Regular RGB-Video-Based Eye Movement Assessment for Parkinson’s Disease

Abstract

Eye-tracking, as an accessible, noninvasive technology, offers valuable insights into the human motor and cognitive functions, and it is an essential tool in studying neurodegenerative diseases such as Parkinson’s disease (PD). While current eye movement assessment for PD diagnosis mainly relies on high-end, specialized eye-tracker equipment, this work demonstrates that advanced deep learning (DL) methods using RGB-video from regular cameras (with 60 f/s sampling rate, $1920\times 1080$ image resolution) can provide promising performance on PD eye movement assessment. Our contributions are twofold: first, we show the potential and feasibility of using readily accessible, regular RGB camera data for PD eye movement assessment, making it more attractive for wide applicability in practice. Second, we propose a novel PD classification model by exploring temporal eye movement patterns from regular RGB-video data, and it can achieve performance comparable to or even better than current standard methods reliant on commercial, specialized eye-tracking equipment. The results highlight the promise of regular RGB-video-based PD assessment and the potential for more accessible diagnostic tools in PD studies.