Digital markers from smartwatch data relate to non-motor clinical examinations of Parkinson’s disease

Abstract

AbstractMonitoring of Parkinson’s disease (PD) has seen substantial improvement over recent years as digital sensors enable a passive and continuous collection of information in the home environment. However, the primary focus of this work has been motor symptoms, with little focus on the non-motor aspects of the disease. To address this, we combined longitudinal clinical non-motor assessment data and digital multi-sensor data from the Verily Study Watch for 85 participants from the Parkinson’s Progression Monitoring Initiative (PPMI) cohort with a diagnosis of PD. We show that digitally collected physical activity and sleep markers do significantly relate to clinical non-motor assessments of cognitive, autonomic, and daily living impairment. The observed poor predictive performance, however, highlights the need for better targeted digital markers to enable a monitoring of non-motor symptoms.