Automated analysis and detection of epileptic seizures in video recordings using artificial intelligence.

Introduction: 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. Methods: In this phase 2 exploratory study, the performance of a contactless, marker-free, video-based motor seizure detection system is assessed, considering video recordings of patients (age 0-80 years), in terms of sensitivity, specificity, and Receiver Operating Characteristic (ROC) curves, with respect to video-electroencephalographic monitoring (VEM) as the medical gold standard. Detection performances 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 s were assessed independently at different detection thresholds (rather than as a categorical classification problem). A total of 230 patients were recruited in the study, of which 334 in-scope (>10 s) motor seizures (out of 1,114 total seizures) were identified by VEM reported from 81 patients. We analyzed both daytime and nocturnal recordings. The control threshold was evaluated at a range of values to compare the sensitivity (n = 81 subjects with seizures) and false detection rate (FDR) (n = all 230 subjects). Results: At optimal thresholds, the performance of seizure groups in terms of sensitivity (CI) and FDR/h (CI): tonic-clonic- 95.2% (82.4, 100%); 0.09 (0.077, 0.103), hyperkinetic- 92.9% (68.5, 98.7%); 0.64 (0.59, 0.69), tonic- 78.3% (64.4, 87.7%); 5.87 (5.51, 6.23), automatism- 86.7% (73.5, 97.7%); 3.34 (3.12, 3.58), unclassified motor seizures- 78% (65.4, 90.4%); 4.81 (4.50, 5.14), and PNES- 97.7% (97.7, 100%); 1.73 (1.61, 1.86). A generic threshold recommended for all motor seizures under study asserted 88% sensitivity and 6.48 FDR/h. Discussion: These results indicate an achievable performance for major motor seizure detection that is clinically applicable for use as a seizure screening solution in diagnostic workflows.

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.

First school year tapping predicts children's third-grade literacy skills.

Rhythmic skills have been repeatedly found to relate to children's early literacy skills. Using rhythmic tasks to predict language and reading performance seems a promising direction as they can be easily administered early as a screening test to identify at-risk children. In the present study, we measured Hungarian children's (N = 37) general cognitive abilities (working memory, non-verbal reasoning and rapid automatized naming), language and literacy skills (vocabulary, word reading, phonological awareness and spelling) and finger tapping performance in a longitudinal design in the first and third grades. We applied metronome stimuli in three tempi (80, 120, 150 bpm) using a synchronization-continuation paradigm and also measured participants' spontaneous motor tempo. While children's synchronization asynchrony was lower in third than in the first grade, with the exception of the slow-tempo trials, tapping consistency and continuation tapping success showed no development in this period. First-year tapping consistency in the slow-tempo tasks was associated with third-year reading and spelling outcomes. Our results show that the relation between tapping performance and literacy skills persists throughout the third school year, making the sensorimotor synchronization task a potentially effective instrument for predicting literacy outcomes, and a useful tool for early screening of reading difficulties.

Tapping to Music Predicts Literacy Skills of First-Grade Children.

The ability to synchronise one's movements to the sound of a regular beat has been found to be associated with children's language and reading abilities. Sensorimotor synchronisation or tapping performance can among other factors [e.g., working memory and rapid automatized naming (RAN)] predict phonological awareness and word reading accuracy and fluency of first graders. While tapping tasks that use a simple metronome sound are more often used, applying musical stimuli has the potential advantage of being more engaging and motivating for children. In the present study, we investigated whether tapping to a metronome beat or complex musical stimuli would predict phonological awareness and reading outcomes of Hungarian 6-7-year olds (N=37). We also measured participants' general cognitive abilities (RAN, non-verbal intelligence and verbal working memory). Our results show that phonological awareness, spelling and reading accuracy were associated with the musical tasks while reading fluency was predicted by the metronome trials. Our findings suggest that complex musical tasks should be considered when investigating this age group, as they were, in general, more effective in predicting literacy outcomes.