Summary
Background: Traditional rehabilitation sessions are often a slow, tedious, disempowering and
non-motivational process, supported by clinical assessment tools, i.e. evaluation
scales that are prone to subjective rating and imprecise interpretation of patient’s
performance. Poor patient motivation and insufficient accuracy are thus critical factors
that can be improved by new sensing/processing technologies.
Objectives: We aim to develop a portable and affordable system, suitable for home rehabilitation,
which combines vision-based and wearable sensors. We introduce a novel approach for
examining and characterizing the rehabilitation movements, using quantitative descriptors.
We propose new Movement Performance Indicators (MPIs) that are extracted directly
from sensor data and quantify the symmetry, velocity, and acceleration of the movement
of different body/hand parts, and that can potentially be used by therapists for diagnosis
and progress assessment.
Methods: First, a set of rehabilitation exercises is defined, with the supervision of neurologists
and therapists for the specific case of Parkinson’s disease. It comprises full-body
movements measured with a Kinect device and fine hand movements, acquired with a data
glove. Then, the sensor data is used to compute 25 Movement Performance Indicators,
to assist the diagnosis and progress monitoring (assessing the disease stage) in Parkinson’s
disease. A kinematic hand model is developed for data verification and as an additional
resource for extracting supplementary movement information.
Results: Our results show that the proposed Movement Performance Indicators are relevant for
the Parkinson’s disease assessment. This is further confirmed by correlation of the
proposed indicators with clinical tapping test and UPDRS clinical scale. Classification
results showed the potential of these indicators to discriminate between the patients
and controls, as well as between the stages that characterize the evolution of the
disease.
Conclusions: The proposed sensor system, along with the developed approach for rehabilitation
movement analysis have a significant potential to support and advance traditional
rehabilitation therapy. The main impact of our work is two-fold: (i) the proposition
of an approach for supporting the therapists during the diagnosis and monitoring evaluations
by reducing subjectivity and imprecision, and (ii) offering the possibility of the
system to be used at home for rehabilitation exercises in between sessions with doctors
and therapists.
Keywords
Rehabilitation - movement analysis - Kinect - wearable sensors
