Search

Objective: To investigate the feasibility of a wear-able, soft-robotic glove system developed to combine assistive support in daily life with performing therapeutic exercises on a computer at home (the HandinMind system)., Design: Feasibility study., Patients: Five chronic stroke patients with limitations in activities of daily living due to impaired hand function., Methods: Participants performed a usability test and several functional tasks with the HandinMind system across 2 sessions. Feasibility was measured using the System Usability Scale (SUS), Intrinsic Motivation Inventory (IMI) and performance times of the functional tasks., Results: User acceptance measured by the SUS and IMI was scored high. The median SUS scores of sessions 1 and 2 were 80.0 (interquartile range (IQR) 70.0-88.8) and 77.5 (IQR 75.0-87.5), respectively, and the median IMI score was 6.3 points out of 7 points (IQR 6.2-6.3). Functional task performance was initially slower with the HandinMind glove compared with performance without the glove, but improved up to the level of performance without the glove across no more than 3 repetitions., Conclusion: Chronic stroke patients with impaired hand function were positive about the feasibility of the first prototype of the HandinMind system. How-ever, performance and ease of use of the system should be improved further in future development phases.

To support stroke survivors in activities of daily living, wearable soft-robotic gloves are being developed. An essential feature for use in daily life is detection of movement intent to trigger actuation without substantial delays. To increase efficacy, the intention to grasp should be detected as soon as possible, while other movements are not detected instead. Therefore, the possibilities to classify reach and grasp movements of stroke survivors, and to detect the intention of grasp movements, were investigated using inertial sensing. Hand and wrist movements of 10 stroke survivors were analyzed during reach and grasp movements using inertial sensing and a Support Vector Machine classifier. The highest mean accuracies of 96.8% and 83.3% were achieved for single- and multi-user classification respectively. Accuracies up to 90% were achieved when using 80% of the movement length, or even only 50% of the movement length after choosing the optimal kernel per person. This would allow for an earlier detection of 300–750ms, but at the expense of accuracy. In conclusion, inertial sensing combined with the Support Vector Machine classifier is a promising method for actuation of grasp-supporting devices to aid stroke survivors in activities of daily living. Online implementation should be investigated in future research. [ABSTRACT FROM AUTHOR]