Looking beyond proportional control: The relevance of mode switching in learning to operate multi-articulating myoelectric upper-limb prostheses

Evaluation of Hand Action Classification Performance Using Machine Learning Based on Signals from Two sEMG Electrodes

Classification-based myoelectric control has attracted significant interest in recent years, leading to prosthetic hands with advanced functionality, such as multi-grip hands. Thus far, high classification accuracies have been achieved by increasing the number of surface electromyography (sEMG) electrodes or adding other sensing mechanisms. While many prescribed myoelectric hands still adopt two-electrode sEMG systems, detailed studies on signal processing and classification performance are still lacking. In this study, nine able-bodied participants were recruited to perform six typical hand actions, from which sEMG signals from two electrodes were acquired using a Delsys Trigno Research+ acquisition system. Signal processing and machine learning algorithms, specifically, linear discriminant analysis (LDA), k-nearest neighbors (KNN), and support vector machines (SVM), were used to study classification accuracies. Overall classification accuracy of 93 ± 2%, action-specific accuracy of 97 ± 2%, and F1-score of 87 ± 7% were achieved, which are comparable with those reported from multi-electrode systems. The highest accuracies were achieved using SVM algorithm compared to LDA and KNN algorithms. A logarithmic relationship between classification accuracy and number of features was revealed, which plateaued at five features. These comprehensive findings may potentially contribute to signal processing and machine learning strategies for commonly prescribed myoelectric hand systems with two sEMG electrodes to further improve functionality.

Assessing the effectiveness of serious game training designed to assist in upper limb prothesis rehabilitation

Introduction

Controlling a myoelectric upper limb prosthesis is difficult, therefore training is required. Since training with serious games showed promising results, the current paper focuses on game design and its effectivity for transfer between in-game skill to actual prosthesis use for proportional control of hand opening and control of switching between grips. We also examined training duration and individual differences.

Method

Thirty-six participants were randomly assigned to one of three groups: a task-specific serious game training group, a non-task-specific serious game training group and a control group. Each group performed a pre-test, mid-test and a post-test with five training sessions between each test moment. Test sessions assessed proportional control using the Cylinder test, a test designed to measure scaling of hand aperture during grabbing actions, and the combined use of proportional and switch control using the Clothespin Relocation Test, part of the Southampton Hand Assessment Procedure and Tray Test. Switch control was assessed during training by measuring amplitude difference and phasing of co-contraction triggers.

Results

Differences between groups over test sessions were observed for proportional control tasks, however there was lack of structure in these findings. Maximum aperture changed with test moment and some participants adjusted maximum aperture for smaller objects. For proportional and switch control tasks no differences between groups were observed. The effect of test moment suggests a testing effect. For learning switch control, an overall improvement across groups was found in phasing of the co-contraction peaks. Importantly, individual differences were found in all analyses.

Conclusion

As improvements over test sessions were found, but no relevant differences between groups were revealed, we conclude that transfer effects from game training to actual prosthesis use did not take place. Task specificity nor training duration had effects on outcomes. Our results imply testing effects instead of transfer effects, in which individual differences played a significant role. How transfer from serious game training in upper limb prosthesis use can be enhanced, needs further attention.

Training prosthesis users to switch between modes of a multi-articulating prosthetic hand

PURPOSE

Producing triggers to switch between modes of myoelectric prosthetic hands has proven to be difficult. We evaluated whether digital training methods were feasible in individuals with an upper limb defect (ULD), whether myosignals in these individuals differ from those of non-impaired individuals and whether acquired skills transfer to prosthesis use.

MATERIALS AND METHODS

Two groups participated in a 9-day pre-test-post-test design study with seven 45-minute training sessions. One group trained using a serious game, the other with their myosignals digitally displayed. Both groups also trained using a prosthesis. The pre- and post-tests consisted of an adapted Clothespin Relocation Test and the spherical subset of the Southampton Hand Assessment Procedure. After the post-test, the System Usability Scale (SUS) was administered. Clinically relevant performance measures and myosignal features were analysed.

RESULTS

Four individuals with a ULD participated. SUS-scores deemed both training methods feasible. Three participants produced only a few correct triggers. Myosignals features indicated larger variability for individuals with a ULD compared to non-impaired individuals (previously published data [1]). Three participants indicated transfer of skill.

CONCLUSIONS

Even though both training methods were deemed feasible and most participants showed transfer, seven training sessions were insufficient to learn reliable switching behaviour.Trial registration: The study was approved by the medical ethics committee of the University Medical Center Groningen (METc 2018.268).Implications for rehabilitationSwitching between pre-programmed modes of a myoelectric prosthetic hand can be learned, however it does require training.Serious games can be considered useful training tools for trigger production in early phases of myoelectric prosthesis control training.In order to evoke transfer of skill from training to daily life both task-specificity and focus of attention during training should be taken into account.

Economic evaluation of upper limb prostheses in the Netherlands including the cost-effectiveness of multi-grip versus standard myoelectric hand prostheses

PURPOSE

To investigate the costs, quality of life, and user experiences associated with upper limb prosthesis use, and to evaluate the cost-effectiveness of multi-grip compared to standard myoelectric hand prostheses (MHPs/SHPs).

MATERIALS AND METHODS

The EQ-5D-5L to assess the quality of life, the patient-reported outcome measure to assess the preferred usage features of upper limb prosthesis (PUF-ULP), and a cost questionnaire (societal perspective) were completed by 242 prosthesis users (57% men; mean age = 58 years). Incremental cost-utility and cost-effectiveness ratios (ICUR/ICER) with respectively the EQ-5D-5L and PUF-ULP were calculated to compare MHPs with SHPs. Statistical uncertainty was estimated using bootstrapping. Netherlands Trial Registry number: NL7682.

RESULTS

The mean yearly total costs related to prosthesis use of MHPs (€54 112) and SHPs (€23 501) were higher compared to prostheses with tools/accessories (€11 977), body-powered (€11 298), and cosmetic/passive prostheses (€10 132). EQ-5D-5L and PUF-ULP scores did not differ between prosthesis types. ICUR was €-728 833 per quality-adjusted life year; ICER was €-187 798 per PUF-ULP point gained.

CONCLUSIONS

Myoelectric prostheses, especially MHPs, were most expensive compared to other prostheses, while no differences in quality of life and user experiences were apparent. MHPs were not cost-effective compared to SHPs. When prescribing MHPs, careful consideration of advantages over SHPs is recommended.

Long-term upper-extremity prosthetic control using regenerative peripheral nerve interfaces and implanted EMG electrodes

Objective.Extracting signals directly from the motor system poses challenges in obtaining both high amplitude and sustainable signals for upper-limb neuroprosthetic control. To translate neural interfaces into the clinical space, these interfaces must provide consistent signals and prosthetic performance.Approach.Previously, we have demonstrated that the Regenerative Peripheral Nerve Interface (RPNI) is a biologically stable, bioamplifier of efferent motor action potentials. Here, we assessed the signal reliability from electrodes surgically implanted in RPNIs and residual innervated muscles in humans for long-term prosthetic control.Main results.RPNI signal quality, measured as signal-to-noise ratio, remained greater than 15 for up to 276 and 1054 d in participant 1 (P1), and participant 2 (P2), respectively. Electromyography from both RPNIs and residual muscles was used to decode finger and grasp movements. Though signal amplitude varied between sessions, P2 maintained real-time prosthetic performance above 94% accuracy for 604 d without recalibration. Additionally, P2 completed a real-world multi-sequence coffee task with 99% accuracy for 611 d without recalibration.Significance.This study demonstrates the potential of RPNIs and implanted EMG electrodes as a long-term interface for enhanced prosthetic control.

The multi-grip and standard myoelectric hand prosthesis compared: does the multi-grip hand live up to its promise?

BACKGROUND

Multi-grip myoelectric hand prostheses (MHPs), with five movable and jointed fingers, have been developed to increase functionality. However, literature comparing MHPs with standard myoelectric hand prostheses (SHPs) is limited and inconclusive. To establish whether MHPs increase functionality, we compared MHPs with SHPs on all categories of the International Classification of Functioning, Disability, and Health-model (ICF-model).

METHODS

MHP users (N = 14, 64.3% male, mean age = 48.6 years) performed physical measurements (i.e., Refined Clothespin Relocation Test (RCRT), Tray-test, Box and Blocks Test, Southampton Hand Assessment Procedure) with their MHP and an SHP to compare the joint angle coordination and functionality related to the ICF-categories 'Body Function' and 'Activities' (within-group comparisons). SHP users (N = 19, 68.4% male, mean age = 58.1 years) and MHP users completed questionnaires/scales (i.e., Orthotics and Prosthetics Users' Survey-The Upper Extremity Functional Status Survey /OPUS-UEFS, Trinity Amputation and Prosthesis Experience Scales for upper extremity/TAPES-Upper, Research and Development-36/RAND-36, EQ-5D-5L, visual analogue scale/VAS, the Dutch version of the Quebec User Evaluation of Satisfaction with assistive technology/D-Quest, patient-reported outcome measure to assess the preferred usage features of upper limb prostheses/PUF-ULP) to compare user experiences and quality of life in the ICF-categories 'Activities', 'Participation', and 'Environmental Factors' (between-group comparisons).

RESULTS

'Body Function' and 'Activities': nearly all users of MHPs had similar joint angle coordination patterns with an MHP as when they used an SHP. The RCRT in the upward direction was performed slower in the MHP condition compared to the SHP condition. No other differences in functionality were found. 'Participation': MHP users had a lower EQ-5D-5L utility score; experienced more pain or limitations due to pain (i.e., measured with the RAND-36). 'Environmental Factors': MHPs scored better than SHPs on the VAS-item holding/shaking hands. The SHP scored better than the MHP on five VAS-items (i.e., noise, grip force, vulnerability, putting clothes on, physical effort to control) and the PUF-ULP.

CONCLUSION

MHPs did not show relevant differences in outcomes compared to SHPs on any of the ICF-categories. This underlines the importance of carefully considering whether the MHP is the most suitable option for an individual taking into account the additional costs of MHPs.

Transfer of mode switching performance: from training to upper-limb prosthesis use

BACKGROUND

Current myoelectric prostheses are multi-articulated and offer multiple modes. Switching between modes is often done through pre-defined myosignals, so-called triggers, of which the training hardly is studied. We evaluated if switching skills trained without using a prosthesis transfer to actual prosthesis use and whether the available feedback during training influences this transfer. Furthermore we examined which clinically relevant performance measures and which myosignal features were adapted during training.

METHODS

Two experimental groups and one control group participated in a five day pre-test-post-test design study. Both experimental groups used their myosignals to perform a task. One group performed a serious game without seeing their myosignals, the second group was presented their myosignal on a screen. The control group played the serious game using the touchpad of the laptop. Each training session lasted 15 min. The pre- and post-test were identical for all groups and consisted of performing a task with an actual prosthesis, where switches had to be produced to change grip mode to relocate clothespins. Both clinically relevant performance measures and myosignal features were analysed.

RESULTS

10 participants trained using the serious game, 10 participants trained with the visual myosignal and 8 the control task. All participants were unimpaired. Both experimental groups showed significant transfer of skill from training to prosthesis use, the control group did not. The degree of transfer did not differ between the two training groups. Clinically relevant measure 'accuracy' and feature of the myosignals 'variation in phasing' changed during training.

CONCLUSIONS

Training switching skills appeared to be successful. The skills trained in the game transferred to performance in a functional task. Learning switching skills is independent of the type of feedback used during training. Outcome measures hardly changed during training and further research is needed to explain this. It should be noted that five training sessions did not result in a level of performance needed for actual prosthesis use. Trial registration The study was approved by the local ethics committee (ECB 2014.02.28_1) and was included in the Dutch trial registry (NTR5876).

User training for machine learning controlled upper limb prostheses: a serious game approach

BACKGROUND

Upper limb prosthetics with multiple degrees of freedom (DoFs) are still mostly operated through the clinical standard Direct Control scheme. Machine learning control, on the other hand, allows controlling multiple DoFs although it requires separable and consistent electromyogram (EMG) patterns. Whereas user training can improve EMG pattern quality, conventional training methods might limit user potential. Training with serious games might lead to higher quality EMG patterns and better functional outcomes. In this explorative study we compare outcomes of serious game training with conventional training, and machine learning control with the users' own one DoF prosthesis.

METHODS

Participants with upper limb absence participated in 7 training sessions where they learned to control a 3 DoF prosthesis with two grips which was fitted. Participants received either game training or conventional training. Conventional training was based on coaching, as described in the literature. Game-based training was conducted using two games that trained EMG pattern separability and functional use. Both groups also trained functional use with the prosthesis donned. The prosthesis system was controlled using a neural network regressor. Outcome measures were EMG metrics, number of DoFs used, the spherical subset of the Southampton Hand Assessment Procedure and the Clothespin Relocation Test.

RESULTS

Eight participants were recruited and four completed the study. Training did not lead to consistent improvements in EMG pattern quality or functional use, but some participants improved in some metrics. No differences were observed between the groups. Participants achieved consistently better results using their own prosthesis than the machine-learning controlled prosthesis used in this study.

CONCLUSION

Our explorative study showed in a small group of participants that serious game training seems to achieve similar results as conventional training. No consistent improvements were found in either group in terms of EMG metrics or functional use, which might be due to insufficient training. This study highlights the need for more research in user training for machine learning controlled prosthetics. In addition, this study contributes with more data comparing machine learning controlled prosthetics with Direct Controlled prosthetics.