Search

Seizures produce autonomic symptoms, mainly sympathetic but also parasympathetic in origin. Within this context, the vagus nerve is a key player as it carries information from the different organs to the brain and vice versa. Hence, exploiting vagal neural traffic for seizure detection might be a promising tool to improve the efficacy of closed-loop Vagus Nerve Stimulation. This study developed a VENG detection algorithm that effectively detects seizures by emphasizing the loss of spontaneous rhythmicity associated with respiration in acute intrahippocampal Kainic Acid rat model. Among 20 induced seizures in six anesthetized rats, 13 were detected (sensitivity: 65%, accuracy: 92.86%), with a mean VENG-detection delay of 25.3 ± 13.5 s after EEG-based seizure onset. Despite variations in detection parameters, 7 out of 20 seizures exhibited no ictal VENG modifications and remained undetected. Statistical analysis highlighted a significant difference in Delta, Theta and Beta band evolution between detected and undetected seizures, in addition to variations in the magnitude of HR changes. Binomial logistic regression analysis confirmed that an increase in delta and theta band activity was associated with a decreased likelihood of seizure detection. This results suggest the possibility of distinct seizure spreading patterns between the two groups which may results in differential activation of the autonomic central network. Despite notable progress, limitations, particularly the absence of respiration recording, underscore areas for future exploration and refinement in closed-loop stimulation strategies for epilepsy management. This study constitutes the initial phase of a longitudinal investigation, which will subsequently involve reproducing these experiments in awake conditions with spontaneous recurrent seizures.

Abstract Epilepsy is a serious neurological disorder that results in seizures. It can be diagnosed by analyzing the brain's electrical activity using an electroencephalogram (EEG). However, the detection of seizures from massive EEG datasets is a challenging task. To address this challenge, researchers have developed several machine‐learning classifiers and feature extraction techniques for detecting seizures. This paper proposes an energy‐efficient and fast field programmable gate array (FPGA) architecture for detecting epileptic seizures using minimal computational resources. The seizure detection system uses the one Hjorth parameter (mobility) and another statistical parameter (nonlinear energy) as features and employs two efficient classifiers, quadratic discriminant analysis and linear support vector machine (LSVM), for classifying signals into seizure and nonseizure categories. The feature extractor block is connected individually to each of these classifiers. Subsequently, the performance of these two proposed models is evaluated in terms of accuracy, sensitivity, power consumption, resource utilization, and other metrics. The results demonstrate that the SVM classifier‐based model achieved the highest accuracy (99.4%) and sensitivity (98.8%) while consuming minimal dynamic power (0.057 mW) and utilizing the minimum FPGA resources. Thus, the proposed hardware system offers a reliable and energy‐efficient solution for detecting seizures in clinical and real‐time applications.

Background and objectiveEpilepsy, which is associated with neuronal damage and functional decline, typically presents patients with numerous challenges in their daily lives. An early diagnosis plays a crucial role in managing the condition and alleviating the patients’ suffering. Electroencephalogram (EEG)-based approaches are commonly employed for diagnosing epilepsy due to their effectiveness and non-invasiveness. In this study, a classification method is proposed that use fast Fourier Transform (FFT) extraction in conjunction with convolutional neural networks (CNN) and long short-term memory (LSTM) models.MethodsMost methods use traditional frameworks to classify epilepsy, we propose a new approach to this problem by extracting features from the source data and then feeding them into a network for training and recognition. It preprocesses the source data into training and validation data and then uses CNN and LSTM to classify the style of the data.ResultsUpon analyzing a public test dataset, the top-performing features in the fully CNN nested LSTM model for epilepsy classification are FFT features among three types of features. Notably, all conducted experiments yielded high accuracy rates, with values exceeding 96% for accuracy, 93% for sensitivity, and 96% for specificity. These results are further benchmarked against current methodologies, showcasing consistent and robust performance across all trials. Our approach consistently achieves an accuracy rate surpassing 97.00%, with values ranging from 97.95 to 99.83% in individual experiments. Particularly noteworthy is the superior accuracy of our method in the AB versus (vs.) CDE comparison, registering at 99.06%.ConclusionOur method exhibits precise classification abilities distinguishing between epileptic and non-epileptic individuals, irrespective of whether the participant’s eyes are closed or open. Furthermore, our technique shows remarkable performance in effectively categorizing epilepsy type, distinguishing between epileptic ictal and interictal states versus non-epileptic conditions. An inherent advantage of our automated classification approach is its capability to disregard EEG data acquired during states of eye closure or eye-opening. Such innovation holds promise for real-world applications, potentially aiding medical professionals in diagnosing epilepsy more efficiently.

IntroductionEpilepsy is a common neurological condition that affects a large number of individuals worldwide. One of the primary challenges in epilepsy is the accurate and timely detection of seizure. Recently, the graph regularized broad learning system (GBLS) has achieved superior performance improvement with its flat structure and less time-consuming training process compared to deep neural networks. Nevertheless, the number of feature and enhancement nodes in GBLS is predetermined. These node settings are also randomly selected and remain unchanged throughout the training process. The characteristic of randomness is thus more easier to make non-optimal nodes generate, which cannot contribute significantly to solving the optimization problem.MethodsTo obtain more optimal nodes for optimization and achieve superior automatic detection performance, we propose a novel broad neural network named self-adaptive evolutionary graph regularized broad learning system (SaE-GBLS). Self-adaptive evolutionary algorithm, which can construct mutation strategies in the strategy pool based on the experience of producing solutions for selecting network parameters, is incorporated into SaE-GBLS model for optimizing the node parameters. The epilepsy seizure is automatic detected by our proposed SaE-GBLS model based on three publicly available EEG datasets and one private clinical EEG dataset.Results and discussionThe experimental results indicate that our suggested strategy has the potential to perform as well as current machine learning approaches.

Closed-loop neuromodulation with intelligence methods has shown great potentials in providing novel neuro-technology for treating neurological and psychiatric diseases. Development of brain-machine interactive neuromodulation strategies could lead to breakthroughs in precision and personalized electronic medicine. The neuromodulation research tool integrating artificial intelligent computing and performing neural sensing and stimulation in real-time could accelerate the development of closed-loop neuromodulation strategies and translational research into clinical application. In this study, we developed a brain-machine interactive neuromodulation research tool (BMINT), which has capabilities of neurophysiological signals sensing, computing with mainstream machine learning algorithms and delivering electrical stimulation pulse by pulse in real-time. The BMINT research tool achieved system time delay under 3 ms, and computing capabilities in feasible computation cost, efficient deployment of machine learning algorithms and acceleration process. Intelligent computing framework embedded in the BMINT enable real-time closed-loop neuromodulation developed with mainstream AI ecosystem resources. The BMINT could provide timely contribution to accelerate the translational research of intelligent neuromodulation by integrating neural sensing, edge AI computing and stimulation with AI ecosystems.

Abstract Background Seizure detection is challenging outside the clinical environment due to the lack of comfortable, reliable, and practical long-term neurophysiological monitoring devices. We developed a novel, discreet, unobstructive in-ear sensing system that enables long-term electroencephalography (EEG) recording. This is the first study we are aware of that systematically compares the seizure detection utility of in-ear EEG with that of simultaneously recorded intracranial EEG. In addition, we present a similar comparison between simultaneously recorded in-ear EEG and scalp EEG. Methods In this foundational research, we conducted a clinical feasibility study and validated the ability of the ear-EEG system to capture focal-onset seizures against 1255 hrs of simultaneous ear-EEG data along with scalp or intracranial EEG in 20 patients with refractory focal epilepsy (11 with scalp EEG, 8 with intracranial EEG, and 1 with both). Results In a blinded, independent review of the ear-EEG signals, two epileptologists were able to detect 86.4% of the seizures that were subsequently identified using the clinical gold standard EEG modalities, with a false detection rate of 0.1 per day, well below what has been reported for ambulatory monitoring. The few seizures not detected on the ear-EEG signals emanated from deep within the mesial temporal lobe or extra-temporally and remained very focal, without significant propagation. Following multiple sessions of recording for a median continuous wear time of 13 hrs, patients reported a high degree of tolerance for the device, with only minor adverse events reported by the scalp EEG cohort. Conclusions These preliminary results demonstrate the potential of using ear-EEG to enable routine collection of complementary, prolonged, and remote neurophysiological evidence, which may permit real-time detection of paroxysmal events such as seizures and epileptiform discharges. This study suggests that the ear-EEG device may assist clinicians in making an epilepsy diagnosis, assessing treatment efficacy, and optimizing medication titration.

Abstract A reliable seizure detection or prediction device can potentially reduce the morbidity and mortality associated with epileptic seizures. Previous findings indicating alterations in cardiac activity during seizures suggest the usefulness of cardiac parameters for seizure detection or prediction. This study aims to examine available studies on seizure detection and prediction based on cardiac parameters using non‐invasive wearable devices. The Embase, PubMed, and Scopus databases were used to systematically search according to the Preferred Reporting Items for Systematic Reviews and Meta‐Analysis guidelines. Human studies that evaluated seizure detection or prediction based on cardiac parameters collected using wearable devices were included. The QUADAS‐2 tool and proposed standards for validation for seizure detection devices were used for quality assessment. Twenty‐four articles were identified and included in the analysis. Twenty studies evaluated seizure detection algorithms, and four studies focused on seizure prediction. Most studies used either a wrist‐worn or chest‐worn device for data acquisition. Among the seizure detection studies, cardiac parameters utilized for the algorithms mainly included heart rate (HR) (n = 11) or a combination of HR and heart rate variability (HRV) (n = 6). HR‐based seizure detection studies collectively reported a sensitivity range of 56%‐100% and a false alarm rate (FAR) of 0.02‐8/h, with most studies performing retrospective validation of the algorithms. Three of the seizure prediction studies retrospectively validated multimodal algorithms, combining cardiac features with other physiological signals. Only one study prospectively validated their seizure prediction algorithm using HRV extracted from ECG data collected from a custom wearable device. These studies have demonstrated the feasibility of using cardiac parameters for seizure detection and prediction with wearable devices, with varying algorithmic performance. Many studies are in the proof‐of‐principle stage, and evidence for real‐time detection or prediction is currently limited. Future studies should prioritize further refinement of the algorithm performance with prospective validation using large‐scale longitudinal data. Plain Language Summary This systematic review highlights the potential use of wearable devices, like wristbands, for detecting and predicting seizures via the measurement of heart activity. By reviewing 24 articles, it was found that most studies focused on using heart rate and changes in heart rate for seizure detection. There was a lack of studies looking at seizure prediction. The results were promising but most studies were not conducted in real‐time. Therefore, more real‐time studies are needed to verify the usage of heart activity‐related wearable devices to detect seizures and even predict them, which will be beneficial to people with epilepsy.

Automatic seizure detection plays a crucial role in epilepsy diagnosis and treatment. Traditional machine learning based automatic seizure detection requires additional feature engineering and finding the optimal hand-crafted features is a challenging issue. Therefore, a novel end-to-end deep learning model that combines attention mechanism, temporal convolutional network(TCN), and bidirectional gated recurrent unit (BiGRU) is proposed for seizure detection in this work. Our model only requires filtering of the raw electroencephalogram(EEG) signals to remove artifacts, without the need for time-consuming feature extraction. Post-processing procedures including moving-average filtering, thresholding, and the collar technique are then applied to enhance the model’s performance. Experiments were conducted on the CHB-MIT dataset and the SH-SDU dataset. In patient-specific experiments, our model achieved average accuracies of 98.77% on the CHB-MIT dataset and 93.61% on the SH-SDU dataset. In cross-patient experiments, average accuracies of 93.78% and 91.37% were obtained, respectively. The total time required for the model to process 1-hour EEG signals is only 5.33s. These outstanding results indicate that our model achieves high accuracy and real-time performance in seizure detection tasks and could provide reference for clinical seizure diagnosis.

The diagnosis of epilepsy can be confirmed in-hospital via video-electroencephalography (vEEG). Currently, long-term monitoring is limited to self-reporting seizure occurrences by the patients. In recent years, the development of wearable sensors has allowed monitoring patients outside of specialized environments. The application of wearable EEG devices for monitoring epileptic patients in ambulatory environments is still dampened by the low performance achieved by automated seizure detection frameworks. In this work, we present the results of a seizure detection grand challenge, organized as an attempt to stimulate the development of automated methodologies for detection of seizures on wearable EEG. The main drawbacks for developing wearable EEG seizure detection algorithms is the lack of data needed for training such frameworks. In this challenge, we provided participants with a large dataset of 42 patients with focal epilepsy, containing continuous recordings of behind-the-ear (bte) EEG. We challenged participants to develop a robust seizure classifier based on wearable EEG. Additionally, we proposed a subtask in order to motivate data-centric approaches to improve the training and performance of seizure detection models. An additional dataset, containing recordings with a bte-EEG wearable device, was employed to evaluate the work submitted by participants. In this paper, we present the five best scoring methodologies. The best performing approach was a feature-based decision tree ensemble algorithm with data augmentation via Fourier Transform surrogates. The organization of this challenge is of high importance for improving automated EEG analysis for epilepsy diagnosis, working towards implementing these technologies in clinical practice.

The diagnosis and treatment of brain diseases represent the forefront of brain science research, with EEG-related research occupying a uniquely significant position. In recent years, deep learning technology has been widely applied to the study of EEG signals, yet the integration of information from multiple EEG channels remains a challenging task. Based on the dynamic routing algorithm, this study established a deep neural network. Subsequently, leveraging this network, an epileptic seizure recognition method, VarChanNet, was proposed. Seizure recognition experiments were conducted using the Bonn and CHB-MIT databases. The experimental results demonstrate that the proposed VarChanNet method maintains high recognition accuracy even when the number of channels involved in the recognition process changes. It reliably functions on both the Bonn and CHB-MIT databases, indicating its potential for generalization. Furthermore, the method provides recommendations for channel selection during the recognition process. For instance, in the case of CHB-MIT, Channel 21 can be selected for single-channel recognition, Channels 2 and 3 for dual-channel, and Channels 1, 2, and 3 for triple-channel epileptic seizure recognition. In a word, the proposed VarChanNet method enables the fusion of information from different EEG channels, supporting recognition tasks even when the number of channels varies. It offers a new perspective for EEG analysis and holds the potential for generalization.

Automatic seizure detection using electroen-cephalogram (EEG) can significantly expedite the diagnosis of epilepsy, thereby facilitating prompt treatment and reducing the risk of future seizures and associated complications. While most existing EEG-based epilepsy detection studies employ deep learning models, they often ignore the chronological relationships between different EEG channels. To tackle this limitation, a novel automatic epilepsy detection method is proposed, which leverages path signature and Bidirectional Long Short-Term Memory (Bi-LSTM) neural network with an attention mechanism. The path signature algorithm is used to extract discriminative features for capturing the dynamic dependencies between different channels of EEG, while Bi-LSTM with attention further analyzes the inherent temporal dependencies hidden in EEG signal features. Our method is evaluated on two public EEG databases with different sizes (CHB-MIT and TUEP) and a private database from a local hospital. Two experimental settings are used, i.e., five-fold cross-validation and leave-one-out cross-validation. Experimental results show that our method achieves 99.09%, 95.60%, and 99.87% average accuracies on CHB-MIT, TUEP with 250Hz, and TUEP with 256Hz, respectively. On the private dataset, our method also achieves 99.40% average accuracy, which outperforms other methods. Furthermore, our method exhibits robustness in patients, as demonstrated by the evaluation results of cross-patient experiments.

IntroductionLong-term electroencephalography (EEG) monitoring is advised to patients with refractory epilepsy who have a failure of anti-seizure medication and therapy. However, its real-life application is limited mainly due to the use of multiple EEG channels. We proposed a patient-specific deep learning-based single-channel seizure detection approach using the long-term scalp EEG recordings of the Children’s Hospital Boston-Massachusetts Institute of Technology (CHB-MIT) dataset, in conjunction with neurologists’ confirmation of spatial seizure characteristics of individual patients.MethodsWe constructed 18-, 4-, and single-channel seizure detectors for 13 patients. Neurologists selected a specific channel among four channels, two close to the behind-the-ear and two at the forehead for each patient, after reviewing the patient’s distinctive seizure locations with seizure re-annotation.ResultsOur multi- and single-channel detectors achieved an average sensitivity of 97.05–100%, false alarm rate of 0.22–0.40/h, and latency of 2.1–3.4 s for identification of seizures in continuous EEG recordings. The results demonstrated that seizure detection performance of our single-channel approach was comparable to that of our multi-channel ones.DiscussionWe suggest that our single-channel approach in conjunction with clinical designation of the most prominent seizure locations has a high potential for wearable seizure detection on long-term EEG recordings for patients with refractory epilepsy.

IntroductionAutomated seizure detection promises to aid in the prevention of SUDEP and improve the quality of care by assisting in epilepsy diagnosis and treatment adjustment.MethodsIn this phase 2 exploratory study, the performance of a contactless, marker-free, video-based motor seizure detection system is assessed, considering video recordings of patients (age 0–80 years), in terms of sensitivity, specificity, and Receiver Operating Characteristic (ROC) curves, with respect to video-electroencephalographic monitoring (VEM) as the medical gold standard. Detection performances of five categories of motor epileptic seizures (tonic–clonic, hyperkinetic, tonic, unclassified motor, automatisms) and psychogenic non-epileptic seizures (PNES) with a motor behavioral component lasting for >10 s were assessed independently at different detection thresholds (rather than as a categorical classification problem). A total of 230 patients were recruited in the study, of which 334 in-scope (>10 s) motor seizures (out of 1,114 total seizures) were identified by VEM reported from 81 patients. We analyzed both daytime and nocturnal recordings. The control threshold was evaluated at a range of values to compare the sensitivity (n = 81 subjects with seizures) and false detection rate (FDR) (n = all 230 subjects).ResultsAt optimal thresholds, the performance of seizure groups in terms of sensitivity (CI) and FDR/h (CI): tonic–clonic- 95.2% (82.4, 100%); 0.09 (0.077, 0.103), hyperkinetic- 92.9% (68.5, 98.7%); 0.64 (0.59, 0.69), tonic- 78.3% (64.4, 87.7%); 5.87 (5.51, 6.23), automatism- 86.7% (73.5, 97.7%); 3.34 (3.12, 3.58), unclassified motor seizures- 78% (65.4, 90.4%); 4.81 (4.50, 5.14), and PNES- 97.7% (97.7, 100%); 1.73 (1.61, 1.86). A generic threshold recommended for all motor seizures under study asserted 88% sensitivity and 6.48 FDR/h.DiscussionThese results indicate an achievable performance for major motor seizure detection that is clinically applicable for use as a seizure screening solution in diagnostic workflows.

About 70 million people globally have been diagnosed with epilepsy. Electroencephalogram (EEG) devices are the primary method for identifying and monitoring seizures. The use of EEG expands the preclinical research involving the long-term recording of neuro-activities in rodent models of epilepsy targeted towards the efficient testing of prospective antiseizure medications. Typically, trained epileptologists visually analyse long-term EEG recordings, which is time-consuming and subject to expert variability. Automated epileptiform discharge detection using machine learning or deep learning methods is an effective approach to tackling these challenges. This systematic review examined and summarised the last 30 years of research on detecting epileptiform discharge in rodent models of epilepsy using machine learning and deep learning methods. A comprehensive literature search was conducted on two databases, PubMed and Google Scholar. Following the PRISMA protocol, the 3021 retrieved articles were filtered to 21 based on inclusion and exclusion criteria. An additional article was obtained through the reference list. Hence, 22 articles were selected for critical analysis in this review. These articles revealed the seizure type, features and feature engineering, machine learning and deep learning methods, training methodologies, evaluation metrics so far explored, and models deployed for real-world validation. Although these studies have advanced the field of epilepsy research, the majority of the models are experimental. Further studies are required to fill in the identified gaps and expedite preclinical research in epilepsy, ultimately leading to translational research.

Epilepsy affects millions worldwide, making timely seizure detection crucial for effective treatment and enhanced well-being. Electroencephalogram (EEG) analysis offers a non-intrusive solution, but its visual interpretation is prone to errors and requires a lot of time. Many existing works focus solely on achieving competitive levels of accuracy without considering processing speed or the computational complexity of their models. This study aimed to develop an automated technique for identifying epileptic seizures in EEG data through analysis methods. The efforts have been primarily focused on achieving high accuracy results by operating exclusively within a narrow frequency band of the signal, while also aiming to minimize computational complexity. In this article, a new automated approach is presented for seizure detection by combining signal processing and machine learning techniques. The proposed method comprises four stages: (1) Preprocessing: Savitzky–Golay filter to remove the background noise. (2) Decomposition: discrete wavelet transform (DWT) to extract spontaneous alpha and beta frequency bands. (3) Feature extraction: six features (mean, standard deviation, skewness, kurtosis, energy, and entropy) are computed for each frequency band. (4) Classification: a support vector machine (SVM) method classifies signals as normal or containing a seizure. The method was assessed using two publicly available EEG datasets. For the alpha band, the highest achieved accuracy was 92.82%, and for the beta band it was 90.55%, which demonstrates adequate capability in both bands for accurate seizure detection. Furthermore, the obtained low computational cost suggests a potentially valuable application in real-time assessment scenarios. The obtained results indicate its capacity as a valuable instrument for diagnosing epilepsy and monitoring patients. Further research is necessary for clinical validation and potential real-time deployment.

Epilepsy is characterized by recurring seizures that result from abnormal electrical activity in the brain. These seizures manifest as various symptoms including muscle contractions and loss of consciousness. The challenging task of detecting epileptic seizures involves classifying electroencephalography (EEG) signals into ictal (seizure) and interictal (non-seizure) classes. This classification is crucial because it distinguishes between the states of seizure and seizure-free periods in patients with epilepsy. Our study presents an innovative approach for detecting seizures and neurological diseases using EEG signals by leveraging graph neural networks. This method effectively addresses EEG data processing challenges. We construct a graph representation of EEG signals by extracting features such as frequency-based, statistical-based, and Daubechies wavelet transform features. This graph representation allows for potential differentiation between seizure and non-seizure signals through visual inspection of the extracted features. To enhance seizure detection accuracy, we employ two models: one combining a graph convolutional network (GCN) with long short-term memory (LSTM) and the other combining a GCN with balanced random forest (BRF). Our experimental results reveal that both models significantly improve seizure detection accuracy, surpassing previous methods. Despite simplifying our approach by reducing channels, our research reveals a consistent performance, showing a significant advancement in neurodegenerative disease detection. Our models accurately identify seizures in EEG signals, underscoring the potential of graph neural networks. The streamlined method not only maintains effectiveness with fewer channels but also offers a visually distinguishable approach for discerning seizure classes. This research opens avenues for EEG analysis, emphasizing the impact of graph representations in advancing our understanding of neurodegenerative diseases.

IntroductionEpilepsy is a global chronic disease that brings pain and inconvenience to patients, and an electroencephalogram (EEG) is the main analytical tool. For clinical aid that can be applied to any patient, an automatic cross-patient epilepsy seizure detection algorithm is of great significance. Spiking neural networks (SNNs) are modeled on biological neurons and are energy-efficient on neuromorphic hardware, which can be expected to better handle brain signals and benefit real-world, low-power applications. However, automatic epilepsy seizure detection rarely considers SNNs.MethodsIn this article, we have explored SNNs for cross-patient seizure detection and discovered that SNNs can achieve comparable state-of-the-art performance or a performance that is even better than artificial neural networks (ANNs). We propose an EEG-based spiking neural network (EESNN) with a recurrent spiking convolution structure, which may better take advantage of temporal and biological characteristics in EEG signals.ResultsWe extensively evaluate the performance of different SNN structures, training methods, and time settings, which builds a solid basis for understanding and evaluation of SNNs in seizure detection. Moreover, we show that our EESNN model can achieve energy reduction by several orders of magnitude compared with ANNs according to the theoretical estimation.DiscussionThese results show the potential for building high-performance, low-power neuromorphic systems for seizure detection and also broaden real-world application scenarios of SNNs.

Epilepsy is a prevalent brain disease, which is quite difficult-to-treat or cure. This study developed a novel automatic seizure detection method based on the persistent homology method. In this study, a Vietoris–Rips (VR) complex filtration model was constructed based on the EEG data. And the persistent homology method was applied to calculate the VR complex filtration barcodes to describe the topological changes of EEG recordings. Afterward, the barcodes as the topological characteristics of EEG signals were fed into the GoogLeNet for classification. The persistent homology is applicable for multi-channel EEG data analysis, where the global topological information is calculated and the features are extracted by considering the multi-channel EEG data as a whole, without the multiple calculations or the post-stitching. Three databases were used to evaluate the proposed approach and the results showed that the approach had high performances in the epilepsy detection. The results obtained from the CHB-MIT Database recordings revealed that the proposed approach can achieve a segment-based averaged accuracy, sensitivity and specificity values of 97.05%, 96.71% and 97.38%, and achieve an event-based averaged sensitivity value of 100% with 1.22 s average detection latency. In addition, on the Siena Scalp Database, the proposed method yields averaged accuracy, sensitivity and specificity values of 96.42%, 95.23% and 97.6%. Multiple tasks of the Bonn Database also showed achieved accuracy of 99.55%, 98.63%, 98.28% and 97.68%, respectively. The experimental results on these three EEG databases illustrate the efficiency and robustness of our approach for automatic detection of epileptic seizure.

Seizure detection from EEG signals is crucial for diagnosing and treating neurological disorders. However, accurately detecting seizures is challenging due to the complexity and variability of EEG signals. This paper proposes a deep learning model, called Hybrid Cross Layer Attention Based Convolutional Bidirectional Gated Recurrent Unit (HCLA_CBiGRU), which combines convolutional neural networks and recurrent neural networks to capture spatial and temporal features in EEG signals. A combinational EEG dataset was created by merging publicly available datasets and applying a preprocessing pipeline to remove noise and artifacts. The dataset was then segmented and split into training and testing sets. The HCLA_CBiGRU model was trained on the training set and evaluated on the testing set, achieving an impressive accuracy of 98.5%, surpassing existing state-of-the-art methods. Sensitivity and specificity, critical metrics in clinical practice, were also assessed, with the model demonstrating a sensitivity of 98.5% and a specificity of 98.9%, highlighting its effectiveness in seizure detection. Visualization techniques were used to analyze the learned features, showing the model's ability to capture distinguishing seizure-related characteristics. In conclusion, the proposed CBiGRU model outperforms existing methods in terms of accuracy, sensitivity, and specificity for seizure detection from EEG signals. Its integration with EEG signal analysis has significant implications for improving the diagnosis and treatment of neurological disorders, potentially leading to better patient outcomes.

Epilepsy is a life-threatening and challenging nervous system disease. There are still many challenges in the detection of epilepsy based on electroencephalogram (EEG). Because the EEG signal is unstable, different patients show different seizure patterns. In addition, EEG detection is time-consuming and laborious, which will not only bring heavy burden to medical staff, but also easily lead to false detection. Therefore, it is necessary to study an efficient automatic epilepsy detection technology across multiple patients. In this paper, an epileptic EEG detection method (convolutional attention bidirectional long short-term memory network, CABLNet) based on the multi-head self-attention mechanism neural network is proposed. Firstly, the convolution layer is used to capture short-term temporal patterns of EEG time series and local dependence among channels. Secondly, this paper uses the multi-head self-attention mechanism to capture the long-distance dependence and time dynamic correlation of the short-term time pattern feature vectors with temporal relationship. Thirdly, the context representation is sent into a bidirectional long short-term memory (BiLSTM) to extract the information in the front and back directions. Finally, logsoftmax function is used for training and classification. Using CHB-MIT scalp EEG database data, the sensitivity, specificity, accuracy and F1-score are 96.18%, 97.04%, 96.61% and 96.59% respectively. The results show that the proposed method is superior to the existing methods and significantly improved in epilepsy detection performance, which is of great significance to the auxiliary diagnosis of epilepsy.

Epilepsy is one of the most common neurological diseases. Clinically, epileptic seizure detection is usually performed by analyzing electroencephalography (EEG) signals. At present, deep learning models have been widely used for single-channel EEG signal epilepsy detection, but this method is difficult to explain the classification results. Researchers have attempted to solve interpretive problems by combining graph representation of EEG signals with graph neural network models. Recently, the combination of graph representations and graph neural network (GNN) models has been increasingly applied to single-channel epilepsy detection. By this methodology, the raw EEG signal is transformed to its graph representation, and a GNN model is used to learn latent features and classify whether the data indicates an epileptic seizure episode. However, existing methods are faced with two major challenges. First, existing graph representations tend to have high time complexity as they generally require each vertex to traverse all other vertices to construct a graph structure. Some of them also have high space complexity for being dense. Second, while separate graph representations can be derived from a single-channel EEG signal in both time and frequency domains, existing GNN models for epilepsy detection can learn from a single graph representation, which makes it hard to let the information from the two domains complement each other. For addressing these challenges, we propose a Weighted Neighbour Graph (WNG) representation for EEG signals. Reducing the redundant edges of the existing graph, WNG can be both time and space-efficient, and as informative as its less efficient counterparts. We then propose a two-stream graph-based framework to simultaneously learn features from WNG in both time and frequency domain. Extensive experiments demonstrate the effectiveness and efficiency of the proposed methods.

The Electroencephalogram (EEG) pattern of seizure activities is highly individual-dependent and requires experienced specialists to annotate seizure events. It is clinically time-consuming and error-prone to identify seizure activities by visually scanning EEG signals. Since EEG data are heavily under-represented, supervised learning techniques are not always practical, particularly when the data is not sufficiently labelled. Visualization of EEG data in low-dimensional feature space can ease the annotation to support subsequent supervised learning for seizure detection. Here, we leverage the benefit of both the time-frequency domain features and the Deep Boltzmann Machine (DBM) based unsupervised learning techniques to represent EEG signals in a 2-dimensional (2D) feature space. A novel unsupervised learning approach based on DBM, namely DBM_transient, is proposed by training DBM to a transient state for representing EEG signals in a 2D feature space and clustering seizure and non-seizure events visually. The effectiveness of DBM_transient is demonstrated on a widely-used benchmark dataset from Bonn University (Bonn dataset) and a raw clinical dataset from Chinese 301 Hospital (C301 dataset), with a large fisher discriminant value, surpassing the abilities of other dimensionality reduction methods, including DBM converged to an equilibrium state, Kernel Principal Component Analysis, Isometric Feature Mapping, t-distributed Stochastic Neighbour Embedding, Uniform Manifold Approximation. Such feature representation and visualization can help physicians to understand better the normal versus epileptic brain activities of each patient and thus enhance their diagnosis and treatment abilities. The significance of our approach facilitates its future usage in clinical applications.

Transfer learning (TL) has been applied in seizure detection to deal with differences between different subjects or tasks. In this paper, we consider cross-subject seizure detection that does not rely on patient history records, that is, acquiring knowledge from other subjects through TL to improve seizure detection performance. We propose a novel domain adaptation method, named the Cluster Embedding Joint-Probability-Discrepancy Transfer (CEJT), for data distribution structure learning. Specifically, 1) The joint probability distribution discrepancy is minimized to reduce the distribution shift in the source and target domains, and strengthen the discriminative knowledge of classes. 2) A clustering is performed on the target domain, and the class centroids of sources is used as the clustering prototype of the target domain to enhance data structure. It is worth noting that the manifold regularization is used to improve the quality of clustering prototypes. In addition, a correlation-alignment-based source selection metric (SSC) is designed for most favorable subject selection, reducing the computational cost as well as avoiding some negative transfer. Experiments on 15 patients with focal epilepsy from the Children’s Hospital, Zhejiang University School of Medicine (CHZU) database shown that CEJT outperforms several state-of-the-art approaches, and can promote the application of seizure detection.

Many deep-learning-based seizure detection algorithms have achieved good classification, which usually outperformed traditional machine-learning-based algorithms. However, the hand-engineered features increase the computational complexity and potentially have an ineffectiveness problem for the category. Therefore, this paper proposes a novel end-to-end deep-learning model comprising an inception module and a residual module to analyze the multi-scales of original EEG signals and realize seizure detection without feature extraction. Experiments were conducted and evaluated on the Bonn dataset and the CHB-MIT dataset. In the subject-dependent experiments, our model achieved an average F1-score of 69.34% on the CHB-MIT dataset. In subject-independent experiments, our method achieved an average accuracy of 99.04% on the Bonn dataset and an average F1-score of 37.31% on the CHB-MIT dataset. A series of analyses confirmed that our proposed model has better classification performance and lower computational complexity than existing end-to-end seizure detection models.

In recent years, many studies have proposed seizure detection algorithms, but most of them require high computing resources and a large amount of memory, which are difficult to implement in wearable devices. This paper proposes a seizure detection algorithm that uses a small number of features to reduce the memory requirements of the algorithm. During feature extraction, this paper proposes an entropy estimation method that uses bitwise operations instead of logarithmic operations to reduce the algorithm’s demand for computing resources. The experimental results show that the computing time can be reduced by about 81.58%. The seizure detection algorithm in this paper is implemented in an ultra-low power embedded system and performs 7 classification tasks in the Bonn data set to verify the performance of the algorithm. The average classification performance is: Accuracy (97.13%), Specificity (97.57%) and Sensitivity (98.42%). Compared with previous studies, the algorithm of this paper has comparable classification performance, but the proposed algorithm only needs 0.23 seconds from feature extraction to classification result, to the best of our knowledge, which is the seizure detection algorithm with the least computing time currently applied to wearable devices.

Abstract Background Quantitative electroencephalogram (QEEG) is a tool that uses a computer to analyze brain activity monitored by electroencephalogram (EEG) according to measurements such as frequency, amplitude, and slope. The purpose of this study was to understand the current situation of QEEG utilization in China and further compare the situations among different regions and different levels of hospitals. Methods An online questionnaire comprising 14 questions was designed. Statistical description and analysis were made for the results of the questionnaire survey. Results A total of 158 people from 134 medical institutions participated in the survey. The participants came from 21 provinces, accounting for 61.76% (21/34) of the 34 provincial administrative regions in China. The Eastern China region accounted for 66.42% (89/134) of all the medical institutions that participated in this survey. Among the institutions surveyed, QEEG was routinely used in only 23.88% (32/134) of them. Among the medical institutions in which QEEG was routinely used, 87.50% (28/32) of them were 3A-grade hospitals. Among the institutions with routine use of QEEG, 56.25% (18/32) were affiliated hospitals of medical schools. There was a significant difference in the utilization of QEEG between the 3A-grade and non-3A-grade hospitals (P = 0.040) and between the hospitals affiliated to medical schools and those non-affiliated to medical schools (P = 0.020). Conclusions The utilization of QEEG is still limited in China. There are differences in the use of QEEG among different hospitals and regions.

Abstract Objective To assess the performance of a multimodal seizure detection device, first tested in adults (sensitivity 86%, PPV 49%), in a pediatric cohort living at home or residential care. Methods In this multicenter, prospective, video‐controlled cohort‐study, nocturnal seizures were detected by heartrate and movement changes in children with epilepsy and intellectual disability. Participants with a history of >1 monthly major motor seizure wore Nightwatch bracelet at night for 3 months. Major seizures were defined as tonic–clonic, generalized tonic >30 s, hyperkinetic, or clusters (>30 min) of short myoclonic or tonic seizures. The video of all events (alarms and nurse diaries) and about 10% of whole nights were reviewed to classify major seizures, and minor or no seizures. Results Twenty‐three participants with focal or generalized epilepsy and nightly motor seizures were evaluated during 1511 nights, with 1710 major seizures. First 1014 nights, 4189 alarms occurred with average of 1.44/h, showing average sensitivity of 79.9% (median 75.4%) with mean PPV of 26.7% (median 11.1%) and false alarm rate of 0.2/hour. Over 90% of false alarms in children was due to heart rate (HR) part of the detection algorithm. To improve this rate, an adaptation was made such that the alarm was only triggered when the wearer was in horizontal position. For the remaining 497 nights, this was tested prospectively, 384 major seizures occurred. This resulted in mean PPV of 55.5% (median 58.1%) and a false alarm rate 0.08/h while maintaining a comparable mean sensitivity of 79.4% (median 93.2%). Significance Seizure detection devices that are used in bed which depend on heartrate and movement show similar sensitivity in children and adults. However, children do show general higher false alarm rate, mostly triggered while awake. By correcting for body position, the false alarms can be limited to a level that comes close to that in adults.

The number of electrodes used to acquire neonatal EEG signals varies between institutions. Therefore, tools for automatic EEG analysis, such as neonatal seizure detection algorithms, need to be able to handle different electrode montages in order to find widespread use. The aim of this study was to analyse the effect of montage on neonatal seizure detector performance. A full 18-channel montage was compared to reduced 3- and 8-channel montages using a convolutional neural network for seizure detection. Sensitivity decreased by 10 - 18 % for the reduced montages while specificity was mostly unaffected. Electrode artefacts and artefacts associated with biological rhythms caused incorrect classification of nonseizure activity in some cases, but these artefacts were filtered out in the 3-channel montage. Other types of artefacts had little effect. Reduced montages result in some reduction in classifier accuracy, but the performance may still be acceptable. Recording artefacts had a limited effect on detection accuracy.

Absence seizures—generalized rhythmic spike-and-wave discharges (SWDs) are the defining property of childhood (CAE) and juvenile (JAE) absence epilepsies. Such seizures are the most compelling examples of pathological neuronal hypersynchrony. All the absence detection algorithms proposed so far have been derived from the properties of individual SWDs. In this work, we investigate EEG phase synchronization in patients with CAE/JAE and healthy subjects to explore the possibility of using the wavelet phase synchronization index to detect seizures and quantify their disorganization (fragmentation). The overlap of the ictal and interictal probability density functions was high enough to preclude effective seizure detection based solely on changes in EEG synchronization. We used a machine learning classifier with the phase synchronization index (calculated for 1 s data segments with 0.5 s overlap) and the normalized amplitude as features to detect generalized SWDs. Using 19 channels (10-20 setup), we identified 99.2% of absences. However, the overlap of the segments classified as ictal with seizures was only 83%. The analysis showed that seizures were disorganized in approximately half of the 65 subjects. On average, generalized SWDs lasted about 80% of the duration of abnormal EEG activity. The disruption of the ictal rhythm can manifest itself as the disappearance of epileptic spikes (with high-amplitude delta waves persisting), transient cessation of epileptic discharges, or loss of global synchronization. The detector can analyze a real-time data stream. Its performance is good for a six-channel setup (Fp1, Fp2, F7, F8, O1, O2), which can be implemented as an unobtrusive EEG headband. False detections are rare for controls and young adults (0.03% and 0.02%, respectively). In patients, they are more frequent (0.5%), but in approximately 82% cases, classification errors are caused by short epileptiform discharges. Most importantly, the proposed detector can be applied to parts of EEG with abnormal EEG activity to quantitatively determine seizure fragmentation. This property is important because a previous study reported that the probability of disorganized discharges is eight times higher in JAE than in CAE. Future research must establish whether seizure properties (frequency, length, fragmentation, etc.) and clinical characteristics can help distinguish CAE and JAE.

Brain maturity and many clinical treatments such as therapeutic hypothermia (TH) can significantly influence the morphology of neonatal EEG seizures after hypoxia–ischemia (HI), and so there is a need for generalized automatic seizure identification. This study validates efficacy of advanced deep-learning pattern classifiers based on a convolutional neural network (CNN) for seizure detection after HI in fetal sheep and determines the effects of maturation and brain cooling on their accuracy. The cohorts included HI–normothermia term (n = 7), HI–hypothermia term (n = 14), sham–normothermia term (n = 5), and HI–normothermia preterm (n = 14) groups, with a total of >17,300 h of recordings. Algorithms were trained and tested using leave-one-out cross-validation and k-fold cross-validation approaches. The accuracy of the term-trained seizure detectors was consistently excellent for HI–normothermia preterm data (accuracy = 99.5%, area under curve (AUC) = 99.2%). Conversely, when the HI–normothermia preterm data were used in training, the performance on HI–normothermia term and HI–hypothermia term data fell (accuracy = 98.6%, AUC = 96.5% and accuracy = 96.9%, AUC = 89.6%, respectively). Findings suggest that HI–normothermia preterm seizures do not contain all the spectral features seen at term. Nevertheless, an average 5-fold cross-validated accuracy of 99.7% (AUC = 99.4%) was achieved from all seizure detectors. This significant advancement highlights the reliability of the proposed deep-learning algorithms in identifying clinically translatable post-HI stereotypic seizures in 256Hz recordings, regardless of maturity and with minimal impact from hypothermia.

Around 70 million people worldwide are affected by epilepsy, a neurological disorder characterized by non-induced seizures that occur at irregular and unpredictable intervals. During an epileptic seizure, transient symptoms emerge as a result of extreme abnormal neural activity. Epilepsy imposes limitations on individuals and has a significant impact on the lives of their families. Therefore, the development of reliable diagnostic tools for the early detection of this condition is considered beneficial to alleviate the social and emotional distress experienced by patients. While the Bonn University dataset contains five collections of EEG data, not many studies specifically focus on subsets D and E. These subsets correspond to EEG recordings from the epileptogenic zone during ictal and interictal events. In this work, the parallel ictal-net (PIN) neural network architecture is introduced, which utilizes scalograms obtained through a continuous wavelet transform to achieve the high-accuracy classification of EEG signals into ictal or interictal states. The results obtained demonstrate the effectiveness of the proposed PIN model in distinguishing between ictal and interictal events with a high degree of confidence. This is validated by the computing accuracy, precision, recall, and F1 scores, all of which consistently achieve around 99% confidence, surpassing previous approaches in the related literature.

Epilepsy is a prevalent neurological disorder with considerable risks, including physical impairment and irreversible brain damage from seizures. Given these challenges, the urgency for prompt and accurate seizure detection cannot be overstated. Traditionally, experts have relied on manual EEG signal analyses for seizure detection, which is labor-intensive and prone to human error. Recognizing this limitation, the rise in deep learning methods has been heralded as a promising avenue, offering more refined diagnostic precision. On the other hand, the prevailing challenge in many models is their constrained emphasis on specific domains, potentially diminishing their robustness and precision in complex real-world environments. This paper presents a novel model that seamlessly integrates the salient features from the time–frequency domain along with pivotal statistical attributes derived from EEG signals. This fusion process involves the integration of essential statistics, including the mean, median, and variance, combined with the rich data from compressed time–frequency (CWT) images processed using autoencoders. This multidimensional feature set provides a robust foundation for subsequent analytic steps. A long short-term memory (LSTM) network, meticulously optimized for the renowned Bonn Epilepsy dataset, was used to enhance the capability of the proposed model. Preliminary evaluations underscore the prowess of the proposed model: a remarkable 100% accuracy in most of the binary classifications, exceeding 95% accuracy in three-class and four-class challenges, and a commendable rate, exceeding 93.5% for the five-class classification.

Epilepsy is a prevalent condition characterized by recurrent, unpredictable seizures. Monitoring with surface electroencephalography (EEG) is the gold standard for diagnosing epilepsy, but a time-consuming, uncomfortable and sometimes ineffective process for patients. Further, using EEG over a brief monitoring period has variable success, dependent on patient tolerance and seizure frequency. The availability of hospital resources and hardware and software specifications inherently restrict the options for comfortable, long-term data collection, resulting in limited data for training machine-learning models. This mini-review examines the current patient journey, providing an overview of the current state of EEG monitoring with reduced electrodes and automated channel reduction methods. Opportunities for improving data reliability through multi-modal data fusion are suggested. We assert the need for further research in electrode reduction to advance brain monitoring solutions towards portable, reliable devices that simultaneously offer patient comfort, perform ultra-long-term monitoring and expedite the diagnosis process.

Summary Objective Majority of seizures are detected within 24 hours on continuous EEG (cEEG). Some patients have delayed seizure detection after 24 hours. The purpose of this research was to identify risk factors that predict delayed seizure detection and to determine optimal cEEG duration for various patient subpopulations. Methods We retrospectively identified all patients ≥18 years of age who underwent cEEG at Cleveland clinic during calendar year 2016. Clinical and EEG data for all patients and time to seizure detection for seizure patients were collected. Results Twenty‐four hundred and two patients met inclusion criteria. Of these, 316 (13.2%) had subclinical seizures. Sixty‐five (20.6%) patients had delayed seizures detection after 24 hours. Seizure detection increased linearly till 36 hours of monitoring, and odds of seizure detection increased by 46% for every additional day of monitoring. Delayed seizure risk factors included stupor (13.2% after 48 hours, P = .031), lethargy (25.9%, P = .013), lateralized (LPDs) (27.7%, P = .029) or generalized periodic discharges (GPDs) (33.3%, P = .022), acute brain insults (25.5%, P = .036), brain bleeds (32.8%, P = .014), especially multiple concomitant bleeds (61.1%, P

Epilepsy is a chronic neurological disorder affecting around 1% of the global population, characterized by recurrent epileptic seizures. Accurate diagnosis and treatment are crucial for reducing mortality rates. Recent advancements in machine learning (ML) algorithms have shown potential in aiding clinicians with seizure detection in electroencephalography (EEG) data. However, these algorithms face significant challenges due to the patient-specific variability in seizure patterns and the limited availability of high-quality EEG data for training, causing erratic predictions. These erratic predictions are harmful, especially for high-stake domains in healthcare, negatively affecting patients. Therefore, ensuring safety in AI is of the utmost importance. In this study, we propose a novel ensemble method for uncertainty quantification to identify patients with low-confidence predictions in ML-based seizure detection algorithms. Our approach aims to mitigate high-risk predictions in previously unseen seizure patients, thereby enhancing the robustness of existing seizure detection algorithms. Additionally, our method can be implemented with most of the deep learning (DL) models. We evaluated the proposed method against established uncertainty detection techniques, demonstrating its effectiveness in identifying patients for whom the model’s predictions are less certain. Our proposed method managed to achieve 87%, 89% and 75% in accuracy, specificity and sensitivity, respectively. This study represents a novel attempt to improve the reliability and robustness of DL algorithms in the domain of seizure detection. This study underscores the value of integrating uncertainty quantification into ML algorithms for seizure detection, offering clinicians a practical tool to gauge the applicability of ML models for individual patients.

Absence seizure as a generalized onset seizure, simultaneously spreading seizure to both sides of the brain, involves around ten-second sudden lapses of consciousness. It common occurs in children than adults, which affects living quality even threats lives. Absence seizure can be confused with inattentive attention-deficit hyperactivity disorder since both have similar symptoms, such as inattention and daze. Therefore, it is necessary to detect absence seizure onset. However, seizure onset detection in electroencephalography (EEG) signals is a challenging task due to the non-stereotyped seizure activities as well as their stochastic and non-stationary characteristics in nature. Joint spectral-temporal features are believed to contain sufficient and powerful feature information for absence seizure detection. However, the resulting high-dimensional features involve redundant information and require heavy computational load. Here, we discover significant low-dimensional spectral-temporal features in terms of mean-standard deviation of wavelet transform coefficient (MS-WTC), based on which a novel absence seizure detection framework is developed. The EEG signals are transformed into the spectral-temporal domain, with their low-dimensional features fed into a convolutional neural network. Superior detection performance is achieved on the widely-used benchmark dataset as well as a clinical dataset from the Chinese 301 Hospital. For the former, seven classification tasks were evaluated with the accuracy from 99.8% to 100.0%, while for the latter, the method achieved a mean accuracy of 94.7%, overwhelming other methods with low-dimensional temporal and spectral features. Experimental results on two seizure datasets demonstrate reliability, efficiency and stability of our proposed MS-WTC method, validating the significance of the extracted low-dimensional spectral-temporal features.

Objective: The electroencephalogram (EEG) tool has great potential for real-time monitoring of abnormal brain activities, such as preictal and ictal seizures. Developing an EEG-based detection system for patients with epilepsy is vital for clinical management and targeted therapy. Methods: This paper proposes a single-channel seizure detection system using brain-rhythmic recurrence biomarkers (BRRM) and an optimized model (ONASNet). BRRM is a direct mapping of the recurrence morphology of brain rhythms in phase space; it reflects the nonlinear dynamics of original EEG signals. The architecture of ONASNet is determined through a modified neural network searching strategy. Then, we exploited transfer learning to apply ONASNet to our EEG data. The combination of BRRM and ONASNet leverages the multiple channels of a neural network to extract features from different brain rhythms simultaneously. Results: We evaluated the efficiency of BRRM-ONASNet on the real EEG recordings derived from Bonn University. In the experiments, different transfer-learning models (TLMs) are respectively constructed using ONASNet and seven well-known neural network structures (VGG16/VGG19/ResNet50/InceptionV3/DenseNet121/Xception/NASNet). Moreover, we compared those TLMs by model size, computing complexity, learning capability, and prediction latency. ONASNet outperforms other structures by strong learning capability, high stability, small model size, short latency, and less requirement of computing resources. Comparing BRRM-ONASNet with other existing methods, our work performs better than others with 100% accuracy under the identical dataset and same detection task. Contributions: The proposed method in this study, analyzing nonlinear features from phase-space representations using a deep neural network, provides new insights for EEG decoding. The successful application of this method in epileptic-seizure detection contributes to computationally medical assistance for epilepsy.

Automatic seizure detection system can serve as a meaningful clinical tool for the treatment and analysis of epilepsy using electroencephalogram (EEG) and has obtained rapid development. An automatic detection of epileptic seizure method based on kernel-based robust probabilistic collaborative representation (ProCRC) combined with graph-regularized non-negative matrix factorization (GNMF) is proposed in this work. The raw EEG signals are pre-processed through the wavelet transform to obtain time-frequency distribution of EEG signals as preliminary feature information and GNMF is further employed for dimension reduction, retaining and enhancing the productive feature information of EEG signals. Then, the test sample is represented using robust ProCRC that can decide whether the testing sample belongs to each class (seizure or non-seizure) by jointly maximizing the likelihood. In addition, the kernel trick is applied to improve the separability of non-linear high dimensional EEG signals in robust ProCRC. Finally, post-processing techniques are introduced to generate more accurate and reliable results. The average epoch-based sensitivity of 96.48%, event-based sensitivity of 93.65% and specificity of 98.55% are acquired in this method, which is evaluated on the public Freiburg EEG database.

With the increasment of epilepsy patients, traditional epileptic seizure recognition is generally completed by encephalography (EEG) technicians, which is time-consuming and labor-intensive, so the automatic detection of seizure is imminent. This paper proposes a method which constructs a multi-layer network and extracts the same features in each network optimized by improved genetic algorithm (IGA). Among them, the multi-layer network refers to the three-layer network constructed by pearson correlation coefficient, mutual information and permutation disalignment index respectively. There is a lack of research on the fusion and comparison of different networks in previous studies. Therefore, this paper analyzes the effectiveness of different networks by studying the fusion relationship of different networks, and further uses IGA for iterative optimization with constraints to weight the network and features, and finally uses the random forest classifier to automatically detect epileptic seizures. On CHB-MIT database, accuracy (ACC), specificity (SPE), sensitivity (SEN) and F1 score (F1) of the method proposed in this paper reach 97.26%, 97.55%, 96.89% and 97.11%, respectively. On Siena scalp database, ACC, SPE, SEN and F1 reach 98.88%, 99.13%, 98.36% and 98.75%, respectively. The results show that the joint detection effect of the multi-layer network is better than the combined effect of other networks, and IGA can improve the effect of seizure detection.

Hyperdimensional (HD) computing is a form of brain-inspired computing which can be applied to numerous classification problems. In past research, it has been shown that seizures can be detected from electroencephalograms (EEG) with high accuracy using local binary pattern (LBP) encoding. This paper explores applicability of binary HD computing to seizure detection from intra-cranial EEG (iEEG) data from the Kaggle seizure detection contest based on using both LBP and power spectral density (PSD) features. In the PSD method, three novel approaches to HD classification are presented for both selected features and all features. These are referred as single classifier long hypervector, multiple classifiers, and single classifier short hypervector. To visualize the quality of classification of test data, a hypervector distance plot is introduced that plots the Hamming distance of the query hpervectors from one class hypervector vs. that from the other. Simulation results show that: 1). LBP method offers an average 80.9% test accuracy, 71.9% sensitivity, 81.4% specificity and 76.6% test AUC whereas the PSD method can achieve an average of 91.0% test accuracy, 81.8% sensitivity, 92.0% specificity and 86.9% test AUC. 2). The average seizure detection latency is 2.5s for LBP method and is 4.5s for the PSD methods. This average latency, less than 5s, is a relevant parameter for fast drug delivery, indicating that both LBP and PSD methods are able to detect the seizures in a timely manner. The performance using selected PSD features is better than that using all features. 3). It is shown that the dimensionality of the hypervector can be reduced to 1, 000 bits for LBP and PSD methods from 10, 000. Futhermore, for some approaches of selected features, the dimensionality of the hypervector can be reduced to 100 bits.

Neonatal seizures are sudden events in brain activity with detrimental effects in neurological functions usually related to epileptic fits. Though neonatal seizures can be identified from electroencephalography (EEG), this is a challenging endeavour since expert visual inspection of EEG recordings is time consuming and prone to errors due the data’s nonstationarity and low signal-to-noise ratio. Towards the greater aim of automatic clinical decision making and monitoring, we propose a multi-output Gaussian process (MOGP) framework for neonatal EEG modelling. In particular, our work builds on the multi-output spectral mixture (MOSM) covariance kernel and shows that MOSM outperforms other commonly-used covariance functions in the literature when it comes to data imputation and hyperparameter-based seizure detection. To the best of our knowledge, our work is the first attempt at modelling and classifying neonatal EEG using MOGPs. Our main contributions are: i) the development of an MOGP-based framework for neonatal EEG analysis; ii) the experimental validation of the MOSM covariance kernel on real-world neonatal EEG for data imputation; and iii) the design of features for EEG based on MOSM hyperparameters and their validation for seizure detection (classification) in a patient specific approach.

Abstract Objective To identify non‐EEG‐based signals and algorithms for detection of motor and non‐motor seizures in people lying in bed during video‐EEG (VEEG) monitoring and to test whether these algorithms work in freely moving people during mobile EEG recordings. Methods Data of three groups of adult people with epilepsy (PwE) were analyzed. Group 1 underwent VEEG with additional devices (accelerometry, ECG, electrodermal activity); group 2 underwent VEEG; and group 3 underwent mobile EEG recordings both including one‐lead ECG. All seizure types were analyzed. Feature extraction and machine‐learning techniques were applied to develop seizure detection algorithms. Performance was expressed as sensitivity, precision, F1 score, and false positives per 24 hours. Results The algorithms were developed in group 1 (35 PwE, 33 seizures) and achieved best results (F1 score 56%, sensitivity 67%, precision 45%, false positives 0.7/24 hours) when ECG features alone were used, with no improvement by including accelerometry and electrodermal activity. In group 2 (97 PwE, 255 seizures), this ECG‐based algorithm largely achieved the same performance (F1 score 51%, sensitivity 39%, precision 73%, false positives 0.4/24 hours). In group 3 (30 PwE, 51 seizures), the same ECG‐based algorithm failed to meet up with the performance in groups 1 and 2 (F1 score 27%, sensitivity 31%, precision 23%, false positives 1.2/24 hours). ECG‐based algorithms were also separately trained on data of groups 2 and 3 and tested on the data of the other groups, yielding maximal F1 scores between 8% and 26%. Significance Our results suggest that algorithms based on ECG features alone can provide clinically meaningful performance for automatic detection of all seizure types. Our study also underscores that the circumstances under which such algorithms were developed, and the selection of the training and test data sets need to be considered and limit the application of such systems to unseen patient groups behaving in different conditions.

The diagnosis of epilepsy primarily relies on the visual and subjective assessment of the patient’s electroencephalographic (EEG) or intracranial electroencephalographic (iEEG) signals. Neurophysiologists, based on their experience, look for characteristic discharges such as spikes and multi-spikes. One of the main challenges in epilepsy research is developing an automated system capable of detecting epileptic seizures with high sensitivity and precision. Moreover, there is an ongoing search for universal features in iEEG signals that can be easily interpreted by neurophysiologists. This article explores the possibilities, issues, and challenges associated with utilizing artificial intelligence for seizure detection using the publicly available iEEG database. The study presents standard approaches for analyzing iEEG signals, including chaos theory, energy in different frequency bands (alpha, beta, gamma, theta, and delta), wavelet transform, empirical mode decomposition, and machine learning techniques such as support vector machines. It also discusses modern deep learning algorithms such as convolutional neural networks (CNN) and long short-term memory (LSTM) networks. Our goal was to gather and comprehensively compare various artificial intelligence techniques, including both traditional machine learning methods and deep learning techniques, which are most commonly used in the field of seizure detection. Detection results were tested on a separate dataset, demonstrating classification accuracy, sensitivity, precision, and specificity of seizure detection. The best results for seizure detection were obtained with features related to iEEG signal energy (accuracy of 0.97, precision of 0.96, sensitivity of 0.99, and specificity of 0.96), as well as features related to chaos, Lyapunov exponents, and fractal dimension (accuracy, precision, sensitivity, and specificity all equal to 0.95). The application of CNN and LSTM networks yielded significantly better results (CNN: Accuracy of 0.99, precision of 0.98, sensitivity of 1, and specificity of 0.99; LSTM: Accuracy of 0.98, precision of 0.96, sensitivity of 1, and specificity of 0.99). Additionally, the use of the gradient-weighted class activation mapping algorithm identified iEEG signal fragments that played a significant role in seizure detection.

Epilepsy, a prevalent neurological disorder, profoundly affects patients’ quality of life due to the unpredictable nature of seizures. The development of a reliable and user-friendly wearable EEG system capable of detecting and predicting seizures has the potential to revolutionize epilepsy care. However, optimizing electrode configurations for such systems, which is crucial for balancing accuracy and practicality, remains to be explored. This study addresses this gap by developing a systematic approach to optimize electrode configurations for a seizure detection machine-learning algorithm. Our approach was applied to an extensive database of prolonged annotated EEG recordings from 158 epilepsy patients. Multiple electrode configurations ranging from one to eighteen were assessed to determine the optimal number of electrodes. Results indicated that the performance was initially maintained as the number of electrodes decreased, but a drop in performance was found to have occurred at around eight electrodes. Subsequently, a comprehensive analysis of all eight-electrode configurations was conducted using a computationally intensive workflow to identify the optimal configurations. This approach can inform the mechanical design process of an EEG system that balances seizure detection accuracy with the ease of use and portability. Additionally, this framework holds potential for optimizing hardware in other machine learning applications. The study presents a significant step towards the development of an efficient wearable EEG system for seizure detection.

ObjectiveA recent multicenter prospective study (DECIDE trial) examined the use of Ceribell Rapid Response EEG (Rapid-EEG) in the emergent evaluation and management of critically ill patients suspected to have non-convulsive seizures. We present a detailed, patient-level examination of seizures detected either on initial Rapid-EEG or subsequent conventional EEG within 24 h to investigate whether seizures were missed on Rapid-EEG due to the exclusion of midline/parasagittal coverage.MethodsWe identified from 164 patients studied in the DECIDE trial those who had seizures detected on Rapid-EEG but not conventional EEG (n = 6), conventional EEG but not Rapid-EEG (n = 4), or both Rapid-EEG and conventional EEG (n = 9). We examined the electrographic characteristics of ictal and interictal findings on both devices, especially their detection in lateral or midline/parasagittal chains, and patient clinical histories to identify contributors toward discordant seizure detection.ResultsSeizures detected on both EEG systems had similar electrographic appearance and laterality. Seizures detected only on conventional EEG (within 24 h following Rapid-EEG) were visible in the temporal chains, and external clinical factors (e.g., treatment with anti-seizure medications, sedation, and duration of recordings) explained the delayed presentation of seizures. Patients with seizures detected only by Rapid-EEG were treated with anti-seizure medications, and subsequent conventional EEG detected interictal highly epileptiform patterns with similar laterality.ConclusionsOur case series demonstrates that electrographic data obtained from initial Rapid-EEG and subsequent conventional EEG monitoring are largely concordant relative to morphology and laterality. These findings are valuable to inform future investigation of abbreviated EEG systems to optimize management of suspected non-convulsive seizures and status epilepticus. Future, larger studies could further investigate the value of Rapid-EEG findings for forecasting and predicting seizures in long-term EEG recordings.

Neonatal seizure is an important clinical symptom of brain dysfunction, which is more common in infancy than in childhood. At present, video electroencephalogram (VEEG) technology is widely used in clinical practice. However, video electroencephalogram technology has several disadvantages. For example, the wires connecting the medical instruments may interfere with the infant’s movement and the gel patch electrode or disk electrode commonly used to monitor EEG may cause skin allergies or even tears. For the above reasons, we developed a wearable multi-sensor platform for newborns to collect physiological and movement signals. In this study, we designed a second-generation multi-sensor platform and developed an automatic detection algorithm for neonatal seizures based on ECG, respiration and acceleration. Data for 38 neonates were recorded at the Children’s Hospital of Fudan University in Shanghai. The total recording time was approximately 300 h. Four of the patients had seizures during data collection. The total recording time for the four patients was approximately 34 h, with 30 seizure episodes recorded. These data were evaluated by the algorithm. To evaluate the effectiveness of combining ECG, respiration and movement, we compared the performance of three types of seizure detectors. The first detector included features from ECG, respiration and acceleration records; the second detector incorporated features based on respiratory movement from respiration and acceleration records; and the third detector used only ECG-based features from ECG records. Our study illustrated that, compared with the detector utilizing individual modal features, multi-modal feature detectors could achieve favorable overall performance, reduce false alarm rates and give higher F-measures.

Long-term home monitoring of people living with epilepsy cannot be achieved using the standard full-scalp electroencephalography (EEG) coupled with video. Wearable seizure detection devices, such as behind-the-ear EEG (bte-EEG), offer an unobtrusive method for ambulatory follow-up of this population. Combining bte-EEG with electrocardiography (ECG) can enhance automated seizure detection performance. However, such frameworks produce high false alarm rates, making visual review necessary. This study aimed to evaluate a semi-automated multimodal wearable seizure detection framework using bte-EEG and ECG. Using the SeizeIT1 dataset of 42 patients with focal epilepsy, an automated multimodal seizure detection algorithm was used to produce seizure alarms. Two reviewers evaluated the algorithm’s detections twice: (1) using only bte-EEG data and (2) using bte-EEG, ECG, and heart rate signals. The readers achieved a mean sensitivity of 59.1% in the bte-EEG visual experiment, with a false detection rate of 6.5 false detections per day. Adding ECG resulted in a higher mean sensitivity (62.2%) and a largely reduced false detection rate (mean of 2.4 false detections per day), as well as an increased inter-rater agreement. The multimodal framework allows for efficient review time, making it beneficial for both clinicians and patients.

This paper presents a trainable hybrid approach involving a shallow autoencoder (AE) and a conventional classifier for epileptic seizure detection. The signal segments of a channel of electroencephalogram (EEG) (EEG epochs) are classified as epileptic and non-epileptic by employing its encoded AE representation as a feature vector. Analysis on a single channel-basis and the low computational complexity of the algorithm allow its use in body sensor networks and wearable devices using one or few EEG channels for wearing comfort. This enables the extended diagnosis and monitoring of epileptic patients at home. The encoded representation of EEG signal segments is obtained based on training the shallow AE to minimize the signal reconstruction error. Extensive experimentation with classifiers has led us to propose two versions of our hybrid method: (a) one yielding the best classification performance compared to the reported methods using the k-nearest neighbor (kNN) classifier and (b) the second with a hardware-friendly architecture and yet with the best classification performance compared to other reported methods in this category using a support-vector machine (SVM) classifier. The algorithm is evaluated on the Children’s Hospital Boston, Massachusetts Institute of Technology (CHB-MIT), and University of Bonn EEG datasets. The proposed method achieves 98.85% accuracy, 99.29% sensitivity, and 98.86% specificity on the CHB-MIT dataset using the kNN classifier. The best figures using the SVM classifier for accuracy, sensitivity, and specificity are 99.19%, 96.10%, and 99.19%, respectively. Our experiments establish the superiority of using an AE approach with a shallow architecture to generate a low-dimensionality yet effective EEG signal representation capable of high-performance abnormal seizure activity detection at a single-channel EEG level and with a fine granularity of 1 s EEG epochs.

The unpredictable nature of seizures is challenging for caregivers of epileptic dogs, which calls the need for other management strategies such as seizure detection devices. Seizure detection devices are systems that rely on non-electroencephalographic (non-EEG) ictal changes, designed to detect seizures. The aim for its use in dogs would be to provide owners with a more complete history of their dog's seizures and to help install prompt (and potentially life-saving) intervention. Although seizure detection via wearable intracranial EEG recordings is associated with a higher sensitivity in humans, there is robust evidence for reliable detection of generalized tonic-clonic seizures (GTCS) using non-EEG devices. Promising non-EEG changes described in epileptic humans, include heart rate variability (HRV), accelerometry (ACM), electrodermal activity (EDA), and electromyography (EMG). Their sensitivity and false detection rate to detect seizures vary, however direct comparison of studies is nearly impossible, as there are many differences in study design and standards for testing. A way to improve sensitivity and decrease false-positive alarms is to combine the different parameters thereby profiting from the strengths of each one. Given the challenges of using EEG in veterinary clinical practice, non-EEG ictal changes could be a promising alternative to monitor seizures more objectively. This review summarizes various seizure detection devices described in the human literature, discusses their potential use and limitations in veterinary medicine and describes what is currently known in the veterinary literature.

Caregivers of dogs with epilepsy experience severe stress due to unpredictable seizures. Hence, they feel the need for a better management strategy. A seizure detection system (SDS), which can identify seizures and provide notifications to caregivers immediately, is required to address this issue. The current study aimed to establish a wearable automatic SDS using acceleration data and the Mahalanobis distance and to preliminarily investigate its feasibility among dogs. A generalized tonic–clonic seizure (GTCS) was targeted because it is the most common type of seizure and can have serious consequences (i.e., status epilepticus). This study comprised three phases. First, the reference datasets of epileptic and non-epileptic activities were established using acceleration data of GTCSs in 3 dogs and daily activities in 27 dogs. Second, the GTCS-detecting algorithm was created using the reference datasets and was validated using other acceleration data of GTCSs in 4 epileptic dogs and daily activities in 27 dogs. Third, a feasibility test of the SDS prototype was performed in three dogs with epilepsy. The algorithm was effective in identifying all acceleration data of GTCSs as seizures and all acceleration data of daily activities as non-seizure activities. Dogs with epilepsy were monitored with the prototype for 48–72 h, and three GTCSs were identified. The prototype detected all GTCSs accurately. A false positive finding was not obtained unless the accelerometer was displaced. Hence, a method that can detect epileptic seizures, particularly GTCSs, was established. Nevertheless, further large-scale studies must be conducted before the method can be commercialized.