Objective: The consolidation of tele-rehabilitation for the treatment of many diseases over the last decades is a result of its cost-effective results and its ability to offer access to rehabilitation in remote areas. Tele-rehabilitation operates over a distance, so vulnerable patients are never exposed to unnecessary risks. Despite its low cost, the need for a professional to assess therapeutic exercises and proper corporal movements on line should also be mentioned.
Background: The focus of this abstract is on presenting a tele-rehabilitation system for patients suffering from Parkinson’s disease in remote villages and other less accessible locations. A full-stack is presented using big data frameworks that facilitate communication between the patient and the occupational therapist, the recording of each session and even automated evaluation of the exercises using Artificial Intelligence (AI) techniques.
Method: Currently, the system is under application within the framework of a project in the province of Burgos, Spain, for evaluating the use of a multidisciplinary tele-rehabilitation home fall prevention program.
Results: The system has been designed with ease of use in mind, so that users are less likely to abandon it due to excessive difficulty. The on-screen human-machine interface therefore responds fluidly to the patient’s movements and colour codes the positions of the body. The AI techniques are able to estimate the position of the patient’s skeleton, making it easier to
therapist to check whether or not the exercises are being done properly. In addition, the health staff are expected to assign a series of scores to each session based on the quality of the patient’s physical therapy, providing feedback and encouragement to increase motivation and adherence to the program.
Conclusion: Big data technologies are used to process the numerous videos that are generated in the course of treating simultaneous patients. Moreover, once the skeleton has been identified, the comparisons can be drawn along two lines: either comparing treatment sessions with the patient (for assessing improvements over the courseof time) or comparing the exercises that the therapist proposes (evaluating the differences between the gold standard and patients’ exercises).
To cite this abstract in AMA style:A. Olivares-Gil, JM. Ramírez-Sanz, JL. Garrido-Labrador, á. García-Bustillo, á. Arnaiz-González, JF. Díez-Pastor, J. González-Santos, JJ. González-Bernal, M. Allende-Río, F. Valiñas-Sieiro, JM. Trejo-Gabriel-Galan, E. Cubo. A low-cost system using a big-data deep-learning framework for assessing physical tele-rehabilitation: a proof-of-concept [abstract]. Mov Disord. 2022; 37 (suppl 2). https://www.mdsabstracts.org/abstract/a-low-cost-system-using-a-big-data-deep-learning-framework-for-assessing-physical-tele-rehabilitation-a-proof-of-concept/. Accessed December 1, 2023.
« Back to 2022 International Congress
MDS Abstracts - https://www.mdsabstracts.org/abstract/a-low-cost-system-using-a-big-data-deep-learning-framework-for-assessing-physical-tele-rehabilitation-a-proof-of-concept/