Concept-drifts adaptation for machine learning EEG epilepsy seizure prediction.

Seizure prediction remains a challenge, with approximately 30% of patients unresponsive to conventional treatments. Addressing this issue is crucial for improving patients' quality of life, as timely intervention can mitigate the impact of seizures. In this research field, it is critical to identify the preictal interval, the transition from regular brain activity to a seizure. While previous studies have explored various Electroencephalogram (EEG) based methodologies for prediction, few have been clinically applicable. Recent studies have underlined the dynamic nature of EEG data, characterised by data changes with time, known as concept drifts, highlighting the need for automated methods to detect and adapt to these changes. In this study, we investigate the effectiveness of automatic concept drift adaptation methods in seizure prediction. Three patient-specific seizure prediction approaches with a 10-minute prediction horizon are compared: a seizure prediction algorithm incorporating a window adjustment method by optimising performance with Support Vector Machines (Backwards-Landmark Window), a seizure prediction algorithm incorporating a data-batch (seizures) selection method using a logistic regression (Seizure-batch Regression), and a seizure prediction algorithm with a dynamic integration of classifiers (Dynamic Weighted Ensemble). These methods incorporate a retraining process after each seizure and use a combination of univariate linear features and SVM classifiers. The Firing Power was used as a post-processing technique to generate alarms before seizures. These methodologies were compared with a control approach based on the typical machine learning pipeline, considering a group of 37 patients with Temporal Lobe Epilepsy from the EPILEPSIAE database. The best-performing approach (Backwards-Landmark Window) achieved results of 0.75 ± 0.33 for sensitivity and 1.03 ± 1.00 for false positive rate per hour. This new strategy performed above chance for 89% of patients with the surrogate predictor, whereas the control approach only validated 46%.

Improving epilepsy diagnosis across the lifespan: approaches and innovations.

Epilepsy diagnosis is often delayed or inaccurate, exposing people to ongoing seizures and their substantial consequences until effective treatment is initiated. Important factors contributing to this problem include delayed recognition of seizure symptoms by patients and eyewitnesses; cultural, geographical, and financial barriers to seeking health care; and missed or delayed diagnosis by health-care providers. Epilepsy diagnosis involves several steps. The first step is recognition of epileptic seizures; next is classification of epilepsy type and whether an epilepsy syndrome is present; finally, the underlying epilepsy-associated comorbidities and potential causes must be identified, which differ across the lifespan. Clinical history, elicited from patients and eyewitnesses, is a fundamental component of the diagnostic pathway. Recent technological advances, including smartphone videography and genetic testing, are increasingly used in routine practice. Innovations in technology, such as artificial intelligence, could provide new possibilities for directly and indirectly detecting epilepsy and might make valuable contributions to diagnostic algorithms in the future.

Automated Seizure Detection Based on State-Space Model Identification.

In this study, we developed a machine learning model for automated seizure detection using system identification techniques on EEG recordings. System identification builds mathematical models from a time series signal and uses a small number of parameters to represent the entirety of time domain signal epochs. Such parameters were used as features for the classifiers in our study. We analyzed 69 seizure and 55 non-seizure recordings and an additional 10 continuous recordings from Thomas Jefferson University Hospital, alongside a larger dataset from the CHB-MIT database. By dividing EEGs into epochs (1 s, 2 s, 5 s, and 10 s) and employing fifth-order state-space dynamic systems for feature extraction, we tested various classifiers, with the decision tree and 1 s epochs achieving the highest performance: 96.0% accuracy, 92.7% sensitivity, and 97.6% specificity based on the Jefferson dataset. Moreover, as the epoch length increased, the accuracy dropped to 94.9%, with a decrease in sensitivity to 91.5% and specificity to 96.7%. Accuracy for the CHB-MIT dataset was 94.1%, with 87.6% sensitivity and 97.5% specificity. The subject-specific cases showed improved results, with an average of 98.3% accuracy, 97.4% sensitivity, and 98.4% specificity. The average false detection rate per hour was 0.5 ± 0.28 in the 10 continuous EEG recordings. This study suggests that using a system identification technique, specifically, state-space modeling, combined with machine learning classifiers, such as decision trees, is an effective and efficient approach to automated seizure detection.

Cosine convolutional neural network and its application for seizure detection.

Traditional convolutional neural networks (CNNs) often suffer from high memory consumption and redundancy in their kernel representations, leading to overfitting problems and limiting their application in real-time, low-power scenarios such as seizure detection systems. In this work, a novel cosine convolutional neural network (CosCNN), which replaces traditional kernels with the robust cosine kernel modulated by only two learnable factors, is presented, and its effectiveness is validated on the tasks of seizure detection. Meanwhile, based on the cosine lookup table and KL-divergence, an effective post-training quantization algorithm is proposed for CosCNN hardware implementation. With quantization, CosCNN can achieve a nearly 75% reduction in the memory cost with almost no accuracy loss. Moreover, we design a configurable cosine convolution accelerator on Field Programmable Gate Array (FPGA) and deploy the quantized CosCNN on Zedboard, proving the proposed seizure detection system can operate in real-time and low-power scenarios. Extensive experiments and comparisons were conducted using two publicly available epileptic EEG databases, the Bonn database and the CHB-MIT database. The results highlight the performance superiority of the CosCNN over traditional CNNs as well as other seizure detection methods.

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.

Autoimmune and paraneoplastic seizures.

Seizures are a common feature of autoimmune encephalitis and are especially prevalent in patients with the commonest autoantibodies, against LGI1, CASPR2 and the NMDA, GABAB, and GABAA receptors. In this chapter, we discuss the classification, clinical, investigation, and treatment aspects of patients with these, and other autoantibody-mediated and -associated, illnesses. We highlight distinctive and common seizure semiologies which, often alongside other features we outline, can help the clinical diagnosis of an autoantibody-associated syndrome. Next, we classify these syndromes by either focusing on whether they represent underlying causative autoantibodies or T-cell-mediated syndromes and on the distinction between acute symptomatic seizures and a more enduring tendency to autoimmune-associated epilepsy, a practical and valuable distinction for both patients and clinicians which relates to the pathogenesis. We emphasize the more effective immunotherapy response in patients with causative autoantibodies, and discuss the emerging evidence for various first-, second-, and third-line immunotherapies. Finally, we highlight available clinical rating scales which can guide autoantibody testing and immunotherapy in patients with seizures of unknown etiology. Throughout, we relate the clinical and therapeutic observations to the immunobiology and neuroscience which drive these seizures.

Efficient EEG motion artifact elimination framework for ambulatory epileptic seizure detection application.

Motion artifacts are a pervasive challenge in EEG ambulatory monitoring, often obscuring critical neurological signals and impeding accurate seizure detection. In this study, we propose a new approach of outlier based grouping of two level Singular Spectrum Analysis (SSA) decomposition combined with Relative Total Variation (RTV) filter for the effective removal of motion-induced noise from ambulatory EEG data. A two-stage SSA method was employed to decompose single-channel EEG signal, which had been interfered with, into various fre quency bands. The affected sub-band signal was then subjected to an RTV filter to estimate the artifact signal. Subtracting this estimated artifact signal from the contaminated sub-band signal yielded the filtered sub-band signal. Subse quently, the filtered sub-band signal was reintegrated with the other decomposed components from noise-free bands, culminating in the generation of the ultimate denoised EEG signal. Based on the comprehensive set of simulation results, it can be deduced that the algorithm described in the paper outperforms existing methods. It demonstrates superior metrics evaluation in terms of ΔSNR,η,MAE, andPSNRwhen compared to these alternatives. Our framework sig- nificantly enhances the quality of EEG data by successfully eliminating motion artifacts while preserving crucial brainwave information. To evaluate the prac tical impact of this noise reduction technique, we assess its performance in the context of seizure detection. The results reveal a substantial improvement in the accuracy and reliability of seizure detection algorithms when applied to EEG data preprocessed with proposed method.

Crisis en urgencias: una vista a las características clínicas y terapéuticas a través de 122 pacientes / Seizures in the emergency service: the clinical and therapeutic characteristics of 122 patients

Introducción Las crisis epilépticas son un motivo frecuente de consulta en los servicios de urgencias hospitalarias. Llegar al diagnóstico correcto puede ser complejo, y es fundamental decidir cuándo y qué medicamento anticrisis (MAC) pautar. Nuestro objetivo es detallar las características de los pacientes que consultaron por este motivo en un hospital mediano. Pacientes y métodos Estudio observacional retrospectivo de todos los pacientes mayores de edad que consultaron en el servicio de urgencias del Hospital Universitario Lucus Augusti entre enero de 2022 y enero de 2023 con diagnóstico al alta de crisis epiléptica. Se registraron variables demográficas, los antecedentes, si era una primera crisis, el número de éstas, si se inició un MAC y cuál, el diagnóstico, qué pruebas se realizaron y si se interconsultó con la guardia de neurología. Resultados Se diagnosticó a 122 pacientes de crisis epilépticas en urgencias. El 50,8% eran mujeres. La media de edad fue de 69,8 años. Se solicitó valoración por neurología en un 47,6%. El 50,8% presentó una primera crisis. No se llegó al diagnóstico en un 46% de los casos, de los cuales sólo 10 fueron valorados por neurología. La etiología más frecuente fue la vascular. Se realizó un electroencefalograma en un 41,8%. El levetiracetam fue prácticamente el único fármaco utilizado cuando no se consultó con neurología. Conclusiones La valoración precoz de los pacientes con una primera crisis en urgencias por un especialista en neurología es determinante para el diagnóstico de epilepsia. Cuando no se interconsulta, casi siempre se pauta el mismo MAC. (AU)

INTRODUCTION Epileptic seizures are a common cause of admission in emergency services at hospitals. Performing the correct diagnosis can be difficult, and deciding when and which anti-seizure medication (ASM) to prescribe is critical. Our objective is to detail the characteristics of patients treated in a medium-sized hospital for this reason. PATIENTS AND METHODS A retrospective observational study was performed, including all the adult patients treated by the emergency service of the Lucus Augusti University Hospital between January 2022 and January 2023 with a diagnosis of epileptic seizure on discharge. The study recorded their demographic variables, history, whether it was their first seizure, the number of seizures, whether an anti-seizure medication was administered and which one, the diagnosis, the tests performed, and whether the patient was referred to the neurology service. RESULTS A total of 122 patients were diagnosed with epileptic seizures in the emergency service. 50.8% of the patients were women. The mean age was 69.8 years. Neurological assessment was requested for 47.6%. 50.8% presented their first seizure. No diagnosis was performed in 46% of the cases, of which only 10 were evaluated by the neurology service. The most common etiology was vascular. An electroencephalogram was performed on 41.8%. Levetiracetam was practically the only drug administered when the neurology department was not consulted. CONCLUSIONS Early evaluation of patients with their first seizure in the emergency service by a neurological specialist is crucial for the diagnosis of epilepsy. The same anti-seizure medication is almost always prescribed when no cross-consultation takes place. (AU)

Seizure Considerations in Older Adults and Geriatric Patients.

Older adults account for 25% of first-time seizures, with many of these seizures caused by accumulated injuries and insults to the brain and comorbidities associated with aging or as a result of a life-threatening comorbidity, yet seizures in older adults are often so subtle that they are not recognized or treated. Once an older adult has 1 seizure, they are at higher risk of more seizures and ultimately a diagnosis of epilepsy. Epilepsy affects quality of life and safety and may jeopardize life itself in the older adult; thus, it is important to be able to recognize seizures in older adults and know what to do.

Comparison between epileptic seizure prediction and forecasting based on machine learning.

Epilepsy affects around 1% of the population worldwide. Anti-epileptic drugs are an excellent option for controlling seizure occurrence but do not work for around one-third of patients. Warning devices employing seizure prediction or forecasting algorithms could bring patients new-found comfort and quality of life. These algorithms would attempt to detect a seizure's preictal period, a transitional moment between regular brain activity and the seizure, and relay this information to the user. Over the years, many seizure prediction studies using Electroencephalogram-based methodologies have been developed, triggering an alarm when detecting the preictal period. Recent studies have suggested a shift in view from prediction to forecasting. Seizure forecasting takes a probabilistic approach to the problem in question instead of the crisp approach of seizure prediction. In this field of study, the triggered alarm to symbolize the detection of a preictal period is substituted by a constant risk assessment analysis. The present work aims to explore methodologies capable of seizure forecasting and establish a comparison with seizure prediction results. Using 40 patients from the EPILEPSIAE database, we developed several patient-specific prediction and forecasting algorithms with different classifiers (a Logistic Regression, a 15 Support Vector Machines ensemble, and a 15 Shallow Neural Networks ensemble). Results show an increase of the seizure sensitivity in forecasting relative to prediction of up to 146% and in the number of patients that displayed an improvement over chance of up to 300%. These results suggest that a seizure forecasting methodology may be more suitable for seizure warning devices than a seizure prediction one.

Estimate of Patients With Missed Seizures Because of Delay in Conventional EEG.

PURPOSE: There is frequent delay between ordering and placement of conventional EEG. Here we estimate how many patients had seizures during this delay. METHODS: Two hundred fifty consecutive adult patients who underwent conventional EEG monitoring at the University of Wisconsin Hospital were retrospectively chart reviewed for demographics, time of EEG order, clinical and other EEG-related information. Patients were stratified by use of anti-seizure medications before EEG and into low-risk, medium-risk, and high-risk groups based on 2HELPS2B score (0, 1, or >1). Monte Carlo simulations (500 trials) were performed to estimate seizures during delay. RESULTS: The median delay from EEG order to performing EEG was 2.00 hours (range of 0.5-8.00 hours) in the total cohort. For EEGs ordered after-hours, it was 2.00 hours (range 0.5-8.00 hours), and during business hours, it was 2.00 hours (range 0.5-6.00 hours). The place of EEG, intensive care unit, emergency department, and general floor, did not show significant difference (P = 0.84). Anti-seizure medication did not affect time to first seizure in the low-risk (P = 0.37), medium-risk (P = 0.44), or high-risk (P = 0.12) groups. The estimated % of patients who had a seizure in the delay period for low-risk group (2HELPS2B = 0) was 0.8%, for the medium-risk group (2HELPS2B = 1) was 10.3%, and for the high-risk group (2HELPS2B > 1) was 17.6%, and overall risk was 7.2%. CONCLUSIONS: The University of Wisconsin Hospital with 24-hour in-house EEG technologists has a median delay of 2 hours from order to start of EEG, shorter than published reports from other centers. Nonetheless, seizures were likely missed in about 7.2% of patients.

Seizure Detection, Prediction, and Forecasting.

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

A comparative study of CNN-capsule-net, CNN-transformer encoder, and Traditional machine learning algorithms to classify epileptic seizure.

INTRODUCTION: Epilepsy is a disease characterized by an excessive discharge in neurons generally provoked without any external stimulus, known as convulsions. About 2 million people are diagnosed each year in the world. This process is carried out by a neurological doctor using an electroencephalogram (EEG), which is lengthy. METHOD: To optimize these processes and make them more efficient, we have resorted to innovative artificial intelligence methods essential in classifying EEG signals. For this, comparing traditional models, such as machine learning or deep learning, with cutting-edge models, in this case, using Capsule-Net architectures and Transformer Encoder, has a crucial role in finding the most accurate model and helping the doctor to have a faster diagnosis. RESULT: In this paper, a comparison was made between different models for binary and multiclass classification of the epileptic seizure detection database, achieving a binary accuracy of 99.92% with the Capsule-Net model and a multiclass accuracy with the Transformer Encoder model of 87.30%. CONCLUSION: Artificial intelligence is essential in diagnosing pathology. The comparison between models is helpful as it helps to discard those that are not efficient. State-of-the-art models overshadow conventional models, but data processing also plays an essential role in evaluating the higher accuracy of the models.

The role of stand-alone videos in the diagnosis of seizures.

The diagnosis of seizures and seizure mimics relies primarily on the history, but history has well-known limitations. Video recordings of events are a powerful extension of the history because they allow neurologists to view the events in question. In addition, they are readily available in situation, whereas the gold standard of EEG-video is not. That includes underserved or rural areas, and events that are too infrequent to be captured during a few days of EEG-video monitoring. Brief cellphone videos have been shown to be valuable to suggest or guide the correct diagnosis.

Strange episodes during sleep - epilepsy or parasomnia? / Underlige episoder under søvn ­ epilepsi eller parasomni?

In some forms of epilepsy, the seizures occur almost exclusively during sleep. This is particularly the case with hypermotor frontal lobe seizures. Clinically it can be difficult to distinguish such seizures from parasomnias and psychogenic non-epileptic seizures. This clinical review article aims to highlight the importance of making the correct diagnosis, as these conditions require completely different treatment.

A Novel Framework for Epileptic Seizure Detection Using Electroencephalogram Signals Based on the Bat Feature Selection Algorithm.

The precise electroencephalogram (EEG) signal classification with the highest possible accuracy is a key goal in the brain-computer interface (BCI). Considering the complexity and nonstationary nature of the EEG signals, there is an urgent need for effective feature extraction and data mining techniques. Here, we introduce a novel pipeline based on Bat and genetic algorithms for feature construction and dimension reduction of EEG signals. After wavelet extraction and segmentation, the Bat algorithm identifies the most relevant features. We use these features and a genetic algorithm combined with a neural network method to automatically classify the segments of the epilepsy EEG signals. We also use available classification methods based on k-Nearest Neighbors or naïve Bayes for comparison purposes. The code distinguishes individual signals within various combinations of data obtained from healthy volunteers with open or closed eyes and patients suffering from epilepsy disorders during seizure-free periods or seizure activities. Compared to the previously introduced methods, our proposed framework demonstrates a superior balance of high accuracy and short runtime. The minimum achieved accuracies for balanced and unbalanced classes are 100% and 75.9%, respectively. This approach has the potential for direct applications in clinics, enabling accurate and rapid analysis of the epilepsy EEG signals obtained from patients.

Ambulatory seizure detection.

PURPOSE OF REVIEW: To review recent advances in the field of seizure detection in ambulatory patients with epilepsy. RECENT FINDINGS: Recent studies have shown that wrist or arm wearable sensors, using 3D-accelerometry, electrodermal activity or photoplethysmography, in isolation or in combination, can reliably detect focal-to-bilateral and generalized tonic-clonic seizures (GTCS), with a sensitivity over 90%, and false alarm rates varying from 0.1 to 1.2 per day. A headband EEG has also demonstrated a high sensitivity for detecting and help monitoring generalized absence seizures. In contrast, no appropriate solution is yet available to detect focal seizures, though some promising findings were reported using ECG-based heart rate variability biomarkers and subcutaneous EEG. SUMMARY: Several FDA and/or EU-certified solutions are available to detect GTCS and trigger an alarm with acceptable rates of false alarms. However, data are still missing regarding the impact of such intervention on patients' safety. Noninvasive solutions to reliably detect focal seizures in ambulatory patients, based on either EEG or non-EEG biosignals, remain to be developed. To this end, a number of challenges need to be addressed, including the performance, but also the transparency and interpretability of machine learning algorithms.

The 2022 International League Against Epilepsy Classification and Definition of Childhood Epilepsy Syndromes: An Update for Pediatricians.

The 2017 classification of the epilepsies of International League Against Epilepsy (ILAE) defined three diagnostic levels, including seizure type, epilepsy type and epilepsy syndrome. Epilepsy syndromes have been recognized as distinct electroclinical entities well before the first ILAE classification of Epilepsies and Epilepsy Syndromes in 1985. A formally accepted classification of epilepsy syndromes was not available, and hence, the 2017-2021 Nosology and Definitions Task Force of ILAE was formulated. The ILAE position papers were published in 2022, which classified epilepsy syndromes into (1) syndromes with onset in neonates and infants (up to 2 years of age), (2) syndromes with onset in childhood, (3) syndromes that may begin at a variable age and (4) idiopathic generalized epilepsies. This classification recognized the concept of etiology-specific syndrome. These papers have addressed the specific clinical and laboratory features of epilepsy syndromes and specify the rationale for any significant changes in terminology or definition. This paper will review some pertinent changes and essential points relevant to pediatricians.

Factors affecting long-term prognosis in adult patients with psychogenic non-epileptic seizures.

Background and purpose:

Among epileptic patients who are monitored using the video-electroencephalography monitoring (VEM) technique, in some patients a psychogenic non-epileptic seizure (PNES) can be identified as a definitive diagnosis. The long-term prognosis of these patients is not well known. In this study, we aimed to determine the factors that affect the prognosis of PNES.

Forty-one PNES patients diagnosed using VEM between 2012 and 2022 were questioned about their PNES frequencies in the last 12 months. According to their semiological characteristics, PNES types were divided into motor and non-motor seizures. The effects of clinical characteristics (e.g. age, gender, marital status, education level and PNES type) on the prognoses were identified. 

Twenty-one PNES patients (51.2%) had long-term seizure freedom after VEM. Thirteen of them (31.7%) entered the seizure-free period immediately after VEM, and the other eight (19.5%) continued suffering from PNES for several years and became seizure free in the last 12 months. In the poor-prognosis group, female cases showed worse prognoses than male cases. The prognoses of motor and non-motor PNES types did not show significant differences. 

This study showed that 51.2% of the PNES patients examined had long-term seizure freedom and that female patients had worse prognoses than male patients.