Search

Ultra‐long‐term electroencephalographic (EEG) registration using minimally invasive low‐channel devices is an emerging technology to assess sporadic seizure events. Highly sensitive automatic seizure detection algorithms are needed for semiautomatic evaluation of these prolonged recordings. We describe the design and validation of a deep neural network for two‐channel seizure detection. The model is trained using EEG recordings from 590 patients in a publicly available seizure database. These recordings are based on the full 10–20 electrode system and include seizure annotations created by reviews of the full set of EEG channels. Validation was performed using 48 scalp EEG recordings from an independent epilepsy center and consensus seizure annotations from three neurologists. For each patient, a three‐electrode subgroup (two channels with a common reference) of the full montage was selected for validation of the two‐channel model. Mean sensitivity across patients of 88.8% and false positive rate across patients of 12.9/day were achieved. The proposed training approach is of great practical relevance, because true recordings from low‐channel devices are currently available only in small numbers, and the generation of gold standard seizure annotations in two EEG channels is often difficult. The study demonstrates that automatic seizure detection based on two‐channel EEG data is feasible and review of ultra‐long‐term recordings can be made efficient and effective. [ABSTRACT FROM AUTHOR]

Background: Self-recorded EEG by patients at home might present a viable alternative to inpatient epilepsy evaluations. Objectives and Methods: We developed a novel telemonitoring system comprising seamlessly integrated hardand software with automated AI-based EEG analysis. Results: The first complete study participation results demonstrate feasibility and clinical utility. Conclusion: Our telemonitoring solution potentially improves treatment of patients with epilepsy and moreover might help to better distribute resources in the healthcare system. [ABSTRACT FROM AUTHOR]

Automatic computer-based algorithms for the detection of epileptiform potentials and seizure patterns on EEG facilitate a time-saving, objective method of quantitative EEG interpretation which is available 7/24. For the automatic detection of interictal epileptiform potentials sensitivities range from 65 to 99% with false positive detections of 0,09 to 13,4 per minute. Recent studies documented equal or even better performance of automatic spike detection programs compared with experienced human EEG readers. The seizure detection problem-one of the major problems in clinical epileptology-consists of the fact that the majority of focal onset seizures with impaired awareness and of seizures arising out of sleep occur unnoticed by patients and their caregivers. Automatic seizure detection systems could facilitate objective seizure documentation and thus help to solve the seizure detection problem. Furthermore, seizure detection systems may help to prevent seizure-related injuries and sudden unexpected death in epilepsy (SUDEP), and could be an integral part of novel, seizure-triggered on-demand therapies in epilepsy. During long-term video-EEG monitoring seizure detection systems could improve patient safety, provide a time-saving objective and reproducible analysis of seizure patterns and facilitate automatic computer-based patient testing during seizures. Sensitivities of seizure detection systems range from 75 to 90% with extratemporal seizures being more difficult to detect than temporal seizures. The false positive alarm rate ranges from 0,1 to 5 per 24 hours. Finally, machine learning algorithms, especially deep learning approaches, open a new highly promising era in automatic spike and seizure detection., Competing Interests: Erklärung zu finanziellen Interessen Forschungsförderung erhalten: Ja, von einer anderen Institution (Pharma- oder Medizintechnikfirma usw.); Honorar/geldwerten Vorteil für Referententätigkeit erhalten: