Postural instability is one of the main burdens of Parkinson's Disease with important impacts on people safety and quality of life, since it increases the risk of falls and injuries. Home monitoring of the alterations of postural stability, as a consequence of therapies and disease progression, is highly desirable for a better care and management of the disease. In this context, we present a system for the automatic evaluation of postural instability suitable to be used at home. The system is built around an optical RGB-Depth device, which allows the tracking of the body movements both for the interaction and for the assessment. A user-friendly human-machine interaction, suited for impaired people allows for the self-management of the system. A set of tasks has been designed according to standard clinical tests for static and dynamic balance assessment. Tasks are delivered and analyzed by the system to characterize the performance of the subject under test. Temporal and postural kinematic parameters are estimated and used for the objective valuation of the postural instability. The compliance of the automatic evaluation respect to clinical assessment is supported by supervised classifiers in a machine learning approach. Preliminary results on the system accuracy are presented and discussed.
A vision-based approach for the at home assessment of postural stability in Parkinson's disease
Claudia Ferraris;Roberto Nerino;Antonio Chimienti;
2019
Abstract
Postural instability is one of the main burdens of Parkinson's Disease with important impacts on people safety and quality of life, since it increases the risk of falls and injuries. Home monitoring of the alterations of postural stability, as a consequence of therapies and disease progression, is highly desirable for a better care and management of the disease. In this context, we present a system for the automatic evaluation of postural instability suitable to be used at home. The system is built around an optical RGB-Depth device, which allows the tracking of the body movements both for the interaction and for the assessment. A user-friendly human-machine interaction, suited for impaired people allows for the self-management of the system. A set of tasks has been designed according to standard clinical tests for static and dynamic balance assessment. Tasks are delivered and analyzed by the system to characterize the performance of the subject under test. Temporal and postural kinematic parameters are estimated and used for the objective valuation of the postural instability. The compliance of the automatic evaluation respect to clinical assessment is supported by supervised classifiers in a machine learning approach. Preliminary results on the system accuracy are presented and discussed.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.