Automatic classification of hyperkinetic, tonic, and tonic-clonic seizures using unsupervised clustering of video signals.

Introduction: This study evaluated the accuracy of motion signals extracted from video monitoring data to differentiate epileptic motor seizures in patients with drug-resistant epilepsy. 3D near-infrared video was recorded by the Nelli® seizure monitoring system (Tampere, Finland). Methods: 10 patients with 130 seizures were included in the training dataset, and 17 different patients with 98 seizures formed the testing dataset. Only seizures with unequivocal hyperkinetic, tonic, and tonic-clonic semiology were included. Motion features from the catch22 feature collection extracted from video were explored to transform the patients' videos into numerical time series for clustering and visualization. Results: Changes in feature generation provided incremental discrimination power to differentiate between hyperkinetic, tonic, and tonic-clonic seizures. Temporal motion features showed the best results in the unsupervised clustering analysis. Using these features, the system differentiated hyperkinetic, tonic and tonic-clonic seizures with 91, 88, and 45% accuracy after 100 cross-validation runs, respectively. F1-scores were 93, 90, and 37%, respectively. Overall accuracy and f1-score were 74%. Conclusion: The selected features of motion distinguished semiological differences within epileptic seizure types, enabling seizure classification to distinct motor seizure types. Further studies are needed with a larger dataset and additional seizure types. These results indicate the potential of video-based hybrid seizure monitoring systems to facilitate seizure classification improving the algorithmic processing and thus streamlining the clinical workflow for human annotators in hybrid (algorithmic-human) seizure monitoring systems.

Automated detection of nocturnal motor seizures using an audio-video system.

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.

Automatic assessment of the myoclonus severity from videos recorded according to standardized Unified Myoclonus Rating Scale protocol and using human pose and body movement analysis.

PURPOSE: Myoclonus in progressive myoclonus epilepsy type 1 (EPM1) patients shows marked variability, which presents a substantial challenge in devising treatment and conducting clinical trials. Consequently, fast and objective myoclonus quantification methods are needed. METHODS: Ten video-recorded unified myoclonus rating scale (UMRS) myoclonus with action tests were performed on EPM1 patients who were selected for the development and testing of the automatic myoclonus quantification method. Human pose and body movement analyses of the videos were used to identify body keypoints and further analyze movement smoothness and speed. The automatic myoclonus rating scale (ARMS) was developed. It included the jerk count during movement score and the log dimensionless jerk (LDLJ) score to evaluate changes in the smoothness of movement. RESULTS: The scores obtained with the automatic analyses showed moderate to strong significant correlation with the UMRS myoclonus with action scores. The jerk count of the primary keypoints and the LDLJ scores were effective in the evaluation of the myoclonic jerks during hand movements. They also correlated moderately to strongly with the total UMRS test panel scores (r2 = 0,77, P = 0,009 for the jerk count score and r2 = 0,88, P = 0,001 for the LDLJ score). The automatic analyses was weaker in quantification of the neck, trunk, and leg myoclonus. CONCLUSION: Automatic quantification of myoclonic jerks using human pose and body movement analysis of patients' videos is feasible and was found to be quite consistent with the accepted clinical gold standard quantification method. Based on the results of this study, the automatic analytical method should be further developed and validated to improve myoclonus severity follow-up for EPM1 patients.