A low cost, adaptive mixed reality system for home-based stroke rehabilitation

Abstract

This paper presents a novel, low-cost, real-time adaptive multimedia environment for home-based upper extremity rehabilitation of stroke survivors. The primary goal of this system is to provide an interactive tool with which the stroke survivor can sustain gains achieved within the clinical phase of therapy and increase the opportunity for functional recovery. This home-based mediated system has low cost sensing, off the shelf components for the auditory and visual feedback, and remote monitoring capability. The system is designed to continue active learning by reducing dependency on real-time feedback and focusing on summary feedback after a single task and sequences of tasks. To increase system effectiveness through customization, we use data from the training strategy developed by the therapist at the clinic for each stroke survivor to drive automated system adaptation at the home. The adaptation includes changing training focus, selecting proper feedback coupling both in real-time and in summary, and constructing appropriate dialogues with the stroke survivor to promote more efficient use of the system. This system also allows the therapist to review participant's progress and adjust the training strategy weekly.

Automated movement assessment in stroke rehabilitation

“…Even expert clinicians cannot simultaneously observe all aspects of upper extremity pathological movement or compare such observations to a standardized value. There is considerable evidence showing that individual therapists direct their attention towards different elements and assess them differently when evaluating performance in situ and real-time, or when later rating videos of performance (Chen et al, 2011a;Cirstea and Levin, 2007;Nordin et al, 2014;Wolf et al, 2006). The relation of movement quality to function is therefore difficult to ascertain in a standardized quantitative manner (Levin et al, 2008;Chen et al, 2011b).…”