Implications of EMG channel count: enhancing pattern recognition online prosthetic testing.

Introduction: Myoelectric pattern recognition systems have shown promising control of upper limb powered prostheses and are now commercially available. These pattern recognition systems typically record from up to 8 muscle sites, whereas other control systems use two-site control. While previous offline studies have shown 8 or fewer sites to be optimal, real-time control was not evaluated. Methods: Six individuals with no limb absence and four individuals with a transradial amputation controlled a virtual upper limb prosthesis using pattern recognition control with 8 and 16 channels of EMG. Additionally, two of the individuals with a transradial amputation performed the Assessment for Capacity of Myoelectric Control (ACMC) with a multi-articulating hand and wrist prosthesis with the same channel count conditions. Results: Users had significant improvements in control when using 16 compared to 8 EMG channels including decreased classification error (p = 0.006), decreased completion time (p = 0.019), and increased path efficiency (p = 0.013) when controlling a virtual prosthesis. ACMC scores increased by more than three times the minimal detectable change from the 8 to the 16-channel condition. Discussion: The results of this study indicate that increasing EMG channel count beyond the clinical standard of 8 channels can benefit myoelectric pattern recognition users.

Machine Learning-Based Gait Mode Prediction for Hybrid Knee Prosthesis Control.

Recently, hybrid prosthetic knees, which can combine the advantages of passive and active prosthetic knees, have been proposed for individuals with a transfemoral amputation. Users could potentially take advantage of the passive knee mechanics during walking and the active power generation during stair ascent. One challenge in controlling the hybrid knees is accurate gait mode prediction for seamless transitions between passive and active modes. However, data imbalance between passive and active modes may impact the performance of a classifier. In this study, we used a dataset collected from nine individuals with a unilateral transfemoral amputation as they ambulated over level ground, inclines, and stairs. We evaluated several machine learning-based classifiers on the prediction of passive (level-ground walking, incline walking, descending stairs, and donning and doffing the prosthesis) and active mode (ascending stairs). In addition, we developed a generative adversarial network (GAN) to create synthetic data for improving classification performance. The results indicated that linear discriminant analysis and random forest might be the best classifiers regarding sensitivity to the active mode and overall accuracy, respectively. Further, we demonstrated that using the GAN-based synthetic data for training improves the sensitivity of classifiers.

Powered knee and ankle prosthesis use with a K2 level ambulator: a case report.

Powered prosthetic knees and ankles have the capability of restoring power to the missing joints and potential to provide increased functional mobility to users. Nearly all development with these advanced prostheses is with individuals who are high functioning community level ambulators even though limited community ambulators may also receive great benefit from these devices. We trained a 70 year old male participant with a unilateral transfemoral amputation to use a powered knee and powered ankle prosthesis. He participated in eight hours of therapist led in-lab training (two hours per week for four weeks). Sessions included static and dynamic balance activities for improved stability and comfort with the powered prosthesis and ambulation training on level ground, inclines, and stairs. Assessments were taken with both the powered prosthesis and his prescribed, passive prosthesis post-training. Outcome measures showed similarities in velocity between devices for level-ground walking and ascending a ramp. During ramp descent, the participant had a slightly faster velocity and more symmetrical stance and step times with the powered prosthesis compared to his prescribed prosthesis. For stairs, he was able to climb with reciprocal stepping for both ascent and descent, a stepping strategy he is unable to do with his prescribed prosthesis. More research with limited community ambulators is necessary to understand if further functional improvements are possible with either additional training, longer accommodation periods, and/or changes in powered prosthesis control strategies.

Myoelectric prosthesis hand grasp control following targeted muscle reinnervation in individuals with transradial amputation.

BACKGROUND: Despite the growing availability of multifunctional prosthetic hands, users' control and overall functional abilities with these hands remain limited. The combination of pattern recognition control and targeted muscle reinnervation (TMR) surgery, an innovative technique where amputated nerves are transferred to reinnervate new muscle targets in the residual limb, has been used to improve prosthesis control of individuals with more proximal upper limb amputations (i.e., shoulder disarticulation and transhumeral amputation). OBJECTIVE: The goal of this study was to determine if prosthesis hand grasp control improves following transradial TMR surgery. METHODS: Eight participants were trained to use a multi-articulating hand prosthesis under myoelectric pattern recognition control. All participated in home usage trials pre- and post-TMR surgery. Upper limb outcome measures were collected following each home trial. RESULTS: Three outcome measures (Southampton Hand Assessment Procedure, Jebsen-Taylor Hand Function Test, and Box and Blocks Test) improved 9-12 months post-TMR surgery compared with pre-surgery measures. The Assessment of Capacity for Myoelectric Control and Activities Measure for Upper Limb Amputees outcome measures had no difference pre- and post-surgery. An offline electromyography analysis showed a decrease in grip classification error post-TMR surgery compared to pre-TMR surgery. Additionally, a majority of subjects noted qualitative improvements in their residual limb and phantom limb sensations post-TMR. CONCLUSIONS: The potential for TMR surgery to result in more repeatable muscle contractions, possibly due to the reduction in pain levels and/or changes to phantom limb sensations, may increase functional use of many of the clinically available dexterous prosthetic hands.

User Performance With a Transradial Multi-Articulating Hand Prosthesis During Pattern Recognition and Direct Control Home Use.

With the increasing availability of more advanced prostheses individuals with a transradial amputation can now be fit with single to multi-degree of freedom hands. Reliable and accurate control of these multi-grip hands still remains challenging. This is the first multi-user study to investigate at-home control and use of a multi-grip hand prosthesis under pattern recognition and direct control. Individuals with a transradial amputation were fitted with and trained to use an OSSUR i-Limb Ultra Revolution with Coapt COMPLETE CONTROL system. They participated in two 8-week home trials using the hand under myoelectric direct and pattern recognition control in a randomized order. While at home, participants demonstrated broader usage of grips in pattern recognition compared to direct control. After the home trial, they showed significant improvements in the Assessment of Capacity for Myoelectric Control (ACMC) outcome measure while using pattern recognition control compared to direct control; other outcome measures showed no differences between control styles. Additionally, this study provided a unique opportunity to evaluate EMG signals during home use. Offline analysis of calibration data showed that users were 81.5% [7.1] accurate across a range of three to five grips. Although EMG signal noise was identified during some calibrations, overall EMG quality was sufficient to provide users with control performance at or better than direct control.

Corrigendum: Powered knee and ankle prosthesis use with a K2 level ambulator: a case report.

[This corrects the article DOI: 10.3389/fresc.2023.1203545.].

The impact of added mass placement on metabolic and temporal-spatial characteristics of transfemoral prosthetic gait.

BACKGROUND: Despite prosthetic technology advancements, individuals with transfemoral amputation have compromised temporal-spatial gait parameters and high metabolic requirements for ambulation. It is unclear how adding mass at different locations on a transfemoral prosthesis might affect these outcomes. Research question Does walking with mass added at different locations on a transfemoral prosthesis affect temporal-spatial gait parameters and metabolic requirements compared to walking with no additional mass? METHODS: Fourteen participants with unilateral transfemoral amputations took part. A 1.8 kg mass was added to their prostheses in three locations: Knee, just proximal to the prosthetic knee; Shank, mid-shank on the prosthesis; or Ankle, just proximal to the prosthetic foot. Temporal-spatial gait parameters were collected as participants walked over a GAITRite® walkway and metabolic data were collected during treadmill walking for each of these conditions and with no mass added, the None condition. Separate linear mixed effects models were created and post-hoc tests to compare with the control condition of None were performed with a significance level of 0.05. RESULTS: Overground self-selected walking speed for Ankle was significantly slower than for None (p < 0.05) (None: 1.16 ± 0.24; Knee: 1.15 ± 0.19; Shank: 1.14 ± 0.24; Ankle 0.99 ± 0.20 m/s). Compared to None, Ankle showed significantly increased oxygen consumption during treadmill walking (p < 0.05) (None: 13.82 ± 2.98; Knee: 13.83 ± 2.82; Shank: 14.30 ± 2.89; Ankle 14.56 ± 2.99 ml O2/kg/min). Other metabolic outcomes (power, cost of transport, oxygen cost) showed similar trends. Knee and Shank did not have significant negative effects on any metabolic or temporal-spatial parameters, as compared to None (p > 0.05). Significance Results suggest that additional mass located mid-shank or further proximal on a transfemoral prosthesis may not have negative temporal-spatial or metabolic consequences. Clinicians, researchers, and designers may be able to utilize heavier components, as long as the center of mass is not further distal than mid-shank, without adversely affecting gait parameters or metabolic requirements.

Corrigendum: Functional mobility training with a powered knee and ankle prosthesis.

[This corrects the article DOI: 10.3389/fresc.2022.790538.].

Ambulation Control System Design for a Hybrid Knee Prosthesis.

Prosthetic knees available to individuals with transfemoral amputation seek to restore functional ability to the user. Passive prosthetic knees are lightweight but can restore only limited, dissipative ambulation activities whereas active knees can provide energy to restore additional ambulation activities such as stair climbing and standing up from a chair. Semi-active prosthetic devices aim to only power a subset of activities and use passive components and control when that power is not necessary. Here, we outline an ambulation control system for a lightweight Hybrid Knee prosthesis that is powered for climbing stairs and passive for other ambulation activities (level-ground walking, walking on an incline, and stair descent). We include preliminary offline and online intent recognition system results for one able-bodied user and one individual with a transfemoral amputation demonstrating low error rates in predicting between active and passive control.

Functional Mobility Training with a Powered Knee and Ankle Prosthesis.

Limb loss at the transfemoral or knee disarticulation level results in a significant decrease of mobility. Powered lower limb prostheses have the potential to provide increased functional mobility and return individuals to activities of daily living that are limited due to their amputation. Providing power at the knee and/or ankle, new and innovative training is required for the amputee and the clinician to understand the capabilities of these advanced devices. This protocol for functional mobility training with a powered knee and ankle prosthesis was developed while training 30 participants with a unilateral transfemoral or knee disarticulation amputation at a nationally ranked physical medicine and rehabilitation research hospital. Participants received instruction for level ground walking, stair climbing, incline walking and sit to stand transitions. A therapist provided specific training for each mode including verbal, visual and tactile cueing along with patient education on the functionality of the device. The primary outcome measure was the ability of each participant to demonstrate independence with walking and sit to stand transitions along with modified independence for stair climbing and incline walking due to use of a handrail. Every individual was successful in comfortable ambulation of level ground walking and 27 out of 30 were successful in all other functional modes after participating in 1-3 sessions of 1-2 hours in length (3 terminated their participation prior to attempting all activities). As these prosthetic devices continue to advance, therapy techniques must advance as well and this paper serves as an education on new training techniques that can provide amputees with the best possible tools to take advantage of these powered devices in order to achieve their desired clinical outcomes.

Seamless and intuitive control of a powered prosthetic leg using deep neural network for transfemoral amputees.

Powered prosthetic legs are becoming a promising option for amputee patients. However, developing safe, robust, and intuitive control strategies for powered legs remains one of the greatest challenges. Although a variety of control strategies have been proposed, creating and fine-tuning the system parameters is time-intensive and complicated when more activities need to be restored. In this study, we developed a deep neural network (DNN) model that facilitates seamless and intuitive gait generation and transitions across five ambulation modes: level-ground walking, ascending/descending ramps, and ascending/descending stairs. The combination of latent and time sequence features generated the desired impedance parameters within the ambulation modes and allowed seamless transitions between ambulation modes. The model was applied to the open-source bionic leg and tested on unilateral transfemoral users. It achieved the overall coefficient of determination of 0.72 with the state machine-based impedance parameters in the offline testing session. In addition, users were able to perform in-laboratory ambulation modes with an overall success rate of 96% during the online testing session. The results indicate that the DNN model is a promising candidate for subject-independent and tuning-free prosthetic leg control for transfemoral amputees.

Patient-Preferred Prosthetic Ankle-Foot Alignment for Ramps and Level-Ground Walking.

Patient preference of lower limb prosthesis behavior informally guides clinical decision making, and may become increasingly important for tuning new robotic prostheses. However, the processes for quantifying preference are still being developed, and the strengths and weaknesses of preference are not adequately understood. The present study sought to characterize the reliability (consistency) of patient preference of alignment during level-ground walking, and determine the patient-preferred ankle angle for ascent and descent of a 10° ramp, with implications for the design and control of robotic prostheses. Seven subjects with transtibial amputation walked over level ground, and ascended and descended a 10° ramp on a semi-active prosthetic ankle capable of unweighted repositioning in dorsiflexion and plantarflexion. Preferred ankle angle was measured with an adaptive forced-choice psychophysics paradigm, in which subjects walked on a randomized static ankle angle and reported whether they would prefer the ankle to be dorsiflexed or plantarflexed. Subjects had reliable preferences for alignment during level-ground walking, with deviations of 1.5° from preference resulting in an 84% response rate preferring changes toward the preference. Relative to level walking, subjects preferred 7.8° (SD: 4.8°) of dorsiflexion during ramp ascent, and 5.3° (SD: 3.8°) plantarflexion during ramp descent. As the ankle angle better matched the ramp angle, socket pressures and tibial progression (shank pitch) both more closely mirrored those during level walking. These findings provide baseline behaviors for prosthetic ankles capable of adapting to slopes based on patient preference, and provide strong evidence that people with transtibial amputation can finely perceive ankle alignment.

Design and clinical implementation of an open-source bionic leg.

In individuals with lower-limb amputations, robotic prostheses can increase walking speed, and reduce energy use, the incidence of falls and the development of secondary complications. However, safe and reliable prosthetic-limb control strategies for robust ambulation in real-world settings remain out of reach, partly because control strategies have been tested with different robotic hardware in constrained laboratory settings. Here, we report the design and clinical implementation of an integrated robotic knee-ankle prosthesis that facilitates the real-world testing of its biomechanics and control strategies. The bionic leg is open source, it includes software for low-level control and for communication with control systems, and its hardware design is customizable, enabling reduction in its mass and cost, improvement in its ease of use and independent operation of the knee and ankle joints. We characterized the electromechanical and thermal performance of the bionic leg in benchtop testing, as well as its kinematics and kinetics in three individuals during walking on level ground, ramps and stairs. The open-source integrated-hardware solution and benchmark data that we provide should help with research and clinical testing of knee-ankle prostheses in real-world environments.

Exploring augmented grasping capabilities in a multi-synergistic soft bionic hand.

BACKGROUND: State-of-the-art bionic hands incorporate hi-tech devices which try to overcome limitations of conventional single grip systems. Unfortunately, their complexity often limits mechanical robustness and intuitive prosthesis control. Recently, the translation of neuroscientific theories (i.e. postural synergies) in software and hardware architecture of artificial devices is opening new approaches for the design and control of upper-limb prostheses. METHODS: Following these emerging principles, previous research on the SoftHand Pro, which embeds one physical synergy, showed promising results in terms of intuitiveness, robustness, and grasping performance. To explore these principles also in hands with augmented capabilities, this paper describes the SoftHand 2 Pro, a second generation of the device with 19 degrees-of-freedom and a second synergistic layer. After a description of the proposed device, the work explores a continuous switching control method based on a myoelectric pattern recognition classifier. RESULTS: The combined system was validated using standardized assessments with able-bodied and, for the first time, amputee subjects. Results show an average improvement of more than 30% of fine grasp capabilities and about 10% of hand function compared with the first generation SoftHand Pro. CONCLUSIONS: Encouraging results suggest how this approach could be a viable way towards the design of more natural, reliable, and intuitive dexterous hands.

Pattern recognition and direct control home use of a multi-articulating hand prosthesis.

Although more multi-articulating hand prostheses have become commercially available, replacing a missing hand remains challenging from a control perspective. This study investigated myoelectric direct control and pattern recognition home use of a multi-articulating hand prosthesis for individuals with a transradial amputation. Four participants were fitted with an i-limb Ultra Revolution hand and a Coapt COMPLETE CONTROL system. An occupational therapist provided training for each control style and how to use the various grips. The number of grips available to each individual was determined by clinician and user feedback to optimize both the number of grips available and the reliability of grip selection. Home trial data corresponding to individual usage were recorded. No significant differences were found between direct and pattern recognition control home trials in regards to trial length (p=0.96), days powered on (p=0.21), or total time powered on (p=0.91). There was a higher average number of configured grips for direct control at 4.8 [0.5] compared to 3.8 [0.5] for pattern recognition control, but this difference did not reach significance (p=0.092). Across all hand close movements, users spent a majority of time $(\gt80$%) in one grip when using direct control. For pattern recognition usage was spread across more grips $(\gt45$% time in one grip, 25% time in a 2nd grip, and 20% time in a 3rd grip). Pattern recognition control may provide users with a more intuitive way to select and use the various grips available to them.

Deep generative models with data augmentation to learn robust representations of movement intention for powered leg prostheses.

Intent recognition is a data-driven alternative to expert-crafted rules for triggering transitions between pre-programmed activity modes of a powered leg prosthesis. Movement-related signals from prosthesis sensors detected prior to movement completion are used to predict the upcoming activity. Usually, training data comprised of labeled examples of each activity are necessary; however, the process of collecting a sufficiently large and rich training dataset from an amputee population is tedious. In addition, covariate shift can have detrimental effects on a controller's prediction accuracy if the classifier's learned representation of movement intention is not robust enough. Our objective was to develop and evaluate techniques to learn robust representations of movement intention using data augmentation and deep neural networks. In an offline analysis of data collected from four amputee subjects across three days each, we demonstrate that our approach produced realistic synthetic sensor data that helped reduce error rates when training and testing on different days and different users. Our novel approach introduces an effective and generalizable strategy for augmenting wearable robotics sensor data, challenging a pre-existing notion that rehabilitation robotics can only derive limited benefit from state-of-the-art deep learning techniques typically requiring more vast amounts of data.

Decoding the grasping intention from electromyography during reaching motions.

BACKGROUND: Active upper-limb prostheses are used to restore important hand functionalities, such as grasping. In conventional approaches, a pattern recognition system is trained over a number of static grasping gestures. However, training a classifier in a static position results in lower classification accuracy when performing dynamic motions, such as reach-to-grasp. We propose an electromyography-based learning approach that decodes the grasping intention during the reaching motion, leading to a faster and more natural response of the prosthesis. METHODS AND RESULTS: Eight able-bodied subjects and four individuals with transradial amputation gave informed consent and participated in our study. All the subjects performed reach-to-grasp motions for five grasp types, while the elecromyographic (EMG) activity and the extension of the arm were recorded. We separated the reach-to-grasp motion into three phases, with respect to the extension of the arm. A multivariate analysis of variance (MANOVA) on the muscular activity revealed significant differences among the motion phases. Additionally, we examined the classification performance on these phases. We compared the performance of three different pattern recognition methods; Linear Discriminant Analysis (LDA), Support Vector Machines (SVM) with linear and non-linear kernels, and an Echo State Network (ESN) approach. Our off-line analysis shows that it is possible to have high classification performance above 80% before the end of the motion when with three-grasp types. An on-line evaluation with an upper-limb prosthesis shows that the inclusion of the reaching motion in the training of the classifier importantly improves classification accuracy and enables the detection of grasp intention early in the reaching motion. CONCLUSIONS: This method offers a more natural and intuitive control of prosthetic devices, as it will enable controlling grasp closure in synergy with the reaching motion. This work contributes to the decrease of delays between the user's intention and the device response and improves the coordination of the device with the motion of the arm.

Across-user adaptation for a powered lower limb prosthesis.

Pattern recognition algorithms have been used to control powered lower limb prostheses because they are capable of identifying the intent of the amputee user and therefore can provide a method for seamlessly transitioning between the different locomotion modes of the prosthesis. However, one major limitation of current algorithms is that they require subject-specific data from the individual user. These data are difficult and time-consuming to collect and consequently these algorithms do not generalize well across users. We have developed an adaptive pattern recognition algorithm that automatically learns new subject-specific data acquired from a novel user during ambulation. We tested this adaptive algorithm with one transfemoral amputee subject walking on a powered knee-ankle prosthesis. Before adaptation, the algorithm, which was initially trained with data from two other transfemoral amputee subjects, made critical errors that prevented continuous ambulation. With adaptation, error rates dropped from 4.21% before adaptation to 1.25% after adaptation, and allowed the novel amputee user to complete all mode transitions. This study demonstrates that adaptation can decrease error rates over time and can allow pattern recognition algorithms to generalize to novel users.

Delaying Ambulation Mode Transition Decisions Improves Accuracy of a Flexible Control System for Powered Knee-Ankle Prosthesis.

Powered lower limb prostheses can assist users in a variety of ambulation modes by providing knee and/or ankle joint power. This study's goal was to develop a flexible control system to allow users to perform a variety of tasks in a natural, accurate, and reliable way. Six transfemoral amputees used a powered knee-ankle prosthesis to ascend/descend a ramp, climb a 3- and 4-step staircase, perform walking and standing transitions to and from the staircase, and ambulate at various speeds. A mode-specific classification architecture was developed to allow seamless transitions at four discrete gait events. Prosthesis mode transitions (i.e., the prosthesis' mechanical response) were delayed by 90 ms. Overall, users were not affected by this small delay. Offline classification results demonstrate significantly reduced error rates with the delayed system compared to the non-delayed system (p < 0.001). The average error rate for all heel contact decisions was 1.65% [0.99%] for the non-delayed system and 0.43% [0.23%] for the delayed system. The average error rate for all toe off decisions was 0.47% [0.16%] for the non-delayed system and 0.13% [0.05%] for the delayed system. The results are encouraging and provide another step towards a clinically viable intent recognition system for a powered knee-ankle prosthesis.

Assessing the Relative Contributions of Active Ankle and Knee Assistance to the Walking Mechanics of Transfemoral Amputees Using a Powered Prosthesis.

Powered knee-ankle prostheses are capable of providing net-positive mechanical energy to amputees. Yet, there are limitless ways to deliver this energy throughout the gait cycle. It remains largely unknown how different combinations of active knee and ankle assistance affect the walking mechanics of transfemoral amputees. This study assessed the relative contributions of stance phase knee swing initiation, increasing ankle stiffness and powered plantarflexion as three unilateral transfemoral amputees walked overground at their self-selected walking speed. Five combinations of knee and ankle conditions were evaluated regarding the kinematics and kinetics of the amputated and intact legs using repeated measures analyses of variance. We found eliminating active knee swing initiation or powered plantarflexion was linked to increased compensations of the ipsilateral hip joint during the subsequent swing phase. The elimination of knee swing initiation or powered plantarflexion also led to reduced braking ground reaction forces of the amputated and intact legs, and influenced both sagittal and frontal plane loading of the intact knee joint. Gradually increasing prosthetic ankle stiffness influenced the shape of the prosthetic ankle plantarflexion moment, more closely mirroring the intact ankle moment. Increasing ankle stiffness also corresponded to increased prosthetic ankle power generation (despite a similar maximum stiffness value across conditions) and increased braking ground reaction forces of the amputated leg. These findings further our understanding of how to deliver assistance with powered knee-ankle prostheses and the compensations that occur when specific aspects of assistance are added/removed.