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

npj Digital Medicine 2026 Open access

Read full text
Authors: Matteo Moro, Federica Sassi, Ramona Cordani, Anna Castelnovo, Manconi Mauro, Paola Proserpio, Laura Tassi, Federica Provini, Francesca Odone, Maura Casadio, Lino Nobili, for the VISTA group
+9 more Pietro Mattioli, Dario Arnaldi, Valentina Marazzotta, Marco Veneruso, Luca Baldelli, Greta Mainieri, Stefano Francione, Luca Bosisio, Alessandro Consales
DOI: 10.1038/s41746-025-02326-2
Cited by: 0
References: 16

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.

Fields of Study & Subjects

Sleep and Wakefulness Research EEG and Brain-Computer Interfaces Epilepsy research and treatment

Publication details

Journal / source
npj Digital Medicine
Volume
9
Issue
1
Pages
144–144
Publication date
8 January 2026
Language
EN