Seizure detection using scalp‐EEG

Abstract

Scalp electroencephalography (EEG)-based seizure-detection algorithms applied in a clinical setting should detect a broad range of different seizures with high sensitivity and selectivity and should be easy to use with identical parameter settings for all patients. Available algorithms provide sensitivities between 75% and 90%. EEG seizure patterns with short duration, low amplitude, circumscribed focal activity, high frequency, and unusual morphology as well as EEG seizure patterns obscured by artifacts are generally difficult to detect. Therefore, detection algorithms generally perform worse on seizures of extratemporal origin as compared to those of temporal lobe origin. Specificity (false-positive alarms) varies between 0.1 and 5 per hour. Low false-positive alarm rates are of critical importance for acceptance of algorithms in a clinical setting. Reasons for false-positive alarms include physiological and pathological interictal EEG activities as well as various artifacts. To achieve a stable, reproducible performance (especially concerning specificity), algorithms need to be tested and validated on a large amount of EEG data comprising a complete temporal assessment of all interictal EEG. Patient-specific algorithms can further improve sensitivity and specificity but need parameter adjustments and training for individual patients. Seizure alarm systems need to provide on-line calculation with short detection delays in the order of few seconds. Scalp-EEG-based seizure detection systems can be helpful in an everyday clinical setting in the epilepsy monitoring unit, but at the current stage cannot replace continuous supervision of patients and complete visual review of the acquired data by specially trained personnel. In an outpatient setting, application of scalp-EEG-based seizure-detection systems is limited because patients won't tolerate wearing widespread EEG electrode arrays for long periods in everyday life. Recently developed subcutaneous EEG electrodes may offer a solution in this respect.

Ultra‐long‐term subcutaneous home monitoring of epilepsy—490 days of EEG from nine patients

“…[1][2][3] Many factors contribute to this problem, with unrecognized and undocumented seizures being the most important. 8,9 Recently, many new EEG devices have appeared, combining various electrode configurations and data processing methods, [10][11][12][13][14][15] but none of these have been tested in real-life. These clinical problems also concern the patients, 6 and in the context of epilepsy research the problem of wrongful reporting is also well known.…”

“…An EEG acquisition system usable during everyday life could be the tool currently lacking in the toolbox of epilepsy diagnostics and management. 8,9 Recently, many new EEG devices have appeared, combining various electrode configurations and data processing methods, [10][11][12][13][14][15] but none of these have been tested in real-life. In this study, we present the first real-life data on a subcutaneous EEG device for continuous home monitoring of epilepsy.…”

Computer-assisted EEG diagnostic review for idiopathic generalized epilepsy

“…The seizure detection problem has even reached mainstream data science, with recent Kaggle competitions attracting thousands of entrants whose submissions covered a range of machine learning methods from deep convolutional neural networks to extreme gradient boosting [8][9][10]. A recent review of seizure detection from scalp EEG reported good performance from available algorithms, with sensitivities between 75% and 90% and false positive rates of between 0.1 and 5 per hour [6]. However, a large study of 1,478 ambulatory EEG studies found that commercially available automated detectors correctly identified electrographic seizures in only 53% of cases [11].…”

Seizure detection and mobile health devices in epilepsy: Update and future developments

“…The primary methods used to detect seizures are detailed in reviews focusing on scalp EEG, surface electromyography (EMG), movement‐based detection, and multimodal seizure detection . Scalp EEG offers the unique advantage of capturing most seizure types, with high sensitivity (75%‐90%), but also a high rate of false alarms (0.1 and 5 per hour) . It is not currently adapted to chronic ambulatory recordings, although this might change with the development of subcutaneously implanted electrodes.…”

“…9 Scalp EEG offers the unique advantage of capturing most seizure types, with high sensitivity (75%-90%), but also a high rate of false alarms (0.1 and 5 per hour). 6 It is not currently adapted to chronic ambulatory recordings, although this might change with the development of subcutaneously implanted electrodes. Surface EMG is typically used for detecting convulsive seizures, with 2 large-scale blinded prospective studies demonstrating high sensitivity (76%-100%) with average false-alarm rate ranging from 0.7 to 2.5/24 h. 7 Movement-based GTCS detection, primarily using accelerometry sensors, is associated with highly variable sensitivity (31%-95%) and positive predictive value (4%-60%) across video-EEG studies, whereas a field study reported even lower sensitivity (14%).…”