Now showing 1 - 2 of 2
No Thumbnail Available
Patient Involvement With Home-Based Exercise Programs: Can Connected Health Interventions Influence Adherence?
2018-03-01, Argent, Rob, Daly, Ailish, Caulfield, Brian
Adherence to home exercise in rehabilitation is a significant problem, with estimates of nonadherence as high as 50%, potentially having a detrimental effect on clinical outcomes. In this viewpoint, we discuss the many reasons why patients may not adhere to a prescribed exercise program and explore how connected health technologies have the ability to offer numerous interventions to enhance adherence; however, it is hard to judge the efficacy of these interventions without a robust measurement tool. We highlight how well-designed connected health technologies, such as the use of mobile devices, including mobile phones and tablets, as well as inertial measurement units, provide us with the opportunity to better support the patient and clinician, with a data-driven approach that incorporates features designed to increase adherence to exercise such as coaching, self-monitoring and education, as well as remotely monitor adherence rates more objectively.
No Thumbnail Available
Rehabilitation Exercise Segmentation for Autonomous Biofeedback Systems with ConvFSM
2019-06-27, Bevilacqua, Antonio, Brennan, Louise, Argent, Rob, Caulfield, Brian, Kechadi, Tahar
Segmenting physical movements is a key step for any accelerometry-based autonomous biofeedback system oriented to rehabilitation and physiotherapy activities. Fundamentally, this can be reduced to the detection of recurrent patterns, also called motion primitives, in longer inertial signals. Most of the solutions developed in the literature require extensive domain knowledge, or are incapable of scaling to complex motion patterns and new exercises. In this paper, we explore the capabilities of inertial measurement units for the segmentation of upper limb rehabilitation exercises. To do so, we introduce a novel segmentation technique based on Convolutional Neural Networks and Finite State Machines, called ConvFSM. ConvFSM is able to isolate motion primitives from raw streaming data, using very little domain knowledge. We also investigate different combinations of sensors, in order to identify the most effective and flexible setup that could fit a home-based rehabilitation feedback system. Experimental results are presented, based on a dataset obtained from a combination of common upper limb and lower limb exercises.