Unknown

Dataset Information

0

Force Myography for Monitoring Grasping in Individuals with Stroke with Mild to Moderate Upper-Extremity Impairments: A Preliminary Investigation in a Controlled Environment.


ABSTRACT: There is increasing research interest in technologies that can detect grasping, to encourage functional use of the hand as part of daily living, and thus promote upper-extremity motor recovery in individuals with stroke. Force myography (FMG) has been shown to be effective for providing biofeedback to improve fine motor function in structured rehabilitation settings, involving isolated repetitions of a single grasp type, elicited at a predictable time, without upper-extremity movements. The use of FMG, with machine learning techniques, to detect and distinguish between grasping and no grasping, continues to be an active area of research, in healthy individuals. The feasibility of classifying FMG for grasp detection in populations with upper-extremity impairments, in the presence of upper-extremity movements, as would be expected in daily living, has yet to be established. We explore the feasibility of FMG for this application by establishing and comparing (1) FMG-based grasp detection accuracy and (2) the amount of training data necessary for accurate grasp classification, in individuals with stroke and healthy individuals. FMG data were collected using a flexible forearm band, embedded with six force-sensitive resistors (FSRs). Eight participants with stroke, with mild to moderate upper-extremity impairments, and eight healthy participants performed 20 repetitions of three tasks that involved reaching, grasping, and moving an object in different planes of movement. A validation sensor was placed on the object to label data as corresponding to a grasp or no grasp. Grasp detection performance was evaluated using linear and non-linear classifiers. The effect of training set size on classification accuracy was also determined. FMG-based grasp detection demonstrated high accuracy of 92.2% (σ = 3.5%) for participants with stroke and 96.0% (σ = 1.6%) for healthy volunteers using a support vector machine (SVM). The use of a training set that was 50% the size of the testing set resulted in 91.7% (σ = 3.9%) accuracy for participants with stroke and 95.6% (σ = 1.6%) for healthy participants. These promising results indicate that FMG may be feasible for monitoring grasping, in the presence of upper-extremity movements, in individuals with stroke with mild to moderate upper-extremity impairments.

SUBMITTER: Sadarangani GP 

PROVIDER: S-EPMC5529400 | biostudies-other | 2017

REPOSITORIES: biostudies-other

Similar Datasets

| S-EPMC9397847 | biostudies-literature
| S-EPMC4782664 | biostudies-literature
| S-EPMC3972918 | biostudies-literature
| S-EPMC6208648 | biostudies-literature
| S-EPMC6464751 | biostudies-literature
| S-EPMC4086414 | biostudies-literature
| S-EPMC7387111 | biostudies-literature
| S-EPMC8268536 | biostudies-literature
| S-EPMC6989675 | biostudies-literature
| S-EPMC7701100 | biostudies-literature