Automated video-based differentiation of sleep-related hypermotor epilepsy and parasomnia episodes

Matteo Moro, Federica Sassi, Ramona Cordani, Anna Castelnovo, Mauro Manconi, Paola Proserpio, Laura Tassi, Federica Provini, Francesca Odone, Maura Casadio, Lino Nobili, Pietro Mattioli, Dario Arnaldi, Valentina Marazzotta, Marco Veneruso, Luca Baldelli, Greta Mainieri, Stefano Francione, Luca Bosisio, Alessandro Consales

Abstract: Distinguishing epileptic seizures from parasomnias is challenging due to overlapping motor features. This study evaluated a SlowFast deep learning model using video recordings of 167 individuals to classify Sleep-Related Hypermotor Epilepsy, Disorders of Arousal, and REM Sleep Behavior Disorder. The model achieved a mean accuracy of 83.3% across three data splits. This work represents an initial step toward developing automated tools to support clinicians in assessing sleep-related motor events.