Video-Based Detection of Generalized Tonic-Clonic Seizures Using Deep Learning

Timely detection of seizures is crucial to implement optimal interventions, and may help reduce the risk sudden unexpected death in epilepsy (SUDEP) patients with generalized tonic-clonic (GTCSs). While video-based automated seizure systems be able provide alarms both in-hospital at-home settings, earlier studies have primarily employed hand-designed features for such a task. In contrast, deep learning-based approaches do not rely on prior feature selection demonstrated outstanding performance many data classification tasks. Despite these advantages, neural network-based video has rarely been attempted detection. We here assessed feasibility efficacy GTCSs from videos using learning. retrospectively identified 76 GTCS 37 participants who underwent long-term video-EEG monitoring (LTM) along interictal same patients, 10 full-night seizure-free recordings additional patients. Using leave-one-subject-out cross-validation approach (LOSO-CV), we evaluated detect based individual frames (convolutional networks, CNNs) or sequences [CNN+long short-term memory (LSTM) networks]. CNN+LSTM networks outperformed yielding mean sensitivity 88% specificity 92% across The average latency after presumed clinical onset was 22 seconds. Detection increased as function training dataset size. Collectively, that learning feasible efficacious. Deep methods overcome some limitations associated traditional hand-crafted features, serve benchmark future analyses, improve further larger datasets.