Quantitative and accurate tracking of neurodegenerative disease remains an ongoing challenge. Diagnosis requires patients to undergo time-consuming neuropsy- chological tests that suffer from high-retest variability, making it difficult to assess the progression of the disease or a patient’s response to experimental treatments.
We tackle the lack of an objective measurement to track the progression of neurodegenerative diseases by designing algorithms that can quantify subtle changes across time in eye movement patterns that correlate with disease progression. One such feature is saccade latency -- the time delay between the appearance of a visual stimulus and when the eye starts to move towards said stimulus. As a result, an unobtrusive tool that measures saccade latency (or other metrics of eye movement) consistently across time can enable the quantification of disease progression and the assessment of a patient’s response to treatment.
We propose a pipeline to modify and evaluate a set of candidate eye-tracking algorithms to operate on video sequences obtained from an iPhone 6, for accurate and robust determination of saccade latency. A variant of the iTracker algorithm performed most robustly and resulted in mean saccade latencies and associated standard deviations on iPhone recordings that were essentially the same as those obtained from recordings using a high-end, high-speed camera. Results suggest that accurate and robust saccade latency determination is feasible using consumer-grade cameras and might, therefore, enable unobtrusive tracking of neurodegenerative disease progression.