Motor signatures in digitized cognitive and memory tests enhances characterization of Parkinson’s disease

Background Although there is a growing interest in using wearable sensors to characterize movement disorders, there is a lack of methodology for developing clinically interpretable kinematics biomarkers. Such digital biomarkers would provide a more objective diagnosis, capturing finer degrees of motor deficits, while retaining the information of traditional clinical tests. Objectives We aim at digitizing traditional tests of cognitive and memory performance to derive motor biometrics of pen-strokes and voice, thereby complementing clinical tests with objective criteria, while enhancing the overall motor characterization of Parkinson’s disease (PD). Methods 35 participants including patients with PD, healthy young and age-matched controls performed a series of drawing and memory tasks, while their pen movement and voice were digitized. We examined the moment-to-moment variability of time-series reflecting the pen speed and voice amplitude. Results The stochastic signatures of the fluctuations in pen drawing speed and voice amplitude of patients with PD show lower noise-to-signal ratio compared to those derived from the younger and age-matched neurotypical controls. It appears that contact motions of the pen strokes on the tablet evokes sensory feedback for more immediate and predictable control in PD, compared to controls, while voice amplitude loses its neurotypical richness. Conclusions We offer new standardized data types and analytics to help advance our understanding of hidden motor aspects of cognitive and memory clinical assays commonly used in Parkinson’s disease.