Epileptic Seizure Detection and Experimental Treatment: A Review

Epileptic seizure detection using CHB-MIT dataset: The overlooked perspectives

Epilepsy is a life-threatening neurological condition. Manual detection of epileptic seizures (ES) is laborious and burdensome. Machine learning techniques applied to electroencephalography (EEG) signals are widely used for automatic seizure detection. Some key factors are worth considering for the real-world applicability of such systems: (i) continuous EEG data typically has a higher class imbalance; (ii) higher variability across subjects is present in physiological signals such as EEG; and (iii) seizure event detection is more practical than random segment detection. Most prior studies failed to address these crucial factors altogether for seizure detection. In this study, we intend to investigate a generalized cross-subject seizure event detection system using the continuous EEG signals from the CHB-MIT dataset that considers all these overlooked aspects. A 5-second non-overlapping window is used to extract 92 features from 22 EEG channels; however, the most significant 32 features from each channel are used in experimentation. Seizure classification is done using a Random Forest (RF) classifier for segment detection, followed by a post-processing method used for event detection. Adopting all the above-mentioned essential aspects, the proposed event detection system achieved 72.63% and 75.34% sensitivity for subject-wise 5-fold and leave-one-out analyses, respectively. This study presents the real-world scenario for ES event detectors and furthers the understanding of such detection systems.

A systematic review of the literature reporting on remote monitoring epileptic seizure detection devices

BACKGROUND

Early detection and alert notification of an impending seizure for people with epilepsy have the potential to reduce Sudden Unexpected Death in Epilepsy (SUDEP). Current remote monitoring seizure detection devices for people with epilepsy are designed to support real-time monitoring of their vital health parameters linked to seizure alert notification. An understanding of the rapidly growing literature on remote seizure detection devices is essential to address the needs of people with epilepsy and their carers.

AIM

This review aims to examine the technical characteristics, device performance, user preference, and effectiveness of remote monitoring seizure detection devices.

METHODOLOGY

A systematic review referenced to PRISMA guidelines was used.

RESULTS

A total of 1095 papers were identified from the initial search with 30 papers included in the review. Sixteen non-invasive remote monitoring seizure detection devices are currently available. Such seizure detection devices were found to have inbuilt intelligent sensor functionality to monitor electroencephalography, muscle movement, and accelerometer-based motion movement for detecting seizures remotely. Current challenges of these devices for people with epilepsy include skin irritation due to the type of patch electrode used and false alarm notifications, particularly during physical activity. The tight-fitted accelerometer-type devices are reported as uncomfortable from a wearability perspective for long-term monitoring. Also, continuous recording of physiological signals and triggering alert notifications significantly reduce the battery life of the devices. The literature highlights that 3.2 out of 5 people with epilepsy are not using seizure detection devices because of the cost and appearance of the device.

CONCLUSION

Seizure detection devices can potentially reduce morbidity and mortality for people with epilepsy. Therefore, further collaboration of clinicians, technical experts, and researchers is needed for the future development of these devices. Finally, it is important to always take into consideration the expectations and requirements of people with epilepsy and their carers to facilitate the next generation of remote monitoring seizure detection devices.

An approach to detect and predict epileptic seizures with high accuracy using convolutional neural networks and single-lead-ECG signal

One of the epileptic patients' challenges is to detect the time of seizures and the possibility of predicting. This research aims to provide an algorithm based on deep learning to detect and predict the time of seizure from one to two minutes before its occurrence. The proposed Convolutional Neural Network (CNN) can detect and predict the occurrence of focal epilepsy seizures through single-lead-ECG signal processing instead of using EEG signals. The structure of the proposed CNN for seizure detection and prediction is the same. Considering the requirements of a wearable system, after a few light pre-processing steps, the ECG signal can be used as input to the neural network without any manual feature extraction step. The desired neural network learns purposeful features according to the labelled ECG signals and then performs the classification of these signals. Training of 39-layer CNN for seizure detection and prediction has been done separately. The proposed method can detect seizures with an accuracy of 98.84% and predict them with an accuracy of 94.29%. With this approach, the ECG signal can be a promising indicator for the construction of portable systems for monitoring the status of epileptic patients.

Optimizing Electrode Configurations for Wearable EEG Seizure Detection Using Machine Learning

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.

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

OBJECTIVE

Refractory 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.

METHODS

Long-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.

RESULTS

Compared 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.

SIGNIFICANCE

Neuromodulation 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.

Electroceutical and Bioelectric Therapy: Its Advantages and Limitations

Given the long history, the field of electroceutical and bioelectric therapy has grown impressively, recognized as the main modality of mental health treatments along with psychotherapy and pharmacotherapy. Electroceutical and bioelectric therapy comprises electroconvulsive therapy (ECT), vagus nerve stimulation (VNS), repetitive transcranial magnetic stimulation (rTMS), deep brain stimulation (DBS), transcranial electrical stimulation (tES), and other brain stimulation techniques. Much empirical research has been published regarding the application guidelines, mechanism of action, and efficacy of respective brain stimulation techniques, but no comparative study that delineates the advantages and limitations of each therapy exists for a comprehensive understanding of each technique. This review provides a comparison of existing electroceutical and bioelectric techniques, primarily focusing on the therapeutic advantages and limitations of each therapy in the current electroceutical and bioelectric field.

Ictal fMRI: Mapping Seizure Topography with Rhythmic BOLD Oscillations

Functional magnetic resonance imaging (fMRI) has shown elevations in the blood-oxygen-level-dependent (BOLD) signal associated with, but insensitive for, seizure. Rather than evaluating absolute BOLD signal elevations, assessing rhythmic oscillations in the BOLD signal with fMRI may improve the accuracy of seizure mapping. We report a case of a patient with non-convulsive, right hemispheric seizures who underwent fMRI. Unbiased processing methods revealed a map of rhythmically oscillating BOLD signal over the cortical region affected by seizure, and synchronous BOLD signal in the contralateral cerebellum. High-resolution fMRI may help identify the spatial topography of seizure and provide insights into seizure physiology.

Accurate detection of heart rate using in-ear photoplethysmography in a clinical setting

Background

Recent research has shown that photoplethysmography (PPG) based wearable sensors offer a promising potential for chronic disease monitoring. The aim of the present study was to assess the performance of an in-ear wearable PPG sensor in acquiring valid and reliable heart rate measurements in a clinical setting, with epileptic patients.

Methods

Patients undergoing video-electroencephalography (EEG) monitoring with concomitant one-lead electrocardiographic (ECG) recordings were equipped with an in-ear sensor developed by cosinuss°.

Results

In total, 2,048 h of recording from 97 patients with simultaneous ECG and in-ear heart rate data were included in the analysis. The comparison of the quality-filtered in-ear heart rate data with the reference ECG resulted in a bias of 0.78 bpm with a standard deviation of ±2.54 bpm; Pearson's Correlation Coefficient PCC = 0.83; Intraclass Correlation Coefficient ICC = 0.81 and mean absolute percentage error MAPE = 2.57.

Conclusion

These data confirm that the in-ear wearable PPG sensor provides accurate heart rate measurements in comparison with ECG under realistic clinical conditions, especially with a signal quality indicator. Further research is required to investigate whether this technology is helpful in identifying seizure-related cardiovascular changes.

Optimized Design of a Self-Biased Amplifier for Seizure Detection Supplied by Piezoelectric Nanogenerator: Metaheuristic Algorithms versus ANN-Assisted Goal Attainment Method

This work is dedicated to parameter optimization for a self-biased amplifier to be used in preamplifiers for the diagnosis of seizures in neuro-diseases such as epilepsy. For the sake of maximum compactness, which is obligatory for all implantable devices, power is to be supplied by a piezoelectric nanogenerator (PENG). Several meta-heuristic optimization algorithms and an ANN (artificial neural network)-assisted goal attainment method were applied to the circuit, aiming to provide us with the set of optimal design parameters which ensure the minimal overall area of the preamplifier. These parameters are the slew rate, load capacitor, gain–bandwidth product, maximal input voltage, minimal input voltage, input voltage, reference voltage, and dissipation power. The results are re-evaluated and compared in the Cadence 180 nm SCL environment. It has been observed that, among the metaheuristic algorithms, the whale optimization technique reached the best values at low computational cost, decreased complexity, and the highest convergence speed. However, all metaheuristic algorithms were outperformed by the ANN-assisted goal attainment method, which produced a roughly 50% smaller overall area of the preamplifier. All the techniques described here are applicable to the design and optimization of wearable or implantable circuits.

Future Opportunities for Research in Rescue Treatments

Clinical studies of rescue medications for seizure clusters are limited and are designed to satisfy regulatory requirements, which may not fully consider the needs of the diverse patient population that experiences seizure clusters or utilize rescue medication. The purpose of this narrative review is to examine the factors that contribute to, or may influence the quality of, seizure cluster research with a goal of improving clinical practice. We address five areas of unmet needs and provide advice for how they could enhance future trials of seizure cluster treatments. The topics addressed in this article are: (1) unaddressed end points to pursue in future studies, (2) roles for devices to enhance rescue medication clinical development programs, (3) tools to study seizure cluster prediction and prevention, (4) the value of other designs for seizure cluster studies, and (5) unique challenges of future trial paradigms for seizure clusters. By focusing on novel end points and technologies with value to patients, caregivers, and clinicians, data obtained from future studies can benefit the diverse patient population that experiences seizure clusters, providing more effective, appropriate care as well as alleviating demands on health care resources.

Involvement of the Anterior Nucleus of the Thalamus during Focal Automatisms in Epileptic Seizures: A First Evidence Study

The Anterior Nucleus of Thalamus (ANT) Deep Brain Stimulation (DBS) has long been touted as the most effective DBS-target for interrupting seizures in focal refractory epilepsy patients. The ANT is primarily involved in cognitive tasks but has extensive reciprocal connections with motor-related regions, suggesting that it is also involved in motor-cognitive tasks. In this work, we aimed to assess the involvement of the ANT during voluntary upper limbs movements. For this purpose, we analyzed Local Field Potentials (LFPs) signals recorded during a movement protocol from one of the first epilepsy patients implanted with a Percept™ PC system, who performed a 5-day period of simultaneous video electroencephalography (vEEG) and Percept PC-LFPs recordings. We estimated time-frequency maps and performed event-related desynchronization (ERD) or synchronization (ERS) analysis and we found that synchronizations found in left hemisphere 7-17 Hz map corresponded to maximum hand rotations. Positive peaks on the ERD/ERS curve occurred at a similar frequency of the hand movements ([Formula: see text] against [Formula: see text]). These results suggested that the ANT may be involved in the execution of automatisms. Moreover, we found that ERD/ERS appeared approximately 2 seconds before the movement onset, as it was found on the EEG of healthy subjects performing the same protocol.

An On-Demand Drug Delivery System for Control of Epileptiform Seizures

Drug delivery systems have the potential to deliver high concentrations of drug to target areas on demand, while elsewhere and at other times encapsulating the drug, to limit unwanted actions. Here we show proof of concept in vivo and ex vivo tests of a novel drug delivery system based on hollow-gold nanoparticles tethered to liposomes (HGN-liposomes), which become transiently permeable when activated by optical or acoustic stimulation. We show that laser or ultrasound simulation of HGN-liposomes loaded with the GABA_A receptor agonist, muscimol, triggers rapid and repeatable release in a sufficient concentration to inhibit neurons and suppress seizure activity. In particular, laser-stimulated release of muscimol from previously injected HGN-liposomes caused subsecond hyperpolarizations of the membrane potential of hippocampal pyramidal neurons, measured by whole cell intracellular recordings with patch electrodes. In hippocampal slices and hippocampal–entorhinal cortical wedges, seizure activity was immediately suppressed by muscimol release from HGN-liposomes triggered by laser or ultrasound pulses. After intravenous injection of HGN-liposomes in whole anesthetized rats, ultrasound stimulation applied to the brain through the dura attenuated the seizure activity induced by pentylenetetrazol. Ultrasound alone, or HGN-liposomes without ultrasound stimulation, had no effect. Intracerebrally-injected HGN-liposomes containing kainic acid retained their contents for at least one week, without damage to surrounding tissue. Thus, we demonstrate the feasibility of precise temporal control over exposure of neurons to the drug, potentially enabling therapeutic effects without continuous exposure. For future application, studies on the pharmacokinetics, pharmacodynamics, and toxicity of HGN-liposomes and their constituents, together with improved methods of targeting, are needed, to determine the utility and safety of the technology in humans.

A channel independent generalized seizure detection method for pediatric epileptic seizures

BACKGROUND AND OBJECTIVE

Epilepsy the disorder of the central nervous system has its worldwide presence in roughly 50 million people as estimated by the World Health Organization. Electroencephalogram (EEG) is one of the most common and non-invasive ways of analyzing and studying the subtle changes in neuronal activity of the brain during an epileptic seizure attack. These changes can be analyzed for developing an automated system that would assert the chances of an impending seizure. As changeable nature of seizure affects the patients from having a normal life, hence progress in developing new methods will improve the quality of life and also provide assistance in the medical sector. Objective of the proposed method is to avoid EEG channel selection and use all input EEG channel features to design a generalized epileptic seizure detection framework.

METHOD

In this work, a long short-term memory network has been proposed that is not complex and has the capability of effectively detecting epileptic seizures from both non-invasive and invasive electroencephalogram recordings. The proposed framework is simple and effective and designed in such capacity that raw electroencephalogram signals can be used to detect seizures. Also, a generalized approach has been followed that is channel independent such that EEG signals belonging to any hemisphere of the brain can be detected effectively by the proposed architecture.

RESULTS

The automated seizure detection system achieved high seizure detection sensitivity of 99.9%, and a low false-positive rate of 0.003 per hour for the Children's Hospital Boston-Massachusetts Institute of Technology dataset. While for the Sleep-Wake-Epilepsy-Center of the University Department of Neurology at the Inselspital Bern dataset, the sensitivity is 99.4% and false-positive rate of 0.006 per hour. Convergence analysis of the proposed model provides a significant amount of reliability and correctness in the efficient detection of epileptic seizures.

CONCLUSION

Assessment of the proposed framework on non-invasive as well as invasive EEG signals showed that the framework worked well for different type of EEG recordings as different metrics gave satisfactory results. As the framework is simple and did not require any additional parameter optimization techniques, it reduced the processing overheads without affecting the accuracy. Hence, it can be used as an efficient method for monitoring epileptic seizures.

An interictal measurement of cerebral oxygen extraction fraction in MRI-negative refractory epilepsy using quantitative susceptibility mapping

PURPOSE

Oxygen extraction fraction (OEF) can be a factor to identify brain tissue's disability in epileptic patients. This study aimed to assess the OEF's level measurement in refractory epileptic patients (REPs) using a quantitative susceptibility mapping (QSM) method and to determine whether the OEF parameters change.

METHODS

QSM-OEF maps of 26 REPs and 16 healthy subjects were acquired using 3T MRI with a 64-channel coil. Eighteen regions-of-interest (ROIs) were chosen around the cortex in one appropriate slice of the brain and the mean QSM-OEF for each ROI was obtained. The correlations of QSM-OEF among different clinical characteristics of the disease, as well as between the patients and normal subjects, were also investigated.

RESULTS

QSM-OEF was shown to be significantly higher in REPs (44.9 ± 5.8) than that in HS (41.9 ± 6.2) (p < 0.05). Mean QSM-OEF was statistically lower in the ipsilateral side (44.5 ± 6.6) compared to the contralateral side (46.4 ± 6.8) (P < 0.01). QSM-OEF was illustrated to have a strong positive correlation with the attack duration (r = 0.6), and a moderate negative correlation with the attack frequency (r = -0.3). Using an optimized support vector machine algorithm, we could predict the disease in subjects having abnormal OEF values in the brain-selected-ROIs with sensitivity, specificity, AUC, and the precision of 0.96, 1, 0.98, and 1, respectively.

CONCLUSIONS

The results of this study revealed that QSM-OEF of the REPs' brain is higher than that of HS, which indicates that QSM-OEF is associated with disease activity.

Classification with a Deferral Option and Low-Trust Filtering for Automated Seizure Detection

Wearable technology will become available and allow prolonged electroencephalography (EEG) monitoring in the home environment of patients with epilepsy. Neurologists analyse the EEG visually and annotate all seizures, which patients often under-report. Visual analysis of a 24-h EEG recording typically takes one to two hours. Reliable automated seizure detection algorithms will be crucial to reduce this analysis. We investigated such algorithms on a dataset of behind-the-ear EEG measurements. Our first aim was to develop a methodology where part of the data is deferred to a human expert, who performs perfectly, with the goal of obtaining an (almost) perfect detection sensitivity (DS). Prediction confidences are determined by temperature scaling of the classification model outputs and trust scores. A DS of approximately 90% (99%) can be achieved when deferring around 10% (40%) of the data. Perfect DS can be achieved when deferring 50% of the data. Our second contribution demonstrates that a common modelling strategy, where predictions from several short EEG segments are combined to obtain a final prediction, can be improved by filtering out untrustworthy segments with low trust scores. The false detection rate shows a relative decrease between 21% and 43%, and the DS shows a small increase or decrease.

A Review of Microelectronic Systems and Circuit Techniques for Electrical Neural Recording Aimed at Closed-Loop Epilepsy Control

Closed-loop implantable electronics offer a new trend in therapeutic systems aimed at controlling some neurological diseases such as epilepsy. Seizures are detected and electrical stimulation applied to the brain or groups of nerves. To this aim, the signal recording chain must be very carefully designed so as to operate in low-power and low-latency, while enhancing the probability of correct event detection. This paper reviews the electrical characteristics of the target brain signals pertaining to epilepsy detection. Commercial systems are presented and discussed. Finally, the major blocks of the signal acquisition chain are presented with a focus on the circuit architecture and a careful attention to solutions to issues related to data acquisition from multi-channel arrays of cortical sensors.