biostudies-literatureWagle NNIDCD NIH HHS963968https://www.ebi.ac.uk/biostudies/studies/S-EPMC9403604biostudies-literatureUnknown13<h4>Background</h4>Nystagmus identification and interpretation is challenging for non-experts who lack specific training in neuro-ophthalmology or neuro-otology. This challenge is magnified when the task is performed <i>via</i> telemedicine. Deep learning models have not been heavily studied in video-based eye movement detection.<h4>Methods</h4>We developed, trained, and validated a deep-learning system (aEYE) to classify video recordings as normal or bearing at least two consecutive beats of nystagmus. The videos were retrospectively collected from a subset of the monocular (right eye) video-oculography (VOG) recording used in the Acute Video-oculography for Vertigo in Emergency Rooms for Rapid Triage (AVERT) clinical trial (#NCT02483429). Our model was derived from a preliminary dataset Frontiers in neurologyaEYE: A deep learning system for video nystagmus detection.PMC9403604U01 DC013778Winslow RLiu JGreen KENewman-Toker DEReith HZee DSWagle NGreenstein JMorkos JPakhomov DOtero-Millan JGangan IKomogortsev OVHira SGong KfalseaEYE: A deep learning system for video nystagmus detection.<h4>Background</h4>Nystagmus identification and interpretation is challenging for non-experts who lack specific training in neuro-ophthalmology or neuro-otology. This challenge is magnified when the task is performed <i>via</i> telemedicine. Deep learning models have not been heavily studied in video-based eye movement detection.<h4>Methods</h4>We developed, trained, and validated a deep-learning system (aEYE) to classify video recordings as normal or bearing at least two consecutive beats of nystagmus. The videos were retrospectively collected from a subset of the monocular (right eye) video-oculography (VOG) recording used in the Acute Video-oculography for Vertigo in Emergency Rooms for Rapid Triage (AVERT) clinical trial (#NCT02483429). Our model was derived from a preliminary dataset 2022-01-01T00:00:00Z20222025-05-29T16:11:52.324Z2025-04-04T09:32:17.241ZS-EPMC94036043603431110.3389/fneur.2022.963968