Assessment-driven selection and adaptation of exercise difficulty in robot-assisted therapy: a pilot study with a hand rehabilitation robot

Abstract

BackgroundSelecting and maintaining an engaging and challenging training difficulty level in robot-assisted stroke rehabilitation remains an open challenge. Despite the ability of robotic systems to provide objective and accurate measures of function and performance, the selection and adaptation of exercise difficulty levels is typically left to the experience of the supervising therapist.MethodsWe introduce a patient-tailored and adaptive robot-assisted therapy concept to optimally challenge patients from the very first session and throughout therapy progress. The concept is evaluated within a four-week pilot study in six subacute stroke patients performing robot-assisted rehabilitation of hand function. Robotic assessments of both motor and sensory impairments of hand function conducted prior to the therapy are used to adjust exercise parameters and customize difficulty levels. During therapy progression, an automated routine adapts difficulty levels from session to session to maintain patients’ performance around a target level of 70%, to optimally balance motivation and challenge.ResultsRobotic assessments suggested large differences in patients’ sensorimotor abilities that are not captured by clinical assessments. Exercise customization based on these assessments resulted in an average initial exercise performance around 70% (62% ± 20%, mean ± std), which was maintained throughout the course of the therapy (64% ± 21%). Patients showed reduction in both motor and sensory impairments compared to baseline as measured by clinical and robotic assessments. The progress in difficulty levels correlated with improvements in a clinical impairment scale (Fugl-Meyer Assessment) (r s = 0.70), suggesting that the proposed therapy was effective at reducing sensorimotor impairment.ConclusionsInitial robotic assessments combined with progressive difficulty adaptation have the potential to automatically tailor robot-assisted rehabilitation to the individual patient. This results in optimal challenge and engagement of the patient, may facilitate sensorimotor recovery after neurological injury, and has implications for unsupervised robot-assisted therapy in the clinic and home environment.Trial registration: ClinicalTrials.gov, NCT02096445Electronic supplementary materialThe online version of this article (doi:10.1186/1743-0003-11-154) contains supplementary material, which is available to authorized users.

Adaptive Patient-Cooperative Control of a Compliant Ankle Rehabilitation Robot (CARR) With Enhanced Training Safety

“…In addition, Pérez-Rodríguez, et al [28] proposed a new AAN control algorithm to provide anticipatory actuation. To tailor the therapy to each patient, Metzger, et al [29] adapted exercise difficulty based on an assessment-driven selection for hand training. The focus of such adaptation algorithms is that the robot torque varies over time to continuously challenge the patient to exert his/her own effort and thus actively engage in the rehabilitation treatment [26].…”

An intelligent, adaptive, performance‐sensitive, and virtual reality‐based gaming platform for the upper limb

“…Our VR‐based system was adaptive to the participant's PF while the participant interacted with the VR‐based tasks. Here, a cutoff score of 70% was used in tasks across different difficulty levels, similar to that used for robot‐assisted rehabilitation tasks, for outpatient clinics, and technology‐assisted skill learning –. The task switching module offered tasks (chosen randomly) of varying challenges (difficulty level) based on one's PF using a state machine representation (Figure )…”

“…Here, a cutoff score of 70% was used in tasks across different difficulty levels, similar to that used for robot-assisted rehabilitation tasks, for outpatient clinics, and technology-assisted skill learning. [40][41][42] The task switching module offered tasks (chosen randomly) of varying challenges (difficulty level) based on one's PF using a state machine representation (Figure 4). 43 If a participant's performance in a task belonging to a particular difficulty level was "Adequate" (≥70%; condition C1), say DL1, then our task switching module offered tasks of higher difficulty (DL2), except for DL3, because DL3 was the highest difficulty level.…”

Closed-Loop Task Difficulty Adaptation during Virtual Reality Reach-to-Grasp Training Assisted with an Exoskeleton for Stroke Rehabilitation

“…Such an adaptation strategy has the potential to facilitate reinforcement learning (Naros et al, 2016b) by progressively challenging the patient (Naros and Gharabaghi, 2015). Recent studies explored automated adaptation of training difficulty in stroke rehabilitation of less severely affected patients (Metzger et al, 2014; Wittmann et al, 2015). More specifically, both robot-assisted rehabilitation of proprioceptive hand function (Metzger et al, 2014) and inertial sensor-based virtual reality feedback of the arm (Wittmann et al, 2015) benefit from assessment-driven adjustments of exercise difficulty.…”

“…Recent studies explored automated adaptation of training difficulty in stroke rehabilitation of less severely affected patients (Metzger et al, 2014; Wittmann et al, 2015). More specifically, both robot-assisted rehabilitation of proprioceptive hand function (Metzger et al, 2014) and inertial sensor-based virtual reality feedback of the arm (Wittmann et al, 2015) benefit from assessment-driven adjustments of exercise difficulty. Furthermore, a direct comparison between adaptive BRI training and non-adaptive training (Naros et al, 2016b) or sham adaptation (Bauer et al, 2016a) in healthy patients revealed the impact of reinforcement-based adaptation for the improvement of performance.…”