Seizure Detection Performance Research Articles

AI in ECG: Validating an ambulatory semiology labeller and predictor

ObjectivesEarly prediction of epileptic seizures can help reduce morbidity and mortality. In this work, we explore using electrocardiographic (ECG) signal as input to a seizure prediction system and note that the performance can be improved by using selected signal processing techniques. MethodsWe used frequency domain analysis with a deep neural network backend for all our experiments in this work. We further analysed the effect of the proposed system for different seizure semiologies and prediction horizons. We explored refining the signal using signal processing to enhance the system's performance. ResultsOur final system using the Temple University Hospital’s Seizure (TUHSZ) corpus gave an overall prediction accuracy of 84.02 %, sensitivity of 87.59 %, specificity of 81.9 %, and an area under the receiver operating characteristic curve (AUROC) of 0.9112. Notably, these results surpassed the state-of-the-art outcomes reported using the TUHSZ database; all findings are statistically significant. We also validated our study using the Siena scalp EEG database. Using the frequency domain data, our baseline system gave a performance of 75.17 %, 79.17 %, 70.04 % and 0.82 for prediction accuracy, sensitivity, specificity and AUROC, respectively. After selecting the optimal frequency band of 0.8–15 Hz, we obtained a performance of 80.49 %, 89.51 %, 75.23 % and 0.89 for prediction accuracy, sensitivity, specificity and AUROC, respectively which is an improvement of 5.32 %, 10.34 %, 5.19 % and 0.08 for prediction accuracy, sensitivity, specificity and AUROC, respectively. ConclusionsThe seizure information in ECG is concentrated in a narrow frequency band. Identifying and selecting that band can help improve the performance of seizure detection and prediction. SignificanceEEG is susceptible to artefacts and is not preferred in a low-cost ambulatory device. ECG can be used in wearable devices (like chest bands) and is feasible for developing a low-cost ambulatory device for seizure prediction. Early seizure prediction can provide patients and clinicians with the required alert to take necessary precautions and prevent a fatality, significantly improving the patient’s quality of life.

Autonomic biosignals, seizure detection, and forecasting.

Wearable devices have attracted significant attention in epilepsy research in recent years for their potential to enhance patient care through improved seizure monitoring and forecasting. This narrative review presents a detailed overview of the current clinical state of the art while addressing how devices that assess autonomic nervous system (ANS) function reflect seizures and central nervous system (CNS) state changes. This includes a description of the interactions between the CNS and the ANS, including physiological and epilepsy-related changes affecting their dynamics. We first discuss technical aspects of measuring autonomic biosignals and considerations for using ANS sensors in clinical practice. We then review recent seizure detection and seizure forecasting studies, highlighting their performance and capability for seizure detection and forecasting using devices measuring ANS biomarkers. Finally, we address the field's challenges and provide an outlook for future developments.

End-to-end model for automatic seizure detection using supervised contrastive learning

Epilepsy is a chronic neurological disorder characterized by recurrent and unpredictable seizures, caused by abnormal electrical activity in cerebral neurons. Given that it is one of the most common neurological disorders globally, the efficient and accurate automatic seizure detection is urgently needed in the diagnosis of epilepsy to reduce the workload of continuous electroencephalogram (EEG) monitoring. Current deep learning based seizure detection approaches usually employ cross-entropy loss as objective function, which generally suffer from inadequate utilization of sample labels and poor classification margins, resulting in decreased performance in seizure detection. In this study, we propose an end-to-end automatic seizure detection framework based on supervised contrastive learning, which effectively utilizes labeled EEG to cluster similar samples while separating dissimilar ones. A supervised contrastive learning loss is employed to optimize classification boundaries by making full use of EEG labels. We employ long-term continuous EEG for evaluation. Given the presence of various noise and interferences, assessment on long-term continuous EEG proves to be more challenging. Post-processing techniques such as smoothing filter, threshold judgment, and collar technique are further adopted to diminish the artifact impacts on seizure detection performance. The proposed method is evaluated on the publicly available Children's Hospital Boston and the Massachusetts Institute of Technology (CHB-MIT) scalp EEG dataset, achieving an event-based sensitivity of 99.71% and a false detection rate (FDR) of 0.35/h.

Single-channel seizure detection with clinical confirmation of seizure locations using CHB-MIT dataset.

Long-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. We 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. Our 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. We 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.

Automated analysis and detection of epileptic seizures in video recordings using artificial intelligence.

Automated seizure detection promises to aid in the prevention of SUDEP and improve the quality of care by assisting in epilepsy diagnosis and treatment adjustment. In 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). At 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. These results indicate an achievable performance for major motor seizure detection that is clinically applicable for use as a seizure screening solution in diagnostic workflows.

Detection of seizures with ictal tachycardia, using heart rate variability and patient adaptive logistic regression machine learning methods: A hospital-based validation study.

Automated seizure detection of focal epileptic seizures is needed for objective seizure quantification to optimize the treatment of patients with epilepsy. Heart rate variability (HRV)-based seizure detection using patient-adaptive threshold with logistic regression machine learning (LRML) methods has presented promising performance in a study with a Danish patient cohort. The objective of this study was to assess the generalizability of the novel LRML seizure detection algorithm by validating it in a dataset recorded from long-term video-EEG monitoring (LTM) in a Brazilian patient cohort. Ictal and inter-ictal ECG-data epochs recorded during LTM were analyzed retrospectively. Thirty-four patients had 107 seizures (79 focal, 28 generalized tonic-clonic [GTC] including focal-to-bilateral-tonic-clonic seizures) eligible for analysis, with a total of 185.5 h recording. Because HRV-based seizure detection is only suitable in patients with marked ictal autonomic change, patients with >50 beats/min change in heart rate during seizures were selected as responders. The patient-adaptive LRML seizure detection algorithm was applied to all elected ECG data, and results were computed separately for responders and non-responders. The patient-adaptive LRML seizure detection algorithm yielded a sensitivity of 84.8% (95% CI: 75.6-93.9) with a false alarm rate of .25/24 h in the responder group (22 patients, 59 seizures). Twenty-five of the 26 GTC seizures were detected (96.2%), and 25 of the 33 focal seizures without bilateral convulsions were detected (75.8%). The study confirms in a new, independent external dataset the good performance of seizure detection from a previous study and suggests that the method is generalizable. This method seems useful for detecting both generalized and focal epileptic seizures. The algorithm can be embedded in a wearable seizure detection system to alert patients and caregivers of seizures and generate objective seizure counts helping to optimize the treatment of the patients.

An improved GBSO-TAENN-based EEG signal classification model for epileptic seizure detection

Detection and classification of epileptic seizures from the EEG signals have gained significant attention in recent decades. Among other signals, EEG signals are extensively used by medical experts for diagnosing purposes. So, most of the existing research works developed automated mechanisms for designing an EEG-based epileptic seizure detection system. Machine learning techniques are highly used for reduced time consumption, high accuracy, and optimal performance. Still, it limits by the issues of high complexity in algorithm design, increased error value, and reduced detection efficacy. Thus, the proposed work intends to develop an automated epileptic seizure detection system with an improved performance rate. Here, the Finite Linear Haar wavelet-based Filtering (FLHF) technique is used to filter the input signals and the relevant set of features are extracted from the normalized output with the help of Fractal Dimension (FD) analysis. Then, the Grasshopper Bio-Inspired Swarm Optimization (GBSO) technique is employed to select the optimal features by computing the best fitness value and the Temporal Activation Expansive Neural Network (TAENN) mechanism is used for classifying the EEG signals to determine whether normal or seizure affected. Numerous intelligence algorithms, such as preprocessing, optimization, and classification, are used in the literature to identify epileptic seizures based on EEG signals. The primary issues facing the majority of optimization approaches are reduced convergence rates and higher computational complexity. Furthermore, the problems with machine learning approaches include a significant method complexity, intricate mathematical calculations, and a decreased training speed. Therefore, the goal of the proposed work is to put into practice efficient algorithms for the recognition and categorization of epileptic seizures based on EEG signals. The combined effect of the proposed FLHF, FD, GBSO, and TAENN models might dramatically improve disease detection accuracy while decreasing complexity of system along with time consumption as compared to the prior techniques. By using the proposed methodology, the overall average epileptic seizure detection performance is increased to 99.6% with f-measure of 99% and G-mean of 98.9% values.

The ENCEVIS algorithm in the EMU and the factors affecting its performance: Our experience

The study's purpose was to assess the seizure detection performance of ENCEVIS 1.7, identify factors that may influence algorithm performance, and explore its potential for implementation and application in long-term video EEG monitoring units. The study included video-EEG recordings containing at least one epileptic seizure. Forty-three recordings, encompassing 112 seizures, were included in the analysis. True positive, false negative, and false positive seizure detections were defined. Factors that may influence algorithm performance were studied. ENCEVIS demonstrated an overall sensitivity of 71.2%, significantly higher (75.1%) in focal compared to generalized seizures (62%). Ictal patterns rhythmicity (rhythmic 59.4 %, arrhythmic 41.7 %), seizure duration (<10 sec 6.3 %, >60 sec. 63.9 % (p < 0.05)) and patient age (<18 years 39.5 %, >18 years 58.1 % (P < 0.05)) influenced ENCEVIS sensitivity. The coexistence of extracerebral signal changes did not influence sensitivity. ENCEVIS with 79.1% accuracy annotates at least one seizure in those recordings containing epileptic seizures. ENCEVIS seizure detection performance was reasonable for generalized/focal to bilateral tonic-clonic seizures and seizures with temporal lobe onset. Rhythmic ictal patterns, longer seizure duration, and adult age positively influenced algorithm performance. ENCEVIS can be a valuable tool for identifying recordings containing seizures and can potentially reduce the workload of neurophysiologists.

Diagnosing epileptic seizures using combined features from independent components and prediction probability from EEG data.

Epileptic seizures are neurological events that pose significant risks of physical injuries characterized by sudden, abnormal bursts of electrical activity in the brain, often leading to loss of consciousness and uncontrolled movements. Early seizure detection is essential for timely treatments and better patient outcomes. To address this critical issue, there is a need for an advanced artificial intelligence approach for the early detection of epileptic seizure disorder. This study primarily focuses on designing a novel ensemble approach to perform early detection of epileptic seizure disease with high performance. A novel ensemble approach consisting of a fast, independent component analysis random forest (FIR) and prediction probability is proposed, which uses electroencephalography (EEG) data to investigate the efficacy of the proposed approach for early detection of epileptic seizures. The FIR model extracts independent components and class prediction probability features, creating a new feature set. The proposed model combined integrated component analysis (ICA) with predicting probability to enhance seizure recognition accuracy scores. Extensive experimental evaluations demonstrate that FIR assists machine learning models to obtain superior results compared to original features. The research gap is addressed using combined features to improve the performance of epileptic seizure detection compared to a single feature set. In particular, the ensemble model FIR with support vector machine (FIR + SVM) outperforms other methods, achieving an accuracy of 98.4% for epileptic seizure detection. The proposed FIR has the potential for early diagnosis of epileptic seizures and can significantly help the medical industry with enhanced detection and timely interventions.

Comparison of patient non-specific seizure detection using multi-modal signals

Epilepsy is the neurological disorder affecting around 50 million people worldwide. It is characterized by recurrent and unpredictable seizures. Correctly counting seizure occurrences is crucial for diagnosis and treatment of epilepsy, which will lower the risk of SUDEP (sudden unexpected deaths in epilepsy). Many previous researches on patient-specific seizure detection have obtained a good performance but with limited practicability in clinical setting. On the other hand, patient non-specific detection is clinically practicable but with limited performance. This study aims to improve the performance of patient non-specific seizure detection by comparing performances among one modality based models and multi-modal based model. The study was based on clinical data from the open source Siena Scalp EEG Database, which consist of simultaneous EEG (Electroenchephalography) and ECG (electrocardiography) recording from 14 patients with focal epilepsy. The seizures were annotated by an epilepsy expert after a careful review of the clinical and EEG data of each patient. First, relevant signal pre-processing were performed, followed by features extraction. Then, machine learning approach based on random forest was employed for seizure detection with leave-one-patient-out cross validation scheme. EEG detector and ECG detector were separately trained with each signal. Multi-modal detector was based on combining EEG detector and ECG detector by the late integration approach with the Boolean operation “OR” strategy. The performances were compared among those three detectors and with the state of the art. The result has shown that the multi-modal detector achieved a sensitivity of 87.62% and outperformed the ECG detector (41.55%), the EEG detector (81.43%), and the state-of-the-art non-specific detectors. Notably, the ECG detector detected some seizures which EEG detector failed to detect. This indicated that the ECG signal was beneficial for increasing sensitivity. However, due to the “OR” fusion strategy, the multi-modal detector also inherited the false detections resulted from either EEG detector or ECG detector. The findings of the study demonstrate the potential of improving performance of patient non-specific seizure detection by multimodal data. It shows that the proposed method should be further validated on large database and further development should focus on lowering false detections before clinical application.

SeizFt: Interpretable Machine Learning for Seizure Detection Using Wearables.

This work presents SeizFt-a novel seizure detection framework that utilizes machine learning to automatically detect seizures using wearable SensorDot EEG data. Inspired by interpretable sleep staging, our novel approach employs a unique combination of data augmentation, meaningful feature extraction, and an ensemble of decision trees to improve resilience to variations in EEG and to increase the capacity to generalize to unseen data. Fourier Transform (FT) Surrogates were utilized to increase sample size and improve the class balance between labeled non-seizure and seizure epochs. To enhance model stability and accuracy, SeizFt utilizes an ensemble of decision trees through the CatBoost classifier to classify each second of EEG recording as seizure or non-seizure. The SeizIt1 dataset was used for training, and the SeizIt2 dataset for validation and testing. Model performance for seizure detection was evaluated using two primary metrics: sensitivity using the any-overlap method (OVLP) and False Alarm (FA) rate using epoch-based scoring (EPOCH). Notably, SeizFt placed first among an array of state-of-the-art seizure detection algorithms as part of the Seizure Detection Grand Challenge at the 2023 International Conference on Acoustics, Speech, and Signal Processing (ICASSP). SeizFt outperformed state-of-the-art black-box models in accurate seizure detection and minimized false alarms, obtaining a total score of 40.15, combining OVLP and EPOCH across two tasks and representing an improvement of ~30% from the next best approach. The interpretability of SeizFt is a key advantage, as it fosters trust and accountability among healthcare professionals. The most predictive seizure detection features extracted from SeizFt were: delta wave, interquartile range, standard deviation, total absolute power, theta wave, the ratio of delta to theta, binned entropy, Hjorth complexity, delta + theta, and Higuchi fractal dimension. In conclusion, the successful application of SeizFt to wearable SensorDot data suggests its potential for real-time, continuous monitoring to improve personalized medicine for epilepsy.

The Power of ECG in Semi-Automated Seizure Detection in Addition to Two-Channel behind-the-Ear EEG.

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.

Progressive alterations in electrophysiological and epileptic network properties during the development of temporal lobe epilepsy in rats

ObjectiveRefractory temporal lobe epilepsy (TLE) with recurring seizures causing continuing pathological changes in neural reorganization. There is an incomplete understanding of how spatiotemporal electrophysiological characteristics changes during the development of TLE. Long-term multi-site epilepsy patients’ data is hard to obtain. Thus, our study relied on animal models to reveal the changes in electrophysiological and epileptic network characteristics systematically. MethodsLong-term local field potentials (LFPs) were recorded over a period of 1 to 4 months from 6 pilocarpine-treated TLE rats. We compared variations of seizure onset zone (SOZ), seizure onset pattern (SOP), the latency of seizure onsets, and functional connectivity network from 10-channel LFPs between the early and late stages. Moreover, three machine learning classifiers trained by early-stage data were used to test seizure detection performance in the late stage. ResultsCompared to the early stage, the earliest seizure onset was more frequently detected in hippocampus areas in the late stage. The latency of seizure onsets between electrodes became shorter. Low-voltage fast activity (LVFA) was the most common SOP and the proportion of it increased in the late stage. Different brain states were observed during seizures using Granger causality (GC). Moreover, seizure detection classifiers trained by early-stage data were less accurate when tested in late-stage data. SignificanceNeuromodulation especially closed-loop deep brain stimulation (DBS) is effective in the treatment of refractory TLE. Although the frequency or amplitude of the stimulation is generally adjusted in existing closed-loop DBS devices in clinical usage, the adjustment rarely considers the pathological progression of chronic TLE. This suggests that an important factor affecting the therapeutic effect of neuromodulation may have been overlooked. The present study reveals time-varying electrophysiological and epileptic network properties in chronic TLE rats and indicates that classifiers of seizure detection and neuromodulation parameters might be designed to adapt to the current state dynamically with the progression of epilepsy.

A difference attention ResNet-LSTM network for epileptic seizure detection using EEG signal

Epileptic seizures can affect the patient’s physical function and cause irreversible damage to their brain. It is vital to detect epilepsy seizures in time and give patients antiepileptic medical treatment. Hybrid deep learning models, which combine convolutional neural network and recurrent neural network, have better epileptic seizure detection performance as they could simultaneously extract spatial and temporal features. However, the existing hybrid deep learning models still have the following two weaknesses. Firstly, they directly input the raw electroencephalogram signals, where the epilepsy seizure information is limited. Secondly, some characteristic information is extracted in the feature map, distracting the attention of deep learning model. To address these issues, this paper proposes a difference attention ResNet-LSTM network (DARLNet). The proposed model uses a residual neural network (ResNet) and a long short-term memory network (LSTM) to capture spatial correlations and temporal dependencies, respectively. Besides, a difference layer is developed to automatically mine additional epileptic seizure information. Moreover, the channel attention module is introduced to make the model focus on seizure-relevant information. Several groups of experiments are conducted to evaluate the performance of DARLNet based on the Bonn Electroencephalogram dataset, which verifies the superiority of DARLNet on the two-category and five-category epileptic seizure detection tasks.

Patient-independent seizure detection based on long-term iEEG and a novel lightweight CNN

Objective. Patient-dependent seizure detection based on intracranial electroencephalography (iEEG) has made significant progress. However, due to the difference in the locations and number of iEEG electrodes used for each patient, patient-independent seizure detection based on iEEG has not been carried out. Additionally, current seizure detection algorithms based on deep learning have outperformed traditional machine learning algorithms in many performance metrics. However, they still have shortcomings of large memory footprints and slow inference speed. Approach. To solve the above problems of the current study, we propose a novel lightweight convolutional neural network model combining the Convolutional Block Attention Module (CBAM). Its performance for patient-independent seizure detection is evaluated on two long-term continuous iEEG datasets: SWEC-ETHZ and TJU-HH. Finally, we reproduce four other patient-independent methods to compare with our method and calculate the memory footprints and inference speed for all methods. Main results. Our method achieves 83.81% sensitivity (SEN) and 85.4% specificity (SPE) on the SWEC-ETHZ dataset and 86.63% SEN and 92.21% SPE on the TJU-HH dataset. In particular, it takes only 11 ms to infer 10 min iEEG (128 channels), and its memory footprint is only 22 kB. Compared to baseline methods, our method not only achieves better patient-independent seizure detection performance but also has a smaller memory footprint and faster inference speed. Significance. To our knowledge, this is the first iEEG-based patient-independent seizure detection study. This facilitates the application of seizure detection algorithms to the future clinic.

Cluster Embedding Joint-Probability-Discrepancy Transfer For Cross-subject Seizure Detection.

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.

Effects of Data Augmentation with the BNNSMOTE Algorithm in Seizure Detection Using 1D-MobileNet.

Automatic seizure detection technology has important implications for reducing the workload of neurologists for epilepsy diagnosis and treatment. Due to the unpredictable nature of seizures, the imbalanced classification of seizure and nonseizure data continues to be challenging. In this work, we first propose a novel algorithm named the borderline nearest neighbor synthetic minority oversampling technique (BNNSMOTE) to address the imbalanced classification problem and improve seizure detection performance. The algorithm uses the nearest neighbor notion to generate nonseizure samples near the boundary, then determines the seizure samples that are difficult to learn at the boundary, and lastly selects seizure samples at random to be used in the synthesis of new samples. In view of the characteristic that electroencephalogram (EEG) signals are one-dimensional signals, we then develop a 1D-MobileNet model to validate the algorithm's performance. Results demonstrate that the proposed algorithm outperforms previous seizure detection methods on the CHB-MIT dataset, achieving an average accuracy of 99.40%, a recall value of 87.46%, a precision of 97.17%, and an F1-score of 91.90%, respectively. We also had considerable success when we used additional datasets for verification at the same time. Our algorithm's data augmentation effects are more pronounced and perform better at seizure detection than the existing imbalanced techniques. Besides, the model's parameters and calculation volume have been significantly reduced, making it more suitable for mobile terminals and embedded devices.

Continuous Seizure Detection Based on Transformer and Long-Term iEEG.

Automatic seizure detection algorithms are necessary for patients with refractory epilepsy. Many excellent algorithms have achieved good results in seizure detection. Still, most of them are based on discontinuous intracranial electroencephalogram (iEEG) and ignore the impact of different channels on detection. This study aimed to evaluate the proposed algorithm using continuous, long-term iEEG to show its applicability in clinical routine. In this study, we introduced the ability of the transformer network to calculate the attention between the channels of input signals into seizure detection. We proposed an end-to-end model that included convolution and transformer layers. The model did not need feature engineering or format transformation of the original multi-channel time series. Through evaluation on two datasets, we demonstrated experimentally that the transformer layer could improve the performance of the seizure detection algorithm. For the SWEC-ETHZ iEEG dataset, we achieved 97.5% event-based sensitivity, 0.06/h FDR, and 13.7 s latency. For the TJU-HH iEEG dataset, we achieved 98.1% event-based sensitivity, 0.22/h FDR, and 9.9 s latency. In addition, statistics showed that the model allocated more attention to the channels close to the seizure onset zone within 20 s after the seizure onset, which improved the explainability of the model. This paper provides a new method to improve the performance and explainability of automatic seizure detection.

Automatic Epileptic Seizure Detection Using PSO-Based Feature Selection and Multilevel Spectral Analysis for EEG Signals

Automatic epileptic seizure detection technologies for clinical diagnosis mainly rely on electroencephalogram (EEG) recordings, which are immensely useful tools for epileptic location and identification. Currently, traditional seizure detection methods based only on single-view features have great limitations for the typical dynamic and nonlinear EEG signals. An objective of this paper is to investigate the effect of multiview feature selection and multilevel spectral analysis methods on the identification of the EEG signals for seizure detection. Here, multiview features are extracted from time domain, frequency domain, and information theory to collect adequate information of EEG signals. And a feature selection algorithm based on particle swarm optimization (PSO) is proposed for automatic seizure detection. Moreover, due to the different frequency components of the EEG signals, they are divided into four kinds of brain waves for multilevel spectral analysis. The effect of these four rhythm waves on seizure detection is compared. Three well-known classifiers are employed to classify EEG signals concerning seizure or nonseizure events. The result shows that the average accuracy, specificity, and sensitivity of classification with the CHB-MIT database are 98.14%, 98.64%, and 96.79%, respectively. The application of the PSO-based feature selection method for automatic seizure detection improves accuracy by 5.99% with the SVM classifier. Compared with the state-of-the-art methods, the proposed method has superior competence with high performance for automatic seizure detection. It is further shown that the feature selection method is an indispensable step in seizure detection. With PSO-based feature selection and multilevel spectral analysis, the θ wave in the frequency range of 4-7 Hz shows better performance in the identification of EEG signals and is more suitable for the proposed method. The PSO-based feature selection algorithm for automatic seizure detection can be a useful assistant tool for clinical diagnosis.

EEG-Based Epileptic Seizure Detection via Machine/Deep Learning Approaches: A Systematic Review.

Epileptic seizure is one of the most chronic neurological diseases that instantaneously disrupts the lifestyle of affected individuals. Toward developing novel and efficient technology for epileptic seizure management, recent diagnostic approaches have focused on developing machine/deep learning model (ML/DL)-based electroencephalogram (EEG) methods. Importantly, EEG's noninvasiveness and ability to offer repeated patterns of epileptic-related electrophysiological information have motivated the development of varied ML/DL algorithms for epileptic seizure diagnosis in the recent years. However, EEG's low amplitude and nonstationary characteristics make it difficult for existing ML/DL models to achieve a consistent and satisfactory diagnosis outcome, especially in clinical settings, where environmental factors could hardly be avoided. Though several recent works have explored the use of EEG-based ML/DL methods and statistical feature for seizure diagnosis, it is unclear what the advantages and limitations of these works are, which might preclude the advancement of research and development in the field of epileptic seizure diagnosis and appropriate criteria for selecting ML/DL models and statistical feature extraction methods for EEG-based epileptic seizure diagnosis. Therefore, this paper attempts to bridge this research gap by conducting an extensive systematic review on the recent developments of EEG-based ML/DL technologies for epileptic seizure diagnosis. In the review, current development in seizure diagnosis, various statistical feature extraction methods, ML/DL models, their performances, limitations, and core challenges as applied in EEG-based epileptic seizure diagnosis were meticulously reviewed and compared. In addition, proper criteria for selecting appropriate and efficient feature extraction techniques and ML/DL models for epileptic seizure diagnosis were also discussed. Findings from this study will aid researchers in deciding the most efficient ML/DL models with optimal feature extraction methods to improve the performance of EEG-based epileptic seizure detection.