective evolutionary algorithm

Seizure prediction might be the solution to tackle the apparent unpredictability of seizures in patients with drug-resistant epilepsy, which comprise about a third of all patients with epilepsy. Designing seizure prediction models involves defining the pre-ictal period, a transition stage between inter-ictal brain activity and the seizure discharge. This period is typically a fixed interval, with some recent studies reporting the evaluation of different patient-specific pre-ictal intervals. Recently, researchers have aimed to determine the pre-ictal period, a transition stage between regular brain activity and a seizure. Authors have been using deep learning models given the ability of such models to automatically perform pre-processing, feature extraction, classification, and handling temporal and spatial dependencies. As these approaches create black-box models, clinicians may not have sufficient trust to use them in high-stake decisions. By considering these problems, we developed an evolutionary seizure prediction model that identifies the best set of features while automatically searching for the pre-ictal period and accounting for patient comfort. This methodology provides patient-specific interpretable insights, which might contribute to a better understanding of seizure generation processes and explain the algorithm's decisions. We tested our methodology on 238 seizures and 3687 h of continuous data, recorded on scalp recordings from 93 patients with several types of focal and generalised epilepsies. We compared the results with a seizure surrogate predictor and obtained a performance above chance for 32% patients. We also compared our results with a control method based on the standard machine learning pipeline (pre-processing, feature extraction, classifier training, and post-processing), where the control marginally outperformed our approach by validating 35% of the patients. In total, 54 patients performed above chance for at least one method: our methodology or the control one. Of these 54 patients, 21 ([Formula: see text]38%) were solely validated by our methodology, while 24 ([Formula: see text]44%) were only validated by the control method. These findings may evidence the need for different methodologies concerning different patients.

A novel consistency-based training strategy for seizure prediction

BACKGROUND

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 for its outstanding performance. With the aim of predicting unseen seizures, it is essential to guarantee the generalization ability of the model, especially considering the non-stationary nature of EEG and the scarcity of seizure events in EEG recordings. Stability training against extra perturbations is an intuitive and effective way to improve the model's ability to generalize. Though a great number of deep learning methods have been developed for seizure prediction, their strategies to increase generalization performance focus on improving the model's architecture itself, and few of them pay attention to the stability of the model against small perturbations.

NEW METHOD

In this study, we propose a novel consistency-based training strategy to address this issue. The proposed strategy underlines that a robust model should maintain consistent results for the same input under extra perturbations. Specifically, during training, we use stochastic augmentations to make the input vary from iteration to iteration and consider the output as a stochastic variable. Then a consistency constraint is constructed to penalize the difference between the current output and previous outputs. In this way, the generalization ability of the model will be fully enhanced.

RESULTS

To better verify the effectiveness of our proposed strategy, we implement it in two state-of-the-art models with public-available codes, including STFT CNN and Multi-view CNN. Notably, we compare with the first baseline on a scalp EEG dataset and the other on an intracranial EEG dataset. The results show that our strategy could improve the performance significantly for both of them.

COMPARISON WITH EXISTING METHODS

Our strategy has increased the sensitivity by 7.1% and reduced the false prediction rate by 0.12/h on the first baseline while improving the AUC by 0.020 on the second baseline.

CONCLUSIONS

This study is easy to implement, providing a new solution to enhance the performance of seizure prediction.

Temporally Targeted Interactions With Pathologic Oscillations as Therapeutical Targets in Epilepsy and Beyond

Self-organized neuronal oscillations rely on precisely orchestrated ensemble activity in reverberating neuronal networks. Chronic, non-malignant disorders of the brain are often coupled to pathological neuronal activity patterns. In addition to the characteristic behavioral symptoms, these disturbances are giving rise to both transient and persistent changes of various brain rhythms. Increasing evidence support the causal role of these "oscillopathies" in the phenotypic emergence of the disease symptoms, identifying neuronal network oscillations as potential therapeutic targets. While the kinetics of pharmacological therapy is not suitable to compensate the disease related fine-scale disturbances of network oscillations, external biophysical modalities (e.g., electrical stimulation) can alter spike timing in a temporally precise manner. These perturbations can warp rhythmic oscillatory patterns via resonance or entrainment. Properly timed phasic stimuli can even switch between the stable states of networks acting as multistable oscillators, substantially changing the emergent oscillatory patterns. Novel transcranial electric stimulation (TES) approaches offer more reliable neuronal control by allowing higher intensities with tolerable side-effect profiles. This precise temporal steerability combined with the non- or minimally invasive nature of these novel TES interventions make them promising therapeutic candidates for functional disorders of the brain. Here we review the key experimental findings and theoretical background concerning various pathological aspects of neuronal network activity leading to the generation of epileptic seizures. The conceptual and practical state of the art of temporally targeted brain stimulation is discussed focusing on the prevention and early termination of epileptic seizures.

Coherent false seizure prediction in epilepsy, coincidence or providence?

OBJECTIVE

Seizure forecasting using machine learning is possible, but the performance is far from ideal, as indicated by many false predictions and low specificity. Here, we examine false and missing alarms of two algorithms on long-term datasets to show that the limitations are less related to classifiers or features, but rather to intrinsic changes in the data.

METHODS

We evaluated two algorithms on three datasets by computing the correlation of false predictions and estimating the information transfer between both classification methods.

RESULTS

For 9 out of 12 individuals both methods showed a performance better than chance. For all individuals we observed a positive correlation in predictions. For individuals with strong correlation in false predictions we were able to boost the performance of one method by excluding test samples based on the results of the second method.

CONCLUSIONS

Substantially different algorithms exhibit a highly consistent performance and a strong coherency in false and missing alarms. Hence, changing the underlying hypothesis of a preictal state of fixed time length prior to each seizure to a proictal state is more helpful than further optimizing classifiers.

SIGNIFICANCE

The outcome is significant for the evaluation of seizure prediction algorithms on continuous data.

Online Prediction of Lead Seizures from iEEG Data

We describe a novel system for online prediction of lead seizures from long-term intracranial electroencephalogram (iEEG) recordings for canines with naturally occurring epilepsy. This study adopts new specification of lead seizures, reflecting strong clustering of seizures in observed data. This clustering results in fewer lead seizures (~7 lead seizures per dog), and hence new challenges for online seizure prediction, that are addressed in the proposed system. In particular, the machine learning part of the system is implemented using the group learning method suitable for modeling sparse and noisy seizure data. In addition, several modifications for the proposed system are introduced to cope with the non-stationarity of a noisy iEEG signal. They include: (1) periodic retraining of the SVM classifier using most recent training data; (2) removing samples with noisy labels from training data; and (3) introducing a new adaptive post-processing technique for combining many predictions made for 20 s windows into a single prediction for a 4 h segment. Application of the proposed system requires only two lead seizures for training the initial model, and results in high prediction performance for all four dogs (with mean 0.84 sensitivity, 0.27 time-in-warning, and 0.78 false-positive rate per day). The proposed system achieves accurate prediction of lead seizures during long-term test periods, 3–16 lead seizures during a 169–364 day test period, whereas earlier studies did not differentiate between lead vs. non-lead seizures and used much shorter test periods (~few days long).

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.

Epileptic Seizure Prediction Using Deep Transformer Model

The electroencephalogram (EEG) is the most promising and efficient technique to study epilepsy and record all the electrical activity going in our brain. Automated screening of epilepsy through data-driven algorithms reduces the manual workload of doctors to diagnose epilepsy. New algorithms are biased either towards signal processing or deep learning, which holds subjective advantages and disadvantages. The proposed pipeline is an end-to-end automated seizure prediction framework with a Fourier transform feature extraction and deep learning-based transformer model, a blend of signal processing and deep learning - this imbibes the potential features to automatically identify the attentive regions in EEG signals for effective screening. The proposed pipeline has demonstrated superior performance on the benchmark dataset with average sensitivity and false-positive rate per hour (FPR/h) as 98.46%, 94.83% and 0.12439, 0, respectively. The proposed work shows great results on the benchmark datasets and a big potential for clinics as a support system with medical experts monitoring the patients.

Prediction of Seizure Recurrence. A Note of Caution

Great strides have been made recently in documenting that machine-learning programs can predict seizure occurrence in people who have epilepsy. Along with this progress have come claims that appear to us to be a bit premature. We anticipate that many people will benefit from seizure prediction. We also doubt that all will benefit. Although machine learning is a useful tool for aiding discovery, we believe that the greatest progress will come from deeper understanding of seizures, epilepsy, and the EEG features that enable seizure prediction. In this essay, we lay out reasons for optimism and skepticism.

A sparse multiscale nonlinear autoregressive model for seizure prediction

Objectives.Accurate seizure prediction is highly desirable for medical interventions such as responsive electrical stimulation. We aim to develop a classification model that can predict seizures by identifying preictal states, i.e. the precursor of a seizure, based on multi-channel intracranial electroencephalography (iEEG) signals.Approach.A two-level sparse multiscale classification model was developed to classify interictal and preictal states from iEEG data. In the first level, short time-scale linear dynamical features were extracted as autoregressive (AR) model coefficients; arbitrary (usually long) time-scale linear and nonlinear dynamical features were extracted as Laguerre-Volterra AR model coefficients; root-mean-square error of model prediction was used as a feature representing model unpredictability. In the second level, all features were fed into a sparse classifier to discriminate the iEEG data between interictal and preictal states.Main results. The two-level model can accurately classify seizure states using iEEG data recorded from ten canine and human subjects. Adding arbitrary (usually long) time-scale and nonlinear features significantly improves model performance compared with the conventional AR modeling approach. There is a high degree of variability in the types of features contributing to seizure prediction across different subjects.Significance. This study suggests that seizure generation may involve distinct linear/nonlinear dynamical processes caused by different underlying neurobiological mechanisms. It is necessary to build patient-specific classification models with a wide range of dynamical features.

A hybrid deep neural network for classification of schizophrenia using EEG Data

Schizophrenia is a serious mental illness that causes great harm to patients, so timely and accurate detection is essential. This study aimed to identify a better feature to represent electroencephalography (EEG) signals and improve the classification accuracy of patients with schizophrenia and healthy controls by using EEG signals. Our research method involves two steps. First, the EEG time series is preprocessed, and the extracted time-domain and frequency-domain features are transformed into a sequence of red-green-blue (RGB) images that carry spatial information. Second, we construct hybrid deep neural networks (DNNs) that combine convolution neural networks and long short-term memory to address RGB images to classify schizophrenic patients and healthy controls. The results show that the fuzzy entropy (FuzzyEn) feature is more significant than the fast Fourier transform (FFT) feature in brain topography. The deep learning (DL) method that we propose achieves an average accuracy of 99.22% with FuzzyEn and an average accuracy of 96.34% with FFT. These results show that the best effect is to extract fuzzy features as input features from EEG time series and then use a hybrid DNN for classification. Compared with the most advanced methods in this field, significant improvements have been achieved.

A Study of EEG Feature Complexity in Epileptic Seizure Prediction

The purpose of this study is (1) to provide EEG feature complexity analysis in seizure prediction by inter-ictal and pre-ital data classification and, (2) to assess the between-subject variability of the considered features. In the past several decades, there has been a sustained interest in predicting epilepsy seizure using EEG data. Most methods classify features extracted from EEG, which they assume are characteristic of the presence of an epilepsy episode, for instance, by distinguishing a pre-ictal interval of data (which is in a given window just before the onset of a seizure) from inter-ictal (which is in preceding windows following the seizure). To evaluate the difficulty of this classification problem independently of the classification model, we investigate the complexity of an exhaustive list of 88 features using various complexity metrics, i.e., the Fisher discriminant ratio, the volume of overlap, and the individual feature efficiency. Complexity measurements on real and synthetic data testbeds reveal that that seizure prediction by pre-ictal/inter-ictal feature distinction is a problem of significant complexity. It shows that several features are clearly useful, without decidedly identifying an optimal set.

Viability of Preictal High-Frequency Oscillation Rates as a Biomarker for Seizure Prediction

Motivation: There is an ongoing search for definitive and reliable biomarkers to forecast or predict imminent seizure onset, but to date most research has been limited to EEG with sampling rates <1,000 Hz. High-frequency oscillations (HFOs) have gained acceptance as an indicator of epileptic tissue, but few have investigated the temporal properties of HFOs or their potential role as a predictor in seizure prediction. Here we evaluate time-varying trends in preictal HFO rates as a potential biomarker of seizure prediction. Methods: HFOs were identified for all interictal and preictal periods with a validated automated detector in 27 patients who underwent intracranial EEG monitoring. We used LASSO logistic regression with several features of the HFO rate to distinguish preictal from interictal periods in each individual. We then tested these models with held-out data and evaluated their performance with the area-under-the-curve (AUC) of their receiver-operating curve (ROC). Finally, we assessed the significance of these results using non-parametric statistical tests. Results: There was variability in the ability of HFOs to discern preictal from interictal states across our cohort. We identified a subset of 10 patients in whom the presence of the preictal state could be successfully predicted better than chance. For some of these individuals, average AUC in the held-out data reached higher than 0.80, which suggests that HFO rates can significantly differentiate preictal and interictal periods for certain patients. Significance: These findings show that temporal trends in HFO rate can predict the preictal state better than random chance in some individuals. Such promising results indicate that future prediction efforts would benefit from the inclusion of high-frequency information in their predictive models and technological architecture.

Machine Learning for Predicting Epileptic Seizures Using EEG Signals: A Review

With the advancement in artificial intelligence (AI) and machine learning (ML) techniques, researchers are striving towards employing these techniques for advancing clinical practice. One of the key objectives in healthcare is the early detection and prediction of disease to timely provide preventive interventions. This is especially the case for epilepsy, which is characterized by recurrent and unpredictable seizures. Patients can be relieved from the adverse consequences of epileptic seizures if it could somehow be predicted in advance. Despite decades of research, seizure prediction remains an unsolved problem. This is likely to remain at least partly because of the inadequate amount of data to resolve the problem. There have been exciting new developments in ML-based algorithms that have the potential to deliver a paradigm shift in the early and accurate prediction of epileptic seizures. Here we provide a comprehensive review of state-of-the-art ML techniques in early prediction of seizures using EEG signals. We will identify the gaps, challenges, and pitfalls in the current research and recommend future directions.

Clinical and experimental insight into pathophysiology, comorbidity and therapy of absence seizures

Absence seizures in children and teenagers are generally considered relatively benign because of their non-convulsive nature and the large incidence of remittance in early adulthood. Recent studies, however, show that 30% of children with absence seizures are pharmaco-resistant and 60% are affected by severe neuropsychiatric comorbid conditions, including impairments in attention, cognition, memory and mood. In particular, attention deficits can be detected before the epilepsy diagnosis, may persist even when seizures are pharmacologically controlled and are aggravated by valproic acid monotherapy. New functional MRI-magnetoencephalography and functional MRI-EEG studies provide conclusive evidence that changes in blood oxygenation level-dependent signal amplitude and frequency in children with absence seizures can be detected in specific cortical networks at least 1 min before the start of a seizure, spike-wave discharges are not generalized at seizure onset and abnormal cortical network states remain during interictal periods. From a neurobiological perspective, recent electrical recordings and imaging of large neuronal ensembles with single-cell resolution in non-anaesthetized models show that, in contrast to the predominant opinion, cortical mechanisms, rather than an exclusively thalamic rhythmogenesis, are key in driving seizure ictogenesis and determining spike-wave frequency. Though synchronous ictal firing characterizes cortical and thalamic activity at the population level, individual cortico-thalamic and thalamocortical neurons are sparsely recruited to successive seizures and consecutive paroxysmal cycles within a seizure. New evidence strengthens previous findings on the essential role for basal ganglia networks in absence seizures, in particular the ictal increase in firing of substantia nigra GABAergic neurons. Thus, a key feature of thalamic ictogenesis is the powerful increase in the inhibition of thalamocortical neurons that originates at least from two sources, substantia nigra and thalamic reticular nucleus. This undoubtedly provides a major contribution to the ictal decrease in total firing and the ictal increase of T-type calcium channel-mediated burst firing of thalamocortical neurons, though the latter is not essential for seizure expression. Moreover, in some children and animal models with absence seizures, the ictal increase in thalamic inhibition is enhanced by the loss-of-function of the astrocytic GABA transporter GAT-1 that does not necessarily derive from a mutation in its gene. Together, these novel clinical and experimental findings bring about paradigm-shifting views of our understanding of absence seizures and demand careful choice of initial monotherapy and continuous neuropsychiatric evaluation of affected children. These issues are discussed here to focus future clinical and experimental research and help to identify novel therapeutic targets for treating both absence seizures and their comorbidities.

Deep Convolutional Neural Network Based Interictal-Preictal Electroencephalography Prediction: Application to Focal Cortical Dysplasia Type-II

We aimed to differentiate between the interictal and preictal states in epilepsy patients with focal cortical dysplasia (FCD) type-II using deep learning-based classifiers based on intracranial electroencephalography (EEG). We also investigated the practical conditions for high interictal-preictal discriminability in terms of spatiotemporal EEG characteristics and data size efficiency. Intracranial EEG recordings of nine epilepsy patients with FCD type-II (four female, five male; mean age: 10.7 years) were analyzed. Seizure onset and channel ranking were annotated by two epileptologists. We performed three consecutive interictal-preictal classification steps by varying the preictal length, number of electrodes, and sampling frequency with convolutional neural networks (CNN) using 30 s time-frequency data matrices. Classification performances were evaluated based on accuracy, F1 score, precision, and recall with respect to the above-mentioned three parameters. We found that (1) a 5 min preictal length provided the best classification performance, showing a remarkable enhancement of >13% on average compared to that with the 120 min preictal length; (2) four electrodes provided considerably high classification performance with a decrease of only approximately 1% on average compared to that with all channels; and (3) there was minimal performance change when quadrupling the sampling frequency from 128 Hz. Patient-specific performance variations were noticeable with respect to the preictal length, and three patients showed above-average performance enhancements of >28%. However, performance enhancements were low with respect to both the number of electrodes and sampling frequencies, and some patients showed at most 1–2% performance change. CNN-based classifiers from intracranial EEG recordings using a small number of electrodes and efficient sampling frequency are feasible for predicting the interictal-preictal state transition preceding seizures in epilepsy patients with FCD type-II. Preictal lengths affect the predictability in a patient-specific manner; therefore, pre-examinations for optimal preictal length will be helpful in seizure prediction.

From Seizure Detection to Smart and Fully Embedded Seizure Prediction Engine: A Review

Recent review papers have investigated seizure prediction, creating the possibility of preempting epileptic seizures. Correct seizure prediction can significantly improve the standard of living for the majority of epileptic patients, as the unpredictability of seizures is a major concern for them. Today, the development of algorithms, particularly in the field of machine learning, enables reliable and accurate seizure prediction using desktop computers. However, despite extensive research effort being devoted to developing seizure detection integrated circuits (ICs), dedicated seizure prediction ICs have not been developed yet. We believe that interdisciplinary study of system architecture, analog and digital ICs, and machine learning algorithms can promote the translation of scientific theory to a more realistic intelligent, integrated, and low-power system that can truly improve the standard of living for epileptic patients. This review explores topics ranging from signal acquisition analog circuits to classification algorithms and dedicated digital signal processing circuits for detection and prediction purposes, to provide a comprehensive and useful guideline for the construction, implementation and optimization of wearable and integrated smart seizure prediction systems.

Performance metrics for online seizure prediction

Many recent studies on online seizure prediction from iEEG signal describe various prediction algorithms and their prediction performance. In contrast, this paper focuses on proper specification of system parameters, such as prediction period, prediction horizon and data-driven characterization of lead seizures. Whereas prediction performance clearly depends on these system parameters many researchers simply set the values of these parameters in an ad hoc manner. Our paper investigates the effect of these system parameters on online prediction performance, using both synthetic and real-life data sets. Therefore, meaningful comparison of methods/algorithms (for online seizure prediction) should consider proper specification of system parameters.

Machine learning and wearable devices of the future

Machine learning (ML) is increasingly recognized as a useful tool in healthcare applications, including epilepsy. One of the most important applications of ML in epilepsy is seizure detection and prediction, using wearable devices (WDs). However, not all currently available algorithms implemented in WDs are using ML. In this review, we summarize the state of the art of using WDs and ML in epilepsy, and we outline future development in these domains. There is published evidence for reliable detection of epileptic seizures using implanted electroencephalography (EEG) electrodes and wearable, non-EEG devices. Application of ML using the data recorded with WDs from a large number of patients could change radically the way we diagnose and manage patients with epilepsy.

Seizure forecasting and cyclic control of seizures

Epilepsy is a unique neurologic condition characterized by recurrent seizures, where causes, underlying biomarkers, triggers, and patterns differ across individuals. The unpredictability of seizures can heighten fear and anxiety in people with epilepsy, making it difficult to take part in day-to-day activities. Epilepsy researchers have prioritized developing seizure prediction algorithms to combat episodic seizures for decades, but the utility and effectiveness of prediction algorithms has not been investigated thoroughly in clinical settings. In contrast, seizure forecasts, which theoretically provide the probability of a seizure at any time (as opposed to predicting the next seizure occurrence), may be more feasible. Many advances have been made over the past decade in the field of seizure forecasting, including improvements in algorithms as a result of machine learning and exploration of non-EEG-based measures of seizure susceptibility, such as physiological biomarkers, behavioral changes, environmental drivers, and cyclic seizure patterns. For example, recent work investigating periodicities in individual seizure patterns has determined that more than 90% of people have circadian rhythms in their seizures, and many also experience multiday, weekly, or longer cycles. Other potential indicators of seizure susceptibility include stress levels, heart rate, and sleep quality, all of which have the potential to be captured noninvasively over long time scales. There are many possible applications of a seizure-forecasting device, including improving quality of life for people with epilepsy, guiding treatment plans and medication titration, optimizing presurgical monitoring, and focusing scientific research. To realize this potential, it is vital to better understand the user requirements of a seizure-forecasting device, continue to advance forecasting algorithms, and design clear guidelines for prospective clinical trials of seizure forecasting.

Epileptic Seizure Detection and Experimental Treatment: A Review

One-fourths of the patients have medication-resistant seizures and require seizure detection and treatment continuously to cope with sudden seizures. Seizures can be detected by monitoring the brain and muscle activities, heart rate, oxygen level, artificial sounds, or visual signatures through EEG, EMG, ECG, motion, or audio/video recording on the human head and body. In this article, we first discuss recent advances in seizure sensing, signal processing, time- or frequency-domain analysis, and classification algorithms to detect and classify seizure stages. Then, we show a strong potential of applying recent advancements in non-invasive brain stimulation technology to treat seizures. In particular, we explain the fundamentals of brain stimulation approaches, including (1) transcranial magnetic stimulation (TMS), (2) transcranial direct current stimulation (tDCS), (3) transcranial focused ultrasound stimulation (tFUS), and how to use them to treat seizures. Through this review, we intend to provide a broad view of both recent seizure diagnoses and treatments. Such knowledge would help fresh and experienced researchers to capture the advancements in sensing, detection, classification, and treatment seizures. Last but not least, we provide potential research directions that would attract seizure researchers/engineers in the field.

EEG Synchronization Analysis for Seizure Prediction: A Study on Data of Noninvasive Recordings

Objective: Epilepsy is a neurological disorder arising from anomalies of the electrical activity in the brain, affecting ~65 million individuals worldwide. Prediction methods, typically based on machine learning methods, require a large amount of data for training, in order to correctly classify seizures with small false alarm rates. Methods: In this work, we present a new database containing EEG scalp signals of 14 epileptic patients acquired at the Unit of Neurology and Neurophysiology of the University of Siena, Italy. Furthermore, a patient-specific seizure prediction method, based on the detection of synchronization patterns in the EEG, is proposed and tested on the data of the database. The use of noninvasive EEG data aims to explore the possibility of developing a noninvasive monitoring/control device for the prediction of seizures. The prediction method employs synchronization measures computed over all channel pairs and a computationally inexpensive threshold-based classification approach. Results and conclusions: The experimental analysis, performed by inspection and by the proposed threshold-based classifier on all the patients of the database, shows that the features extracted by the synchronization measures are able to detect preictal and ictal states and allow the prediction of the seizures few minutes before the seizure onsets.

Real-time Inference and Detection of Disruptive EEG Networks for Epileptic Seizures

Recent studies in brain science and neurological medicine paid a particular attention to develop machine learning-based techniques for the detection and prediction of epileptic seizures with electroencephalogram (EEG). As a noninvasive monitoring method to record brain electrical activities, EEG has been widely used for capturing the underlying dynamics of disruptive neuronal responses across the brain in real-time to provide clinical guidance in support of epileptic seizure treatments in practice. In this study, we introduce a novel dynamic learning method that first infers a time-varying network constituted by multivariate EEG signals, which represents the overall dynamics of the brain network, and subsequently quantifies its topological property using graph theory. We demonstrate the efficacy of our learning method to detect relatively strong synchronization (characterized by the algebraic connectivity metric) caused by abnormal neuronal firing during a seizure onset. The computational results for a realistic scalp EEG database show a detection rate of 93.6% and a false positive rate of 0.16 per hour (FP/h); furthermore, our method observes potential pre-seizure phenomena in some cases.

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.

Prevention of sudden unexpected death in epilepsy: current status and future perspectives

Introduction: Sudden unexpected death in epilepsy (SUDEP) affects about 1 in 1000 people with epilepsy, and even more in medically refractory epilepsy. As most people are between 20 and 40 years when dying suddenly, SUDEP leads to a considerable loss of potential life years. The most important risk factors are nocturnal and tonic-clonic seizures, underscoring that supervision and effective seizure control are key elements for SUDEP prevention. The question of whether specific antiepileptic drugs are linked to SUDEP is still controversially discussed. Knowledge and education about SUDEP among health-care professionals, patients, and relatives are of outstanding importance for preventive measures to be taken, but still poor and widely neglected.Areas covered: This article reviews epidemiology, pathophysiology, risk factors, assessment of individual SUDEP risk and available measures for SUDEP prevention. Literature search was done using Medline and Pubmed in October 2019.Expert opinion: Significant advances in the understanding of SUDEP were made in the last decade which allow testing of novel strategies to prevent SUDEP. Promising current strategies target neuronal mechanisms of brain stem dysfunction, cardiac susceptibility for fatal arrhythmias, and reliable detection of tonic-clonic seizures using mobile health technologies.Abbreviations: AED, antiepileptic drug; CBZ, carbamazepine; cLQTS, congenital long QT syndrome; EMU, epilepsy monitoring unit; FBTCS, focal to bilateral tonic-clonic seizures; GTCS, generalized tonic-clonic seizures; ICA, ictal central apnea; LTG, lamotrigine; PCCA, postconvulsive central apnea; PGES, postictal generalized EEG suppression; SRI, serotonin reuptake inhibitor; SUDEP, sudden unexpected death in epilepsy; TCS, tonic-clonic seizures.

Predicting epileptic seizures using nonnegative matrix factorization

This paper presents a procedure for the patient-specific prediction of epileptic seizures. To this end, a combination of nonnegative matrix factorization (NMF) and smooth basis functions with robust regression is applied to power spectra of intracranial electroencephalographic (iEEG) signals. The resulting time and frequency components capture the dominant information from power spectra, while removing outliers and noise. This makes it possible to detect structure in preictal states, which is used for classification. Linear support vector machines (SVM) with L1 regularization are used to select and weigh the contributions from different number of not equally informative channels among patients. Due to class imbalance in data, synthetic minority over-sampling technique (SMOTE) is applied. The resulting method yields a computationally and conceptually simple, interpretable model of EEG signals of preictal and interictal states, which shows a good performance for the task of seizure prediction on two datasets (the EPILEPSIAE and on the public Epilepsyecosystem dataset).

Seizure prediction and intervention

Epilepsy treatment is challenging due to a lack of essential diagnostic tools, including methods for reliable seizure detection in the ambulatory setting, to assess seizure risk over time and to monitor treatment efficacy. This lack of objective diagnostics constitutes a significant barrier to better treatments, raises methodological concerns about the antiseizure medication evaluation process and, to patients, is a main issue contributing to the disease burden. Recent years have seen rapid progress towards better diagnostics that meet these needs of epilepsy patients and clinicians. Availability of comprehensive data and the rise of more powerful computational analysis methods have driven progress in this area. Here, we provide an overview on data- and theory-driven approaches aimed at identifying methods to reliably detect and forecast seizures as well as to monitor brain excitability and treatment efficacy in epilepsy. We provide a particular account on neural criticality, the hypothesis that cortical networks may be poised in a critical state at the boundary between different types of dynamics, and discuss its role in informing diagnostics to track cortex excitability and seizure risk in recent experiments. With the further expansion of digitalization in medicine, tele-medicine and long-term, ambulatory monitoring, these computationally based methods may gain more relevance in epilepsy in the future. This article is part of the special issue entitled 'New Epilepsy Therapies for the 21st Century - From Antiseizure Drugs to Prevention, Modification and Cure of Epilepsy'.

A Resource-Optimized VLSI Implementation of a Patient-Specific Seizure Detection Algorithm on a Custom-Made 2.2 cm 2 Wireless Device for Ambulatory Epilepsy Diagnostics

A patient-specific epilepsy diagnostic solution in the form of a wireless wearable ambulatory device is presented. First, the design, VLSI implementation, and experimental validation of a resource-optimized machine learning algorithm for epilepsy seizure detection are described. Next, the development of a mini-PCB that integrates a low-power wireless data transceiver and a programmable processor for hosting the seizure detection algorithm is discussed. The algorithm uses only EEG signals from the frontal lobe electrodes while yielding a seizure detection sensitivity and specificity competitive to the standard full EEG systems. The experimental validation of the algorithm VLSI implementation proves the possibility of conducting accurate seizure detection using quickly-mountable dry-electrode headsets without the need for uncomfortable/painful through-hair electrodes or adhesive gels. Details of design and optimization of the algorithm, the VLSI implementation, and the mini-PCB development are presented and resource optimization techniques are discussed. The optimized implementation is uploaded on a low-power Microsemi Igloo FPGA, requires 1237 logic elements, consumes 110 μW dynamic power, and yields a minimum detection latency of 10.2 μs. The measurement results from the FPGA implementation on data from 23 patients (198 seizures in total) shows a seizure detection sensitivity and specificity of 92.5% and 80.1%, respectively. Comparison to the state of the art is presented from system integration, the VLSI implementation, and the wireless communication perspectives.