Toward Accessible Mobility: A Theoretical Approach to Seizure Detection in Driver Monitoring Systems

Epilepsy is a chronic neurological condition with unpredictable seizures that often trigger driving restrictions limiting autonomy and social participation. No driver monitoring systems (DMS) alert medical events like seizures, leaving a major safety and accessibility gap. Prior work in automatic seizure detection (ASD) identifies distinctive ocular signatures of seizures: ictal nystagmus, versive gaze, and prolonged fixation. Modern vehicles already use in-cabin eye tracking to monitor fatigue and distraction. This theoretical paper proposes a framework in which DMS eye trackers, combined with machine learning, detect seizures by flagging ictal deviations from driver-specific baseline gaze behavior. Key challenges include establishing external validity across ambient lighting and behavioral variability, managing false positives and false negatives, and distinguishing involuntary medical events from ordinary inattention. By reframing eye tracking from passive monitoring to proactive intervention, seizure-aware DMS could enhance road safety and expand mobility for people with epilepsy and other causes of sudden driver incapacitation.