A Feasibility Study of Expanded Home-Based Telerehabilitation After Stroke

Abstract

Introduction: High doses of activity-based rehabilitation therapy improve outcomes after stroke, but many patients do not receive this for various reasons such as poor access, transportation difficulties, and low compliance. Home-based telerehabilitation (TR) can address these issues. The current study evaluated the feasibility of an expanded TR program. Methods: Under the supervision of a licensed therapist, adults with stroke and limb weakness received home-based TR (1 h/day, 6 days/week) delivered using games and exercises. New features examined include extending therapy to 12 weeks duration, treating both arm and leg motor deficits, patient assessments performed with no therapist supervision, adding sensors to real objects, ingesting a daily experimental (placebo) pill, and generating automated actionable reports. Results: Enrollees (n = 13) were median age 61 (IQR 52-65.5), and 129 (52-486) days post-stroke. Patients initiated therapy on 79.9% of assigned days and completed therapy on 65.7% of days; median therapy dose was 50.4 (33.3-56.7) h. Non-compliance doubled during weeks 7-12. Modified Rankin scores improved in 6/13 patients, 3 of whom were >3 months post-stroke. Fugl-Meyer motor scores increased by 6 (2.5-12.5) points in the arm and 1 (-0.5 to 5) point in the leg. Assessments spanning numerous dimensions of stroke outcomes were successfully implemented; some, including a weekly measure that documented a decline in fatigue (p = 0.004), were successfully scored without therapist supervision. Using data from an attached sensor, real objects could be used to drive game play. The experimental pill was taken on 90.9% of therapy days. Automatic actionable reports reliably notified study personnel when critical values were reached. Conclusions: Several new features performed well, and useful insights were obtained for those that did not. A home-based telehealth system supports a holistic approach to rehabilitation care, including intensive rehabilitation therapy, secondary stroke prevention, screening for complications of stroke, and daily ingestion of a pill. This feasibility study informs future efforts to expand stroke TR. Clinical Trial Registration: Clinicaltrials.gov, # NCT03460587.

Keywords: holistic; recovery; rehabilitation; stroke; telehealth.

Figure 1

Compliance with TR assignments declined during the 12 weeks. (A) During TR weeks 1–6 (days 1–36), there was a decline in TR session initiation compared to weeks 7–12 (days 37–72), from 86.4 to 73.5% (p < 0.0001). (B) There was a similar decline in in TR session completion, from 76.9 to 54.6% (p < 0.0001).

Figure 2

For the virtual varmint game, a camera under the table pointed at the floor captured live images, including the patient's paretic foot, that were projected onto the screen of a tabletop tablet. When patients directed their gaze at the tabletop, they were thus able to see real-time images of their foot movements. A virtual varmint was introduced into the tablet image, which the patient was able to manipulate with their foot. (A) A virtual image of a varmint is introduced onto the screen of the tabletop tablet. (B) The patient moves his foot toward the virtual varmint. (C) The patient swats the virtual varmint with his foot, scoring points.

Figure 3

Sensors were attached to real objects to play a game that drives an iADL. The patient grasped an actual water pitcher onto which an accelerometer (green arrow) was attached magnetically. Accelerometer data were sent to the computer running the TR program. As the subject rotated the hand-held pitcher, the figure of a pitcher on the video screen moved synchronously. In this way, the subject used a real object to play a game, displayed on the TR computer screen, where the goal was to fill empty cups to the correct level.

Figure 4

Photographs were used to confirm that the study pill was taken each day as instructed. (A) The patient is seated; arrow indicates cap on the bottle holding study pills. (B) The patient has removed the pill bottle lid and placed onto the trackpad; arrow indicates the lid. (C) The patient has removed one pill and placed into her palm; arrow indicates the pill. (D) The patient has taken the pill. (E) The lid has been replaced; arrow indicates the lid.

Figure 5

GDS scores during a live visit 12 weeks after study entry are closely related to GDS scores obtained during a TR videoconference 9 weeks after study entry (r = 0.89, p < 0.0001, n = 12). The intraclass correlation coefficient was 0.66.