Problem
Research questions and friction points this paper is trying to address.
saccadic eye movement
digital biomarker
neurophysiologic states
data scarcity
privacy issues
GenEyePose: Patient-Free, Knowledge-Based Saccadic Eye Movement Modeling for Digital Neurophysiologic Biomarker Development
🤖 AI Summary
Current video-based oculomotor digital biomarkers face significant challenges in screening and localizing neurological disorders due to privacy constraints and the scarcity of real patient data. This study proposes the first multimodal synthetic eye movement generation framework that operates without involving actual patients, integrating knowledge-driven modeling with deep learning classifiers to enable generalizable saccade analysis. By circumventing the clinical data acquisition bottleneck, the approach achieves an AUROC of 0.76 and a sensitivity of 0.71 on real-world clinical data, demonstrating that purely synthetic data can effectively support both neurological disease screening and neuroanatomical localization while exhibiting strong generalization potential.
📝 Abstract
Eye movements, including saccades, are widely regarded as highly sensitive and objective biomarkers of neurophysiologic states. Detecting saccadic signatures in neurologic diseases offers a rapid, portable alternative to brain imaging, avoiding access and cost barriers. Currently, there are no robust AI-enabled video-oculographic solutions (e.g., digital biomarkers) for screening, triaging, or localizing brain abnormalities due to privacy issues and scarce datasets. In this work, we propose the first fully synthetic, patient-free, multimodal eye movement generation pipeline for generalizable saccade analysis. Using this synthetic dataset, we trained a deep learning classifier to distinguish between normal and abnormal (hypometria and hypermetria) saccadic accuracies and evaluated its performance on real-world clinical data. The model achieved an AUROC of 0.76 and a sensitivity of 0.71, showing that the synthetic data has strong potential to generalize for clinical applications, including as a screening tool in at-home and emergency room settings or a tool for precise neuroanatomic localization.
Innovation
Methods, ideas, or system contributions that make the work stand out.
synthetic data generation
patient-free modeling
saccadic eye movement
digital biomarker
knowledge-based AI
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
