AI-Powered Detection and Rehabilitation Support for Brain Wellness

Abstract

Concussion diagnosis remains a complex and resource-intensive process, yet early detection is essential to reducing the risk of long-term neurological impairment. This feasibility study explores a cost-effective, portable solution lever-aging the ubiquity of smartphones. Unlike previous approaches that relied on virtual reality environments, our method adapts established assessment techniques to a more accessible platform by utilizing front-facing sensors and integrated eye-tracking capabilities available in modern mobile devices. Specifically, we investigate the feasibility of combining ARKit-based gaze estimation with lightweight electroencephalography (EEG) sensors to measure saccades, fixation, reaction time, and neural activity. Through multi-modal data fusion and machine learning, we assess the system’s ability to reliably identify potential concussion symptoms and provide timely, on-site screening prior to formal clinical evaluation. This work does not replace medical diagnosis but establishes the foundation for an accessible mobile health tool aimed at improving the speed and reach of concussion screening.

Ähnliche Arbeiten