Dataset Information

Learning an EMG Controlled Game: Task-Specific Adaptations and Transfer.

ABSTRACT: Video games that aim to improve myoelectric control (myogames) are gaining popularity and are often part of the rehabilitation process following an upper limb amputation. However, direct evidence for their effect on prosthetic skill is limited. This study aimed to determine whether and how myogaming improves EMG control and whether performance improvements transfer to a prosthesis-simulator task. Able-bodied right-handed participants (N = 28) were randomly assigned to 1 of 2 groups. The intervention group was trained to control a video game (Breakout-EMG) using the myosignals of wrist flexors and extensors. Controls played a regular Mario computer game. Both groups trained 20 minutes a day for 4 consecutive days. Before and after training, two tests were conducted: one level of the Breakout-EMG game, and grasping objects with a prosthesis-simulator. Results showed a larger increase of in-game accuracy for the Breakout-EMG group than for controls. The Breakout-EMG group moreover showed increased adaptation of the EMG signal to the game. No differences were found in using a prosthesis-simulator. This study demonstrated that myogames lead to task-specific myocontrol skills. Transfer to a prosthesis task is therefore far from easy. We discuss several implications for future myogame designs.

SUBMITTER: van Dijk L

PROVIDER: S-EPMC4996424 | biostudies-other | 2016

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Learning an EMG Controlled Game: Task-Specific Adaptations and Transfer.

van Dijk Ludger L van der Sluis Corry K CK van Dijk Hylke W HW Bongers Raoul M RM

PloS one 20160824 8

Video games that aim to improve myoelectric control (myogames) are gaining popularity and are often part of the rehabilitation process following an upper limb amputation. However, direct evidence for their effect on prosthetic skill is limited. This study aimed to determine whether and how myogaming improves EMG control and whether performance improvements transfer to a prosthesis-simulator task. Able-bodied right-handed participants (N = 28) were randomly assigned to 1 of 2 groups. The interven ...[more]

PMID: 27556154

Similar Datasets

Project description:As a leading cause of loss of functional movement, stroke often makes it difficult for patients to walk. Interventions to aid motor recovery in stroke patients should be carried out as a matter of urgency. However, muscle activity in the knee is usually too weak to generate overt movements, which poses a challenge for early post-stroke rehabilitation training. Although electromyography (EMG)-controlled exoskeletons have the potential to solve this problem, most existing robotic devices in rehabilitation centers are expensive, technologically complex, and allow only low training intensity. To address these problems, we have developed an EMG-controlled knee exoskeleton for use at home to assist stroke patients in their rehabilitation. EMG signals of the subject are acquired by an easy-to-don EMG sensor and then processed by a Kalman filter to control the exoskeleton autonomously. A newly-designed game is introduced to improve rehabilitation by encouraging patients' involvement in the training process. Six healthy subjects took part in an initial test of this new training tool. The test showed that subjects could use their EMG signals to control the exoskeleton to assist them in playing the game. Subjects found the rehabilitation process interesting, and they improved their control performance through 20-block training, with game scores increasing from 41.3 ± 15.19 to 78.5 ± 25.2. The setup process was simplified compared to traditional studies and took only 72 s according to test on one healthy subject. The time lag of EMG signal processing, which is an important aspect for real-time control, was significantly reduced to about 64 ms by employing a Kalman filter, while the delay caused by the exoskeleton was about 110 ms. This easy-to-use rehabilitation tool has a greatly simplified training process and allows patients to undergo rehabilitation in a home environment without the need for a therapist to be present. It has the potential to improve the intensity of rehabilitation and the outcomes for stroke patients in the initial phase of rehabilitation.

Project description:BACKGROUND AND PURPOSE:MR imaging-based modeling of tumor cell density can substantially improve targeted treatment of glioblastoma. Unfortunately, interpatient variability limits the predictive ability of many modeling approaches. We present a transfer learning method that generates individualized patient models, grounded in the wealth of population data, while also detecting and adjusting for interpatient variabilities based on each patient's own histologic data. MATERIALS AND METHODS:We recruited patients with primary glioblastoma undergoing image-guided biopsies and preoperative imaging, including contrast-enhanced MR imaging, dynamic susceptibility contrast MR imaging, and diffusion tensor imaging. We calculated relative cerebral blood volume from DSC-MR imaging and mean diffusivity and fractional anisotropy from DTI. Following image coregistration, we assessed tumor cell density for each biopsy and identified corresponding localized MR imaging measurements. We then explored a range of univariate and multivariate predictive models of tumor cell density based on MR imaging measurements in a generalized one-model-fits-all approach. We then implemented both univariate and multivariate individualized transfer learning predictive models, which harness the available population-level data but allow individual variability in their predictions. Finally, we compared Pearson correlation coefficients and mean absolute error between the individualized transfer learning and generalized one-model-fits-all models. RESULTS:Tumor cell density significantly correlated with relative CBV (r = 0.33, P < .001), and T1-weighted postcontrast (r = 0.36, P < .001) on univariate analysis after correcting for multiple comparisons. With single-variable modeling (using relative CBV), transfer learning increased predictive performance (r = 0.53, mean absolute error = 15.19%) compared with one-model-fits-all (r = 0.27, mean absolute error = 17.79%). With multivariate modeling, transfer learning further improved performance (r = 0.88, mean absolute error = 5.66%) compared with one-model-fits-all (r = 0.39, mean absolute error = 16.55%). CONCLUSIONS:Transfer learning significantly improves predictive modeling performance for quantifying tumor cell density in glioblastoma.

Dataset Information

Learning an EMG Controlled Game: Task-Specific Adaptations and Transfer.

Publications

Learning an EMG Controlled Game: Task-Specific Adaptations and Transfer.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure