Background Unsupervised nocturnal tonic‐clonic seizures (TCSs) may lead to sudden unexpected death in epilepsy (SUDEP). Major motor seizures (TCSs and hypermotor seizures) may lead to injuries. Our goal was to develop and validate an automated audio‐video system for the real‐time detection of major nocturnal motor seizures. Methods In this Phase‐3 clinical validation study, we assessed the performance of automated detection of nocturnal motor seizures using audio‐video streaming, computer vision and an artificial intelligence‐based algorithm (Nelli). The detection threshold was predefined, the validation dataset was independent from the training dataset, patients were prospectively recruited, and the analysis was performed in real time. The gold standard was based on expert evaluation of long‐term video electroencephalography (EEG). The primary outcome was the detection of nocturnal major motor seizures (TCSs and hypermotor seizures). The secondary outcome was the detection of other (minor) nocturnal motor seizures. Results We recruited 191 participants aged 1–72 years (median: 20 years), and we monitored them for 4183 h during the night. Device deficiency was present 10.5% of the time. Fifty‐one patients had nocturnal motor seizures during the recording. The sensitivity for the major motor seizures was 93.7% (95% confidence interval: 69.8%–99.8%). The system detected all 11 TCS and four out of five (80%) hypermotor seizures. For the minor motor seizure types, the sensitivity was low (8.3%). The false detection rate was 0.16 per h. Conclusion The Nelli system detects nocturnal major motor seizures with a high sensitivity and is suitable for implementation in institutions (hospitals, residential care facilities), where rapid interventions triggered by alarms can potentially reduce the risk of SUDEP and injuries.

Automated seizure detection promises to aid in the prevention of SUDEP and improve the quality of care by assisting in epilepsy diagnosis and treatment adjustment. In this phase 2 validation, the algorithmic model performance of a contactless, marker-free video-based motor seizure detection system is evaluated against video-electroencephalographic monitoring (VEM) from two Danish epilepsy monitoring units. Detection performance of five categories of motor epileptic seizures (tonic-clonic, hyperkinetic, tonic, unclassified motor, automatisms) and psychogenic non-epileptic seizures (PNES) with a motor behavioral component lasting for >10 seconds were assessed. 230 patients were recruited in the validation set, with 340 motor seizures identified by VEM. The control threshold was evaluated at a range of values to compare the sensitivity and false detection rate (FDR). At optimal thresholds, the performance of seizure groups in terms of sensitivity (CI) and FDR/hr (CI): tonic-clonic- 95.2% (77.3%, 99.2%); 0.084 (0.081, 0.11), hyperkinetic- 92.9% (68.5%, 98.7%); 0.62 (0.57, 0.67), tonic- 78.3% (64.4%, 87.7%); 5.81 (5.46, 6.19), automatism- 87% (74.3%, 93.9%); 3.30 (3.08, 3.54), unclassified motor seizures- 77.7% (70.8%, 83.4%); 4.79 (4.48, 5.12), and PNES- 95.6% (85.2%, 98.8%); 1.70 (1.59, 1.83). A generic threshold recommended for all motor seizures under study asserted 87.8% sensitivity and 6.48 FDR/hr. These results indicate the system’s achievable performance at pre-specified thresholds that is clinically applicable for use as a seizure screening solution in diagnostic workflows.

No abstract