To describe users’ and therapists’ opinions on multi-function myoelectric upper limb prostheses with conventional control and pattern recognition control. Qualitative interview study. Two rehabilitation institutions in the Netherlands and one in Austria. The study cohort consisted of 15 prosthesis users (13 males, mean age: 43.7 years, average experience with multi-function prosthesis: 3.15 years) and seven therapists (one male, mean age: 44.1 years, average experience with multi-function prostheses: 6.6 years). Four of these users and one therapist had experience with pattern recognition control. This study consisted of semi-structured interviews. The participants were interviewed at their rehabilitation centres or at home by telephone. The thematic framework approach was used for analysis. The themes emerging from prosthesis users and therapists were largely congruent and resulted in one thematic framework with three main themes: control, prosthesis, and activities. The participants mostly addressed (dis-) satisfaction with the control type and the prosthesis itself and described the way they used their prostheses in daily tasks. Prosthesis users and therapists described multi-function upper limb prostheses as more functional devices than conventional one-degree-of-freedom prostheses. Nonetheless, the prostheses were seldom used to actively grasp and manipulate objects. Moreover, the participants clearly expressed their dissatisfaction with the mechanical robustness of the devices and with the process of switching prosthesis function under conventional control. Pattern recognition was appreciated as an intuitive control that facilitated fast switching between prosthesis functions, but was reported to be too unreliable for daily use and require extensive training.

In myoelectric machine learning (ML) based control, it has been demonstrated that control performance usually increases with training, but it remains largely unknown which underlying factors govern these improvements. It has been suggested that the increase in performance originates from changes in characteristics of the Electromyography (EMG) patterns, such as separability or repeatability. However, the relation between these EMG metrics and control performance has hardly been studied. We assessed the relation between three common EMG feature space metrics (separability, variability and repeatability) in 20 able bodied participants who learned ML myoelectric control in a virtual task over 15 training blocks on 5 days. We assessed the change in offline and real-time performance, as well as the change of each EMG metric over the training. Subsequently, we assessed the relation between individual EMG metrics and offline and real-time performance via correlation analysis. Last, we tried to predict real-time performance from all EMG metrics via L2-regularized linear regression. Results showed that real-time performance improved with training, but there was no change in offline performance or in any of the EMG metrics. Furthermore, we only found a very low correlation between separability and real-time performance and no correlation between any other EMG metric and real-time performance. Finally, real-time performance could not be successfully predicted from all EMG metrics employing L2-regularized linear regression. We concluded that the three EMG metrics and real-time performance appear to be unrelated.

Objective: When evaluating methods for machine-learning controlled prosthetic hands, able-bodied participants are often recruited, for practical reasons, instead of participants with upper limb absence (ULA). However, able-bodied participants have been shown to often perform myoelectric control tasks better than participants with ULA. It has been suggested that this performance difference can be reduced by restricting the wrist and hand movements of able-bodied participants. However, the effect of such restrictions on the consistency and separability of the electromyogram’s (EMG) features remains unknown. The present work investigates whether the EMG separability and consistency between unaffected and affected arms differ and whether they change after restricting the unaffected limb in persons with ULA. Methods: Both arms of participants with unilateral ULA were compared in two conditions: with the unaffected hand and wrist restricted or not. Furthermore, it was tested if the effect of arm and restriction is influenced by arm posture (arm down, arm in front, or arm up). Results: Fourteen participants (two women, age=53.4±4.05) with acquired transradial limb loss were recruited. We found that the unaffected limb generated more separated EMG than the affected limb. Furthermore, restricting the unaffected hand and wrist lowered the separability of the EMG when the arm was held down. Conclusion: Limb restriction is a viable method to make the EMG of able-bodied participants more similar to that of participants with ULA. Significance: Future research that evaluates methods for machine learning controlled hands in able-bodied participants should restrict the participants’ hand and wrist.

Objective: We show that state-of-the-art deep neural networks achieve superior results in regression-based multi-class proportional myoelectric hand prosthesis control than two common baseline approaches, and we analyze the neural network mapping to explain why this is the case. Methods: Feedforward neural networks and baseline systems are trained on an offline corpus of 11 able-bodied subjects and 4 prosthesis wearers, using the $R^2$ score as metric. Analysis is performed using diverse qualitative and quantitative approaches, followed by a rigorous evaluation. Results: Our best neural networks have at least three hidden layers with at least 128 neurons per layer; smaller architectures, as used by many prior studies, perform substantially worse. The key to good performance is to both optimally regress the target movement, and to suppress spurious movements. Due to the properties of the underlying data, this is impossible to achieve with linear methods, but can be attained with high exactness using sufficiently large neural networks. Conclusion: Neural networks perform significantly better than common linear approaches in the given task, in particular when sufficiently large architectures are used. This can be explained by salient properties of the underlying data, and by theoretical and experimental analysis of the neural network mapping. Significance: To the best of our knowledge, this work is the first one in the field which not only reports that large and deep neural networks are superior to existing architectures, but also explains this result.

Background: A thorough assessment of upper limb prostheses could help facilitate their transfer from scientific developments into the daily lives of users. Ideally, routine clinical testing would include assessments of upper limb function using motion-capturing technology. This is particularly relevant for the state-of-the-art upper limb prostheses. Methods: We designed a test based on an activity of daily life (“tray-task”) which could be completed outside the laboratory, and developed a set of outcome measures aimed at characterizing the movement quality. For this purpose, kinematics of the thorax and the humerus were captured with an inertial–magnetic measurement unit (IMMU) motion-capture system. Six prosthesis users and ten able-bodied participants were recruited to test the feasibility of the proposed assessment procedure and to evaluate the outcome variables. Results: All participants completed the test either at home or in our lab. The prosthesis users needed more time to complete the task and showed a larger range of motion in the thoracic flexion and a smaller range of motion in the humeral elevation, compared to the able-bodied participants. Furthermore, the prosthesis users’ movements were less smooth and characterized by less stable coordination patterns between the humerus and thorax. Conclusion: A new test method and associated outcome variables have been proposed.