AI-Driven Analysis of Wrist-Worn Sensor Data for Monitoring Individual Treatment Response and Optimizing Levodopa Dosing in Parkinson’s Disease

Parkinson’s Disease is a progressive neurodegenerative disorder marked by motor fluctuations that complicate treatment with levodopa. Traditional approaches to dosing are often inadequate for capturing the complex and dynamic nature of these fluctuations. In this study, we present a novel algorithm for continuous motor state monitoring based on data from a wrist-worn inertial measurement unit sensor. The PD9™ algorithm translates sensor data into a continuous motor state scale that captures the severity of bradykinesia, dyskinesia, and ON states. Data collected from 67 patients over 55,482 minutes were analyzed to characterize levodopa cycles and their impact on motor states. Results re-vealed distinct patterns of symptom severity changes based on motor state at the time of levodopa administration, highlighting the potential of individualized, mo-tor-state-informed dosing strategies. These findings underscore the importance of AI-enabled continuous monitoring for optimizing Parkinson care and improving patient outcomes. Our approach demonstrates the potential of integrating wearable technology and machine learning to revolutionize treatment personalization in neurodegenerative disorders.