NeuralCipher Research overview
The text below is the source article’s original abstract under a verified reuse license. cc by
We report on a Kinect-based, augmented reality, real-time physiotherapy platform tailored to Parkinson's disease (PD) patients. The platform employs a Kinect sensor to extract real-time 3D skeletal data (joint information) from a patient facing the sensor (at 30 frames per second). In addition, a small collection of exercises practiced in traditional physiotherapy for PD patients has been implemented in the Unity 3D game engine. Each exercise employs linear or circular movement patterns and poses very light-weight processing demands on real-time computations. During an exercise, trainer instruction demonstrates correct execution and Kinect-provided 3D joint data are fed to the game engine and compared to exercise-specific control routines to assess proper posture and body control in real time. When an exercise is complete, performance metrics appropriate for that exercise are computed and displayed on screen to enable the attending physiotherapist to fine-tune the exercise to the abilities/needs of an individual patient as well as to provide performance feedback to the patient. The platform can operate in a physiotherapist's office and, following appropriate validation, in a home environment. Finally, exercises can be parameterized meaningfully, depending on the intended purpose (motor assessment versus plain exercise at home).
Scientific assessment
Research question
Assess the question within the original study’s scope.
Methods & sample
Check the source article for study design and sample details.
Key findings
An editorially approved findings summary is not yet published for this record.
Limitations
Generalizability, bias and clinical meaning require separate assessment.
Methods, samples and clinical conclusions are not inferred from bibliographic metadata.