Validity and Impact of Methods for Collecting Training Data for Myoelectric Prosthetic Control Algorithms.

Intuitive regression control of prostheses relies on training algorithms to correlate biological recordings to motor intent. The quality of the training dataset is critical to run-time regression performance, but accurately labeling intended hand kinematics after hand amputation is challenging. In this study, we quantified the accuracy and precision of labeling hand kinematics using two common training paradigms: 1) mimic training, where participants mimic predetermined motions of a prosthesis, and 2) mirror training, where participants mirror their contralateral intact hand during synchronized bilateral movements. We first explored this question in healthy non-amputee individuals where the ground-truth kinematics could be readily determined using motion capture. Kinematic data showed that mimic training fails to account for biomechanical coupling and temporal changes in hand posture. Additionally, mirror training exhibited significantly higher accuracy and precision in labeling hand kinematics. These findings suggest that the mirror training approach generates a more faithful, albeit more complex, dataset. Accordingly, mirror training resulted in significantly better offline regression performance when using a large amount of training data and a non-linear neural network. Next, we explored these different training paradigms online, with a cohort of unilateral transradial amputees actively controlling a prosthesis in real-time to complete a functional task. Overall, we found that mirror training resulted in significantly faster task completion speeds and similar subjective workload. These results demonstrate that mirror training can potentially provide more dexterous control through the utilization of task-specific, user-selected training data. Consequently, these findings serve as a valuable guide for the next generation of myoelectric and neuroprostheses leveraging machine learning to provide more dexterous and intuitive control.

Delayed Muscle Activity in Stroke Survivors with Upper-Limb Hemiparesis.

Stroke is the leading cause of disability worldwide, and nearly 80% of stroke survivors suffer from upper-limb hemiparesis. Myoelectric exoskeletons can restore dexterity and independence to stroke survivors with upper-limb hemiparesis. However, the ability of patients to dexterously control myoelectric exoskeletons is limited by an incomplete understanding of the electromyographic (EMG) hallmarks of hemiparesis, such as muscle weakness and spasticity. Here we show that stroke survivors with upper-limb hemiparesis suffer from delayed voluntary muscle contraction and delayed muscle relaxation. We quantified the time constants of EMG activity associated with initiating and terminating voluntary hand grasps and extensions for both the paretic and non-paretic hands of stroke survivors. We found that the initiation and termination time constants were greater on the paretic side for both hand grasps and hand extensions. Notably, the initiation time constant during hand extension was approximately three times longer for the paretic hand than for the contralateral non-paretic hand (0.618 vs 0.189 s). We also show a positive correlation between the initiation and termination time constants and clinical scores on the Modified Ashworth Scale. The difficulty stroke survivors have in efficiently modulating their EMG presents a challenge for appropriate control of assistive myoelectric devices, such as exoskeletons. This work constitutes an important step towards understanding EMG differences after stroke and how to accommodate these EMG differences in assistive myoelectric devices. Real-time quantitative biofeedback of EMG time constants may also have broad implications for guiding rehabilitation and monitoring patient recovery.Clinical Relevance- After a stroke, muscle activity changes, and these changes make it difficult to use muscle activity to drive assistive and rehabilitative technologies. We identified slower muscle contraction and muscle relaxation as a key difference in muscle activity after a stroke. This quantifiable difference in muscle activity can be used to develop better assistive technologies, guide rehabilitation, and monitor patient recovery.

A Recurrent Neural Network Provides Stable Across-Day Prosthetic Control for a Human Amputee with Implanted Intramuscular Electromyographic Recording Leads.

Upper-limb prosthetic control is often challenging and non-intuitive, leading to up to 50% of prostheses users abandoning their prostheses. Convolutional neural networks (CNN) and recurrent long short-term memory (LSTM) networks have shown promise in extracting high-degree-of-freedom motor intent from myoelectric signals, thereby providing more intuitive and dexterous prosthetic control. An important next consideration for these algorithms is if performance remains stable over multiple days. Here we introduce a new LSTM network and compare its performance to previously established state-of-the-art algorithms-a CNN and a modified Kalman filter (MKF)-in offline analyses using 76 days of intramuscular recordings from one amputee participant collected over 425 calendar days. Specifically, we assessed the robustness of each algorithm over time by training on data from the first (one, five, ten, 30, or 60) days and then testing on myoelectric signals on the last 16 days. Results indicate that training on additional datasets from prior days generally decreases the Root Mean Squared Error (RMSE) of intended and unintended movements for all algorithms. Across all algorithms trained with 60 days of data, the lowest RMSE for unintended movements was achieved with the LSTM. The LSTM also showed less across-day variance in RMSE of unintended movements relative to the other algorithms. Altogether this work suggests that the LSTM algorithm introduced here can provide more intuitive and dexterous control for prosthetic users, and that training on multiple days of data improves overall performance on subsequent days, at least for offline analyses.