Modalities and algorithms for generalized motor seizure detection and prediction: a scoping review.

INTRODUCTION: Generalized tonic - clonic seizures (GTCS) are among the most severe seizure types and a major cause of sudden unexpected death in epilepsy (SUDEP). Continuous monitoring is essential, particularly for individuals with drug-resistant epilepsy. While electroencephalography (EEG) remains the diagnostic gold standard, non-EEG wearable systems have emerged as promising, user-friendly alternatives enhancing comfort, mobility, and social acceptance. AREAS COVERED: This scoping review compared sensing modalities and computational methods used for seizure detection and prediction, identified effective sensor combinations, and highlighted current research gaps. Following PRISMA-ScR guidelines, three databases - Scopus, IEEE Xplore, and PubMed - were searched up to 22 April 2025. Twenty-nine studies met inclusion criteria (twenty-six on detection and three on prediction). Combining electrodermal activity (EDA) with motion sensors - accelerometers (ACC), gyroscopes (GYR), and surface electromyography (sEMG) - achieved the highest detection performance (95.2% sensitivity, 98.6% precision, false alarm rate (FAR) 0.64/24 h). As for seizure prediction, HR data showed promise for having sufficient seizure-predictive information with a sensitivity of 62%. EXPERT OPINION: Wearable multimodal non-EEG seizure detection and prediction systems offer personalized care but face validation, hardware, and privacy hurdles. Future success depends on efficient AI, IoT integration, patient-centric design, and clear regulations ensuring accessible and trustworthy clinical tools.