Automatic Computer-Based Detection of Epileptic Seizures

Abstract

Automatic computer-based seizure detection and warning devices are important for objective seizure documentation, for SUDEP prevention, to avoid seizure related injuries and social embarrassments as a consequence of seizures, and to develop on demand epilepsy therapies. Automatic seizure detection systems can be based on direct analysis of epileptiform discharges on scalp-EEG or intracranial EEG, on the detection of motor manifestations of epileptic seizures using surface electromyography (sEMG), accelerometry (ACM), video detection systems and mattress sensors and finally on the assessment of changes of physiologic parameters accompanying epileptic seizures measured by electrocardiography (ECG), respiratory monitors, pulse oximetry, surface temperature sensors, and electrodermal activity. Here we review automatic seizure detection based on scalp-EEG, ECG, and sEMG. Different seizure types affect preferentially different measurement parameters. While EEG changes accompany all types of seizures, sEMG and ACM are suitable mainly for detection of seizures with major motor manifestations. Therefore, seizure detection can be optimized by multimodal systems combining several measurement parameters. While most systems provide sensitivities over 70%, specificity expressed as false alarm rates still needs to be improved. Patients' acceptance and comfort of a specific device are of critical importance for its long-term application in a meaningful clinical way.

Automatische Erkennung von epilepsietypischen Potenzialen und Anfällen im EEG

“…Es besteht deshalb ein dringender klinischer Bedarf für automatische computerbasierte Anfallsdetektionssysteme zur objektiven Anfallsdokumentation, wodurch ein wichtiger Beitrag zur Lösung des Anfallserfassungsproblems geleistet werden könnte [24][25][26]. Derartige Systeme könnten auch als Anfallswarnsysteme eingesetzt werden, wodurch die Unvorhersehbarkeit der Anfälle und deren soziale Konsequenzen abgemildert, anfallsassoziierte Verletzungen verhindert und ein Beitrag zur Prävention von Sudden Unexpected Death in Epilepsy (SUDEP) geleistet werden könnte [27].…”

“…Die Spezifität variiert zwischen 0,1-5 falsch-positiven Alarmen (FAR) pro h [24][25][26]. Niedrige FARs sind für die praktisch-klinische Akzeptanz eines Algorithmus wichtig, und zwar besonders dann, wenn der Algorithmus als Alarmsystem verwendet wird.…”

Sudden unexpected death in epilepsy: The neuro-cardio-respiratory connection

“…Home-based seizure monitoring devices are also available; both non-EEG systems that combine detection methods for movement and heart rate [130], as well as automatic computer-based seizure detection and warning multimodal systems (EEG, ECG, electromyography, oximetry, etc.) have been introduced [131]; however, despite sensitivities over 70% provided by most of these systems, specificity expressed as false alarm rates still lags behind.…”

Comparison of Frontal-Temporal Channels in Epilepsy Seizure Prediction Based on EEMD-ReliefF and DNN

“…For epilepsy seizure detection, scalp EEGs (sEEGs) and intracranial EEGs (iEEGs) are used to measure the ictal changes that lead to a biomarker for the presence of a seizure. The iEEG reading has a higher specificity, but a limited sampling coverage of the cerebral cortex compared with sEEG readings [9]. More than 40 years have been devoted to predicting epileptic seizures, with the challenge of forecasting seizures before they happen [10].…”