Visual seizure annotation and automated seizure detection using behind-the-ear electroencephalographic channels

Visual seizure annotation and automated seizure detection using behind-the-ear electroencephalographic channels

Vandecasteele, Kaat (Katholieke Universiteit Leuven)
De Cooman, Thomas (Katholieke Universiteit Leuven)
Dan, Jonathan (Katholieke Universiteit Leuven; Byteflies)
Cleeren, Evy (University Hospital Leuven)
Van Huffel, Sabine (Katholieke Universiteit Leuven)
Hunyadi, B. (TU Delft Circuits and Systems)
Van Paesschen, Wim (University Hospital Leuven; Katholieke Universiteit Leuven)

2020

Objective: Seizure diaries kept by patients are unreliable. Automated electroencephalography (EEG)-based seizure detection systems are a useful support tool to objectively detect and register seizures during long-term video-EEG recording. However, this standard full scalp-EEG recording setup is of limited use outside the hospital, and a discreet, wearable device is needed for capturing seizures in the home setting. We are developing a wearable device that records EEG with behind-the-ear electrodes. In this study, we determined whether the recognition of ictal patterns using only behind-the-ear EEG channels is possible. Second, an automated seizure detection algorithm was developed using only those behind-the-ear EEG channels. Methods: Fifty-four patients with a total of 182 seizures, mostly temporal lobe epilepsy (TLE), and 5284 hours of data, were recorded with a standard video-EEG at University Hospital Leuven. In addition, extra behind-the-ear EEG channels were recorded. First, a neurologist was asked to annotate behind-the-ear EEG segments containing selected seizure and nonseizure fragments. Second, a data-driven algorithm was developed using only behind-the-ear EEG. This algorithm was trained using data from other patients (patient-independent model) or from the same patient (patient-specific model). Results: The visual recognition study resulted in 65.7% sensitivity and 94.4% specificity. By using those seizure annotations, the automated algorithm obtained 64.1% sensitivity and 2.8 false-positive detections (FPs)/24 hours with the patient-independent model. The patient-specific model achieved 69.1% sensitivity and 0.49 FPs/24 hours. Significance: Visual recognition of ictal EEG patterns using only behind-the-ear EEG is possible in a significant number of patients with TLE. A patient-specific seizure detection algorithm using only behind-the-ear EEG was able to detect more seizures automatically than what patients typically report, with 0.49 FPs/24 hours. We conclude that a large number of refractory TLE patients can benefit from using this device.

automated algorithms
behind-the-ear EEG
epilepsy
reduced electrode montage
seizure detection
wearable sensors

http://resolver.tudelft.nl/uuid:48e91477-aee2-43f2-9211-1acc13dcb5e8

https://doi.org/10.1111/epi.16470

0013-9580

Epilepsia, 61 (4), 766-775

Institutional Repository

journal article

© 2020 Kaat Vandecasteele, Thomas De Cooman, Jonathan Dan, Evy Cleeren, Sabine Van Huffel, B. Hunyadi, Wim Van Paesschen