Assessment of parkinson’s disease at-home using a natural interface based system

A system for the management of the automatic assessment of Parkinson’s Disease (PD) at-home is presented. The system is based on a non-contact and natural human computer interface which is suitable for motor impaired users, as are PD patients. The interface, built around optical RGB-Depth devices, allows for both gesture-based interaction with the system and tracking of hands and body movements during the performance of standard upper and lower limb tasks, as specified by the Unified Parkinson’s Disease Rating Scale (UPDRS). The accurate tracking and characterization of the movements allows for an automatic and objective assessment of the UPDRS tasks, making feasible the monitoring of motor fluctuations at-home and on daily basis, which are important features in the management of the disease progression. The assessment of the different tasks is performed by machine learning techniques. Selected kinematic parameters characterizing the movements are input to trained classifiers to rate the motor performance. Results on monitoring experiments at-home and on the system accuracy as compared to clinical evaluations are presented and discussed.