Search

International audience; Voluntary phantom movements are systematically associated with muscle contractions in the residual limb. These latter are specific to the type of movement and can be classified by pattern recognition algorithms. However, phantom mobility generates fatigue that could impact classification metrics. This study explored whether daily phantom movement training at home with no other feedback than inherent somatosensory information can impact the classification success rate. Kinematics and muscle activity were compared between before and after a two-month home training in six major upper limb amputees. Surface EMG patterns were classified to quantify a potential change in the features space with training. Our results showed that this type of training induces faster, smoother, and richer phantom mobility. However, classification metrics did not change with training. When including the new types of movements achievable after training, accuracy did not decrease, indicating that muscle activation patterns associated with these movements were sufficiently different not to interfere with the already existing movement classes. Thus, although phantom training with only somatosensory feedback increases the overall phantom movement capacity, it does not increase the classification success rate. Yet, it is possible that paired with other forms of feedback, phantom training could improve this success rate.

Musculoskeletal simulations are useful in biomechanics to investigate the causes of movement disorder, to estimate non-measurable physiological quantities or to study the optimality of human movement. We introduce Bioptim, an easy-to-use Python framework for biomechanical optimal control, handling musculoskeletal models. Relying on algorithmic differentiation and the multiple shooting formulation, Bioptim interfaces nonlinear solvers to quickly provide dynamically consistent optimal solutions. The software is both computationally efficient (C++ core) and easily customizable, thanks to its Python interface. It allows to quickly define a variety of biomechanical problems such as motion tracking/prediction, muscle-driven simulations, parameters optimization, multiphase problems, etc. It is also intended for real-time applications such as moving horizon estimation and model predictive control. Six contrasting examples are presented, comprising various models, dynamics, objective functions and constraints. They include data-driven simulations (i.e., a multiphase muscle driven gait cycle and an upper-limb real-time moving horizon estimation of muscle forces) and predictive simulations (i.e., a muscle-driven pointing task, a twisting somersault with a quaternion-based model, a position controller using external forces, and a multiphase torque-driven maximum-height jump motion).

International audience; Assistive devices for indivuals with upper-limb movement often lack controllability and intuitiveness, in particular for grasping function. In this work, we introduce a novel user interface for grasping movement control in which the user delegates the grasping task decisions to the device, only moving their (potentially prosthetic) hand toward the targeted object.

Human-robot interaction based on real-time kinematics or electromyography (EMG) feedback improves rehabilitation using assist-as-needed strategies. Muscle forces are expected to provide even more comprehensive information than EMG to control these assistive rehabilitation devices. Measuring in vivo muscle force is challenging, leading to the development of numerical methods to estimate them. Due to their high computational cost, forward dynamics-based optimization algorithms were not viable for real-time estimation until recently. To achieve muscle forces estimation in real time, a moving horizon estimator (MHE) algorithm was used to track experimental biosignals. Two participants were equipped with EMG sensors and skin markers that were streamed in real time and used as targets for the MHE. The upper-limb musculoskeletal (MSK) model was composed of 10 degrees-of-freedom actuated by 31 muscles. The MHE relies on a series of overlapping trajectory optimization subproblems of which the following parameters have been adjusted: the fixed duration and the frame to export. We based this adjustment on the estimation delay, the muscle saturation, the joint kinematic mean power frequency, and errors to experimental data. Our algorithm provided consistent estimates of muscle forces and kinematics with visual feedback at 30 Hz with a 110 ms delay. This method is promising to guide rehabilitation and enrich assistive device control laws with personalized force estimations.

International audience

International audience; Two multi-contact epineural electrodes were placed around radial and median nerves of two subjects with high tetraplegia C4, American Spinal Injury Association Impairment Scale (AIS) A, group 0 of the International Classification for Surgery of the Hand in Tetraplegia. The purpose was to study the safety and capability of these electrodes to generate synergistic motor activation and functional movements and to test control interfaces that allow subjects to trigger pre-programmed stimulation sequences. The device consists of a pair of neural cuff electrodes and percutaneous cables with two extracorporeal connection cables inserted during a surgical procedure and maintained for 28 days. Continuity tests of the electrodes, selectivity of movements induced, motor capacities for grasping and gripping, conformity of the control order, tolerance, and acceptability were assessed. Neither of the two participants showed general and local comorbidity. Acceptability was optimal. None of the stimulation configurations generated contradictory movements. The success rate in task execution by the electro-stimulated hand exceeded the target of 50% (54% and 51% for patients 1 and 2, respectively). The compliance rate of the control orders in both patients was >90% using motion inertial measurement unit (IMU)-based detection and 100% using electromyography (EMG)-based detection in patient 1. These results support the relevance of neural stimulation of the tetraplegic upper limb with a more selective approach, using multi-contact epineural electrodes with nine and six contact points for the median and radial nerve respectively.

Direct multiple shooting (DMS) and direct collocation (DC) are two common transcription methods for solving optimal control problems (OCP) in biomechanics and robotics. They have rarely been compared in terms of solution and speed. Through five examples of predictive simulations solved using five transcription methods and 100 initial guesses in the Bioptim software, we showed that not a single method outperformed systematically better. All methods converged to almost the same solution (cost, states, and controls) in all but one OCP, with several local minima being found in the latter. Nevertheless, DC based on fourth-order Legendre polynomials provided overall better results, especially in terms of dynamic consistency compared to DMS based on a fourth-order Runge-Kutta method. Furthermore, expressing the rigid-body constraints using inverse dynamics was usually faster than forward dynamics. DC with dynamics constraints based on inverse dynamics converged to better and less variable solutions. Consequently, we recommend starting with this transcription to solve OCPs but keep testing other methods., 19 pages, 4 figures

International audience; Complete tetraplegia can deprive a person of hand function. Assistive technologies may improve autonomy but needs for ergonomic interfaces for the user to pilot these devices still persist. Despite the paralysis of their arms, people with tetraplegia may retain residual shoulder movements. In this work we explored these movements as a mean to control assistive devices. Methods: We captured shoulder movement with a single inertial sensor and, by training a support vector machine based classifier, we decode such information into user intent. Results: The setup and training process take only a few minutes and so the classifiers can be user specific. We tested the algorithm with 10 able body and 2 spinal cord injury participants. The average classification accuracy was 80% and 84%, respectively. Conclusion: The proposed algorithm is easy to set up, its operation is fully automated, and achieved results are on par with state-of-the-art systems. Significance: Assistive devices for persons without hand function present limitations in their user interfaces. Our work present a novel method to overcome some of these limitations by classifying user movement and decoding it into user intent, all with simple setup and training and no need for manual tuning. We demonstrate its feasibility with experiments with end users, including persons with complete tetraplegia without hand function.

International audience; Stroke can lead to upper limb impairments. However, due to the brain's neuroplasticity, the upper limb’smotor skills may be recovered through hybrid robotic rehabilitation systems. This study presents a software architecture to control a hybrid FES-robotic orthosis, whose function is to rehabilitate the upper limbs of individuals with post-stroke hemiplegia. A software was developed to integrate the equipment different drive system in order to control two modules: the elbow module controlled by the motor and the hand module controlled by FES. The software was divided into three layers with different functionalities. The open loop control is based, for each functional task, on a predefined sequence of actions to be executed in a given time. The result is a modular software, which is flexible enough to accept future expansions focused on specific patient needs.

A wrist joint in upper limb prostheses significantly increases its handling capacity. However, current prostheses cannot reproduce the ability of torque combined with the volume and weight of the human wrist. Consequently, they do not provide high efficiency in handling and generate user dissatisfaction. In this context, this study aims to optimal design a wrist supination and pronation brake to improve the handling capacity of an upper limb prosthesis. The wrist actuator consists of an EC motor and harmonic drive parallel with a magnetorheological brake. The brake guarantees a fast response time, low energy consumption, controllability, and small dimensions. A particle swarm algorithm is applied to optimize design variables to minimize mass and energy consumption. As a result, the brake provided resistive torque of 7.4 N.m with dimensions close to a healthy member and weighing 0.1972 kg. Finally, a finite element analysis confirmed a satisfactory magnetic flux for the magnetorheological brake operating conditions. The designed brake addressed all the desired characteristics and is suitable to integrate the forearm prosthesis with wrist rotation.

The "14th Vienna International Workshop on Functional Electrical Stimulation" will be held as an integral part of the BMT2022; International audience

International audience; This study introduces a novel controller based on a Reinforcement Learning (RL) algorithm for real-time adaptation of the stimulation pattern during FES-cycling. Core to our approach is the introduction of an RL agent that interacts with the cycling environment and learns through trial and error how to modulate the electrical charge applied to the stimulated muscle groups according to a predefined policy and while tracking a reference cadence. Instead of a static stimulation pattern to be modified by a control law, we hypothesized that a non-stationary baseline set of parameters would better adjust the amount of injected electrical charge to the time-varying characteristics of the musculature. Overground FES-assisted cycling sessions were performed by a subject with spinal cord injury (SCI AIS-A, T8). For tracking a predefined pedaling cadence, two closed-loop control laws were simultaneously used to modulate the pulse intensity of the stimulation channels responsible for evoking the muscle contractions. First, a Proportional-Integral (PI) controller was used to control the current amplitude of the stimulation channels over an initial parameter setting with predefined pulse amplitude, width and fixed frequency parameters. In parallel, an RL algorithm with a decayed-epsilon-greedy strategy was implemented to randomly explore nine different variations of pulse amplitude and width parameters over the same stimulation setting, aiming to adjust the injected electrical charge according to a predefined policy. The performance of this global control strategy was evaluated in two different RL settings and explored in two different cycling scenarios. The participant was able to pedal overground for distances over 3.5 km, and the results evidenced the RL agent learned to modify the stimulation pattern according to the predefined policy and was simultaneously able to track a predefined pedaling cadence. Despite the simplicity of our approach and the existence of more sophisticated RL algorithms, our method can be used to reduce the time needed to define stimulation patterns. Our results suggest interesting research possibilities to be explored in the future to improve cycling performance since more efficient stimulation cost dynamics can be explored and implemented for the agent to learn.

International audience; Multi-contact epineural electrical stimulation is a technique that can be used to restore grip movements in people with complete tetraplegia. However, neural stimulation can induce undesired H-reflex. This reflex is known to induce a global lower recruitment threshold together with a steepest recruitment curve leading to a degraded selective response. In this study, during stimulation of the median nerve using a multi-contact cuff electrode, a H-reflex response was observed for one muscle (the pronator teres i.e. PT) among the five recorded. As both M-wave and H-wave were separately recorded, we compared the changes of recruitment, recruitment order and se-lectivity with and without the H-reflex and found that blocking the reflex would have enhance the selectivity and increase the range of the intensity amplitude while providing a higher level of gripping force. Thus, blocking H-reflex is an important issue to further enhance epineural multicontact selective stimulation.

International audience

International audience; We investigated the feasibility of a novel approach aiming at restoring functional movements in completely paralyzed upper limbs using neural stimulation. Two multi-contact cuff electrodes were wrapped around radial and median nerves, unilaterally, in 2 individuals with complete high tetraplegia. Electrodes were maintained for 28 days. Advanced stimulation configurations were implemented to achieve selective activation of fascicles and elicit different graspings. A control interface was developed to allow users to pilot movements of their hand by triggering stimulation. Both participants were able to execute palmar and key pinch grasping during functional tasks.

International audience

Stroke has a considerable incidence in the world population and would cause sequelae in the upper limbs. One way to increase the efficiency in the rehabilitation process of patients with these sequelae is through robot-assisted therapy. The present study developed a portable robotic orthosis called Pinotti Portable Robotic Exoskeleton (PPRE) and validated its functioning in clinical tests. The static and dynamic parts of the device modules are described. Design issues, such as heavyweight and engine positioning, have been optimized. The implementation of control was through a smartphone application that communicates with a microcontroller to perform desired movements. Four individuals with motor impairment of the upper limbs due to stroke performed clinical tests to validate the device. Participants did not mention pain, discomfort, tingling, and paresthesia. The robotic device showed the ability to perform the flexion and extension movements of the fingers and elbow. The PPRE was confirmed to be adequate and functional at different levels of motor impairment assessed. The orthosis presented advantages over the currently existing devices, concerning its biomechanical functioning, portability, comfort, and versatility. Thus, the apparatus has the great innovative potential to become a device for home use, serving as an aid to the therapist and facilitating the rehabilitation of patients after an injury. In a larger sample, future studies are needed to assess the effect of a robotic orthosis on the level of rehabilitation in individuals with upper limb impairment.

International audience; When estimating full-body motion from experimental data, inverse kinematics followed by inverse dynamics does not guarantee dynamical consistency of the resulting motion, especially in movements where the trajectory depends heavily on the initial state, such as in free-fall. Our objective was to estimate dynamically consistent joint kinematics and kinetics of complex aerial movements. A 42-degrees-of-freedom model with 95 markers was personalised for five elite trampoline athletes performing various backward and forward twisting somersaults. Using dynamic optimisation, our algorithm estimated joint angles, velocities and torques by tracking the recorded marker positions. Kinematics, kinetics, angular and linear momenta, and marker tracking difference were compared to results of an Extended Kalman Filter (EKF) followed by inverse dynamics. Angular momentum and horizontal linear momentum were conserved throughout the estimated motion, as per free-fall dynamics. Marker tracking difference went from 17 ± 4 mm for the EKF to 36 ± 11 mm with dynamic optimisation tracking the experimental markers, and to 49 ± 9 mm with dynamic optimisation tracking EKF joint angles. Joint angles from the dynamic optimisations were similar to those of the EKF, and joint torques were smoother. This approach satisfies the dynamics of complex aerial rigid-body movements while remaining close to the experimental 3D marker dataset.

International audience; We propose a novel approach to restore grasping in individuals with complete tetraplegia using epineural stimulation. Two multi-contact cuff electrodes were positioned around radial and median nerves in 2 volunteers during a surgery. The electrodes were maintained for 28 days. A user interface allowed the triggering of pre-programmed stimulation sequences on demand by executing stereotyped movements or by contracting voluntarily muscle on the contralateral shoulder. The stimulation selectivity obtained with the epineural electrodes was sufficient to obtain functional palmar and key pinch grip.

Individuals with complete cervical spinal cord injury suffer from a permanent paralysis of upper limbs which prevents them from achieving most of the activities of daily living. We developed a neuroprosthetic solution to restore hand motor function. Electrical stimulation of the radial and median nerves by means of two epineural electrodes enabled functional movements of paralyzed hands. We demonstrated in two participants with complete tetraplegia that selective stimulation of nerve fascicles by means of optimized spreading of the current over the active contacts of the multicontact epineural electrodes induced functional and powerful grasping movements which remained stable over the 28 days of implantation. We also showed that participants were able to trigger the activation of movements of their paralyzed limb using an intuitive interface controlled by voluntary actions and that they were able to perform useful functional movements such as holding a can and drinking through a straw.

The "14th Vienna International Workshop on Functional Electrical Stimulation" will be held as an integral part of the BMT2022.; International audience

International audience; BackgroundBrain-to-brain evoked potentials constitute a new methodology that could help to understand the network-level correlates of electrical stimulation applied for brain mapping during tumor resection. In this paper, we aimed to describe the characteristics of axono-cortical evoked potentials recorded from distinct, but in the same patient, behaviorally eloquent white matter sites.MethodsWe report the intraoperative white matter mapping and axono-cortical evoked potentials recordings observed in a patient operated on under awake condition of a diffuse low-grade glioma in the left middle frontal gyrus. Out of the eight behaviorally eloquent sites identified with 60-Hz electrical stimulation, five were probed with single electrical pulses (delivered at 1 Hz), while recording evoked potentials on two electrodes, covering the inferior frontal gyrus and the precentral gyrus, respectively. Postoperative diffusion-weighted MRI was used to reconstruct the tractograms passing through each of the five stimulated sites.ResultsEach stimulated site generated an ACEP on at least one of the recorded electrode contacts. The whole pattern—i.e., the specific contacts with ACEPs and their waveform—was distinct for each of the five stimulated sites.ConclusionsWe found that the patterns of ACEPs provided unique electrophysiological signatures for each of the five white matter functional sites. Our results could ultimately provide neurosurgeons with a new tool of intraoperative electrophysiologically based functional guidance.

International audience; Peripheral Nerve Stimulation (PNS) is a promising approach in functional restoration following neural impairments. Although it proves to be advantageous in the number of implantation sites provided compared with intramuscular or epimysial stimulation and the fact that it does not require daily placement, as is the case with surface electrodes, the further advancement of PNS paradigms is hampered by the limitation of spatial selectivity due to the current spread and variations of nerve physiology. New electrode designs such as the Transverse Intrafascicular Multichannel Electrode (TIME) were proposed to resolve this issue, but their use was limited by a lack of innovative multichannel stimulation devices. In this study, we introduce a new portable multichannel stimulator-called STIMEP-and implement different stimulation protocols in rats to test its versatility and unveil the potential of its combined use with TIME electrodes in rehabilitation protocols. We developed and tested various stimulation paradigms in a single fascicle and thereafter implanted two TIMEs. We also tested its stimulation using two different waveforms. The results highlighted the versatility of this new stimulation device and advocated for the parameterizing of a hyperpolarizing phase before depolarization as well as the use of small pulse widths when stimulating with multiple electrodes.

International audience; The purpose of this observational study was to report the experience of a 1-yr home training with functional electrical stimulation cycling of a person with T4 American Impairment Scale A paraplegia for 9 yrs, homebound due to the COVID-19 health crisis. The 40-yr-old participant had a three-phase training: V1, isometric stimulation; V2, functional electrical stimulation cycling for 3 sessions/wk; and V3, functional electrical stimulation cycling for 2–4 sessions/wk. Data on general and physical tolerance, health impact, and performance were collected. Borg Scale score relating to fatigue was 10.1 before training and 11.8 after training. The average score for satisfaction at the end of sessions was 8.7. Lean leg mass increased more than 29%, although total bone mineral density dropped by 1.6%. The ventilatory thresholds increased from 19.5 to 29% and the maximum ventilatory peak increased by 9.5%. Rosenberg’s Self-esteem Scale score returned to its highest level by the end of training. For the only track event on a competition bike, the pilot covered a distance of 1607.8 m in 17 mins 49 secs. When functional electrical stimulation cycling training is based on a clear and structured protocol, it offers the person with paraplegia the opportunity to practice this activity recreationally and athletically. In times of crisis, this training has proven to be very relevant.

International audience; Study design: Systematic Review Objectives: The sacral anterior root stimulator (SARS) was developed 40 years ago to restore urinary and bowel functions to individuals with spinal cord injury (SCI). Mostly used to restore lower urinary tract function, SARS implantation is coupled with sacral deafferentation to counteract the problems of chronic detrusor sphincter dyssynergia and detrusor overactivity. In this article, we systematically review 40 years of SARS implantation and assess the medical added-value of this approach in accordance with the PRISMA guidelines (Preferred Reporting Items for Systematic reviews and Meta-Analyses). We identified four axes of investigation: i) impact on visceral functions, ii) implantation safety and device reliability, iii) individuals quality of life, and iv) additional information about the procedure. Methods: Three databases were consulted: Pubmed, EBSCOhost and Pascal. 219 abstracts were screened and 38 publications were retained for analysis (1,147 implantations). Results: The SARS technique showed good clinical results (85.9% of individuals used their implant for micturition and 67.9% to ease bowel movements) and improved individual quality Guiho et al. 2 of life. Conversely, several sources of complications were reported after implantation (surgical complications, failures etc.). Conclusions: Despite promising results, a decline in implantations was observed. This decline can be linked to the complication rate, as well as to the development of new therapeutics (botulinum toxin, etc.) and directions for research (spinal cord stimulation) that may have an impact on people. Nevertheless, the lack of alternatives in the short-term suggests that the SARS implant is still relevant for the restoration of visceral functions after SCI.

International audience

International audience; Botulinum toxin-A (BoNT-A) blocks acetylcholine release at the neuromuscular junction (NMJ) and is widely used for neuromuscular disorders (involuntary spasms, dystonic disorders and spasticity). However, its therapeutic effects are usually measured by clinical scales of questionable validity. Single-fiber electromyography (SFEMG) is a sensitive, validated diagnostic technique for NMJ impairment such as myasthenia. The jitter parameter (µs) represents the variability of interpotential intervals of two muscle fibers from the same motor unit. This narrative review reports SFEMG use in BoNT-A treatment. Twenty-four articles were selected from 175 eligible articles searched in Medline/Pubmed and Cochrane Library from their creation until May 2020. The results showed that jitter is sensitive to early NMJ modifications following BoNT-A injection, with an increase in the early days’ post-injection and a peak between Day 15 and 30, when symptoms diminish or disappear. The reappearance of symptoms accompanies a tendency for a decrease in jitter, but always precedes its normalization, either delayed or nonexistent. Increased jitter is observed in distant muscles from the injection site. No dose effect relationship was demonstrated. SFEMG could help physicians in their therapeutic evaluation according to the pathology considered. More data are needed to consider jitter as a predictor of BoNT-A clinical efficacy.

International audience; Most of the studies using functional electrical stimulation (FES) in gait rehabilitation have been focused on correcting the drop foot syndrome. Using FES to control the knee joint in individuals with central nervous system (CNS) disorders could also play a key role in gait recovery: spasticity decrease, higher range of motion, positive effect on balance, limiting hyperextension and flexion in stance phase, reducing joint overload, etc. In stance phase, an accurate timing and a fine tuning of stimulation parameters are however required to provide a proper control of the knee stimulation while ensuring a safe and efficient support. In this study, 11 participants were equipped with inertial measurements units (IMU) and foot pressure insoles after supratentorial ischemic or hemorrhagic stroke, informing on knee angle and gait events used to online adapt FES during a 10 m walking protocol. Asymmetry of stance time and weight bearing were monitored as well as gait quality and physiological cost through a series of relevant markers. Vertical trunk motion has been significantly reduced during gait with FES (p-value = 0.038). Despite no significant improvement of stance phase asymmetry has been found, this preliminary work shows evidence of promising technical and rehabilitative potentials of a sensor-based multichannel FES system to control knee joint in post-stroke gait.

International audience; Background: Rapid onset of muscular fatigue is still one of the main issues of functional electrical stimulation (FES). A promising technique, known as distributed stimulation, aims to activate sub-units of a muscle at a lower stimulation frequency to increase fatigue-resistance. Besides a general agreement on the beneficial effects, the great heterogeneity of evaluation techniques, raises the demand for a standardized method to better reflect the requirements of a practical application. Methods: This study investigated the fatigue-development of 6 paralysed quadriceps muscles over the course of 180 dynamic contractions, evaluating different electrode-configurations (conventional and distributed stimulation). For a standardized comparison, fatigue-testing was performed at 40% of the peak-torque during a maximal evoked contraction (MEC). Further, we assessed the isometric torque for each electrode-configuration at different kneeextension-angles (70°-170°, 10° steps).Results: Our results showed no significant difference in the fatigue-index for any of the tested electrode-configurations, compared to conventional-stimulation. We conjecture that the positive effects of distributed stimulation become less pronounced at higher stimulation amplitudes. The isometric torque produced at different knee-extension angles was similar for most electrode-configurations. Maximal torque-production was found at 130°-140° kneeextension-angle, which correlates with the maximal knee-flexion-angles during running. Conclusion: In most practical applications, FES is intended to initiate dynamic movements. Therefore, it is crucial to assess fatigue-resistance by using dynamic contractions. Reporting the relationship between produced torque and knee-extension-angle can help to observe the stability of a chosen electrode-configuration for a targeted range-ofmotion. Additionally, we suggest to perform fatigue testing at higher forces (e.g. 40% of the maximal evoked torque) in pre-trained subjects with SCI to better reflect the practical demands of FES-applications.

International audience; Direct electrical stimulation (DES) is used to perform functional brain mapping during awake surgery and in epileptic patients. DES may be coupled with the measurement of Evoked Potentials (EP) to study the conductive and integrative properties of activated neural ensembles and probe the spatiotemporal dynamics of short- and long-range networks. However, its electrophysiological effects remain by far unknown. We recorded ECoG signals on two patients undergoing awake brain surgery and measured EP on functional sites after cortical stimulations and were the firsts to record three different types of EP on the same patients. Using low-intensity (1–3 mA) to evoke electrogenesis we observed that: (i) “true” remote EPs are attenuated in amplitude and delayed in time due to the divergence of white matter pathways; (ii) “false” remote EPs are attenuated but not delayed: as they originate from the same electrical source; (iii) Singular but reproducible positive components in the EP can be generated when the DES is applied in the temporal lobe or the premotor cortex; and (iv) rare EP can be triggered when the DES is applied subcortically: these can be either negative, or surprisingly, positive. We proposed different activation and electrophysiological propagation mechanisms following DES, based on the nature of activated neural elements and discussed important methodological pitfalls when measuring EP in the brain. Altogether, these results pave the way to map the connectivity in real-time between the DES and the recording sites; to characterize the local electrophysiological states and to link electrophysiology and function. In the future, and in practice, this technique could be used to perform electrophysiological mapping in order to link (non)-functional to electrophysiological responses with DES and could be used to guide the surgical act itself.

International audience; Functional electrical stimulation (FES) is a technique used in rehabilitation, allowing the recreation or facilitation of a movement or function, by electrically inducing the activation of targeted muscles. FES during cycling often uses activation patterns which are based on the crank angle of the pedals. Dynamic changes in their underlying predefined geometrical models (e.g., change in seating position) can lead to desynchronised contractions. Adaptive algorithms with a real-time interpretation of anatomical segments can avoid this and open new possibilities for the automatic design of stimulation patterns. However, their ability to accurately and precisely detect stimulation triggering events has to be evaluated in order to ensure their adaptability to real-case applications in various conditions. In this study, three algorithms (Hilbert, BSgonio, and Gait Cycle Index (GCI) Observer) were evaluated on passive cycling inertial data of six participants with spinal cord injury (SCI). For standardised comparison, a linear phase reference baseline was used to define target events (i.e., 10%, 40%, 60%, and 90% of the cycle’s progress). Limits of agreement (LoA) of ±10% of the cycle’s duration and Lin’s concordance correlation coefficient (CCC) were used to evaluate the accuracy and precision of the algorithm’s event detections. The delays in the detection were determined for each algorithm over 780 events. Analysis showed that the Hilbert and BSgonio algorithms validated the selected criteria (LoA: +5.17/−6.34% and +2.25/−2.51%, respectively), while the GCI Observer did not (LoA: +8.59/−27.89%). When evaluating control algorithms, it is paramount to define appropriate criteria in the context of the targeted practical application. To this end, normalising delays in event detection to the cycle’s duration enables the use of a criterion that stays invariable to changes in cadence. Lin’s CCC, comparing both linear correlation and strength of agreement between methods, also provides a reliable way of confirming comparisons between new control methods and an existing reference.

International audience; The use of modeling to simulate the effects of electrical stimulation on the nervous system can improve the development and use of neuroprosthesis devices, avoid long adjustment tests during the implantation surgery, and select a priori relevant parameters that could improve the benefits of stimulation and reduce side effects. In this chapter, we will focus on ways to model the nervous system in response to electrical stimulation, starting with electrical properties of the neuron membrane and ending with complex biophysics models representing the whole nerve trunk.Modeling of the peripheral nerve is a huge topic, and the first computational model could be considered to be almost 70 years old from the work of Hodgkin and Huxley. From this key starting point, both the membrane electrophysiological behavior and the biophysics of the conductive tissue get increased interest and accuracy. Finally, with the rise of more and more powerful computers and numerical solvers, it is now possible to gain insight into the intimate functioning of the axon and the nerve electrophysiological behavior. It could be used in two ways, from traveling action potentials to recording electrodes or from stimulating electrodes through current injection to action potential delivery. The chapter focuses on the second topic knowing that almost all the modeling frame is valid to achieve the inverse problem. We thus detail the method to model the biophysics and then the membrane dynamics up to the axon level through detailed equations and examples. The extension to the spinal cord or brain neural network is not introduced even though the basics remain similar.

accepted 2020-08-04; International audience; Recurrence quantification analysis (RQA) is an acknowledged method for the characterization of experimental time series. We propose a parametric version of RQA, pRQA, allowing a fast processing of spatial arrays of time series, once each is modeled by an autoregressive stochastic process. This method relies on the analytical derivation of asymptotic expressions for five current RQA measures as a function of the model parameters. By avoiding the construction of the recurrence plot of the time series, pRQA is computationally efficient. As a proof of principle, we apply pRQA to pattern recognition in multichannel electroencephalographic (EEG) data from a patient with a brain tumor.

Patients with central respiratory paralysis can benefit from diaphragm pacing to restore respiratory function. However, it would be important to develop a continuous respiratory monitoring method to alert on apnea occurrence, in order to improve the efficiency and safety of the pacing system. In this study, we present a preliminary validation of an acoustic apnea detection method on healthy subjects data. Thirteen healthy participants performed one session of two 2-min recordings, including a voluntary respiratory pause. The recordings were post-processed by combining temporal and frequency detection domains, and a new method was proposed&mdash, Phonocardiogram-Derived Respiration (PDR). The detection results were compared to synchronized pneumotachograph, electrocardiogram (ECG), and abdominal strap (plethysmograph) signals. The proposed method reached an apnea detection rate of 92.3%, with 99.36% specificity, 85.27% sensitivity, and 91.49% accuracy. PDR method showed a good correlation of 0.77 with ECG-Derived Respiration (EDR). The comparison of R-R intervals and S-S intervals also indicated a good correlation of 0.89. The performance of this respiratory detection algorithm meets the minimal requirements to make it usable in a real situation. Noises from the participant by speaking or from the environment had little influence on the detection result, as well as body position. The high correlation between PDR and EDR indicates the feasibility of monitoring respiration with PDR.

Objective Micro-fabricated neural interfaces based on polyimide (PI) are achieving increasing importance in translational research. The ability to produce well-defined micro-structures with properties that include chemical inertness, mechanical flexibility and low water uptake are key advantages for these devices. Approach This paper reports the development of the transverse intrafascicular multichannel electrode (TIME) used to deliver intraneural sensory feedback to an upper-limb amputee in combination with a sensorized hand prosthesis. A failure mode analysis on the explanted devices was performed after a first-in-human study limited to 30 d. Main results About 90% of the stimulation contact sites of the TIMEs maintained electrical functionality and stability during the full implant period. However, optical analysis post-explantation revealed that 62.5% of the stimulation contacts showed signs of delamination at the metallization-PI interface. Such damage likely occurred due to handling during explantation and subsequent analysis, since a significant change in impedance was not observed in vivo. Nevertheless, whereas device integrity is mandatory for long-term functionality in chronic implantation, measures to increase the bonding strength of the metallization-PI interface deserve further investigation. We report here that silicon carbide (SiC) is an effective adhesion-promoting layer resisting heavy electrical stimulation conditions within a rodent animal trial. Optical analysis of the new electrodes revealed that the metallization remained unaltered after delivering over 14 million pulses in vivo without signs of delamination at the metallization-PI interface. Significance Failure mode analysis guided implant stability optimization. Reliable adhesion of thin-film metallization to substrate has been proven using SiC, improving the potential transfer of micro-fabricated neural electrodes for chronic clinical applications., Journal of Neural Engineering, 17 (4), ISSN:1741-2560, ISSN:1741-2552

Background We hypothesized that a selective neural electrical stimulation of radial and median nerves enables the activation of functional movements in the paralyzed hand of individuals with tetraplegia. Compared to previous approaches for which up to 12 muscles were targeted through individual muscular stimulations, we focused on minimizing the number of implanted electrodes however providing almost all the needed and useful hand movements for subjects with complete tetraplegia. Methods We performed acute experiments during scheduled surgeries of the upper limb with eligible subjects. We scanned a set of multicontact neural stimulation cuff electrode configurations, pre-computed through modeling simulations. We reported the obtained isolated and functional movements that were considered useful for the subject (different grasping movements). Results In eight subjects, we demonstrated that selective stimulation based on multicontact cuff electrodes and optimized current spreading over the active contacts provided isolated, compound, functional and strong movements; most importantly 3 out of 4 had isolated fingers or thumb flexion, one patient performed a Key Grip, another one the Power and Hook Grips, and the 2 last all the 3 Grips. Several configurations were needed to target different areas within the nerve to obtain all the envisioned movements. We further confirmed that the upper limb nerves have muscle specific fascicles, which makes it possible to activate isolated movements. Conclusions The future goal is to provide patients with functional restoration of object grasping and releasing with a minimally invasive solution: only two cuff electrodes above the elbow. Ethics Committee / ANSM clearance prior to the beginning of the study (inclusion period 2016–2018): CPP Sud Méditerranée, #ID-RCB:2014-A01752–45, first acceptance 10th of February 2015, amended 12th of January 2016. Trial registration ( www.clinicaltrials.gov ): # NCT03721861 , Retrospectively registered on 26th of October 2018.

The HILECOP methodology is a process for the design of critical digital systems. In HILECOP, Petri Net (PN) models are used as a high-level formalism to specify the behavior of the designed systems. VHDL (VHSIC Hardware Description Language) code is then automatically generated from PN models to implement the digital system on Field Programmable Gate Array (FPGA) circuits. The goal of this work is to formally verify that through this model-to-text transformation, the behavior described by a PN model is preserved in the produced VHDL code, knowing that the transformed PN models are synchronously executed on the target. As a first step toward the achievement of this goal, we present our implementation of HILECOP's PN structure and semantics , which has been formalized using the Coq proof assistant. We also describe a token player program for these PNs, which has been proved sound and complete with respect to HILECOP's PN semantics.

International audience; A recent tasked-based fMRI study unveiled a network of areas implicated in the process of visuo-proprioceptive integration of the right hand. In this study, we report a case of a patient operated on in awake conditions for a glioblastoma of the left superior parietal lobule. When stimulating a white matter site in the anterior wall of the cavity, the patient spontaneously reported a discrepancy between the visual and proprioceptive perceptions of her right hand. Using several multimodal approaches (axono-cortical evoked potentials, tractography, resting-state functional connectivity), we demonstrated converging support for the hypothesis that tumor-induced plasticity redistributed the left-lateralized network of right-hand visuo-proprioceptive integration towards its right-lateralized homolog.

Introduction: Patients who have an artificial ventilation dependence are usually treated with mechanical ventilation. If their phrenic nerves and diaphragms are still functional, implanted diaphragm pacing (DP) can provide them a more natural respiration. But existing DP systems cannot monitor patient’s induced respiration and stimulate with a current of constant intensity and frequency. Adding adaptive abilities to existing systems would improve the efficiency of the delivered stimulation and could also deliver an alarm in case of an apnea detection. A respiratory monitoring method based on recordings from tracheal sounds by microphone is introduced. This method aims at being ambulatory and non-invasive for all-day long real-time use.Methods: Tracheal sounds were recorded by a microphone inserted into a 3D printed bell-shape support, which was stuck over patient’s neck. Recorded signals were filtered and pre-amplified then saved and processed in a computer. Four protocols were designed to record and analyze respiration in different contexts: (1) 15 healthy subjects; (2) 1 patient with high tetraplegia under IT-PNS; (3) 13 healthy subjects in sitting and lying positions with reference signals; (4) 30 patients with sleep apnoea and 10 patients with implanted IT-PNS will be included in short future. One real-time processing algorithm detected all inspiration/expiration phases by combining results from temporal envelope detection, frequency detection, and also PDR detection (PCG-derived respiration: variation of cardiac peak amplitude corresponds to respiration). Combining the detection results in these 3 domains allowed for a better specificity of system (less false positives).Results: The application of the algorithms to protocols 1 to 3 data lead to good detection results that met the minimum requirements for the system. These result also showed that noises like speech or environments and different body position do not influence much the detection results. The new proposed respiratory effort evaluation method -- PDR showed a good correlation with EDR, this demonstrates the feasibility to use the PDR to monitor respiration. At a good correlation between R-R intervals and S-S intervals also showed that it would also be possible to monitor heart activity from tracheal sounds.Conclusions: This thesis shows the feasibility of detecting the apnoea and of monitoring cardiac activity from tracheal sounds. The extracted signal PDR could be used to identify the type of apnoea (obstructive/central). Furthermore, the microphone-based recording system could capture stimulation signals which can indicate a dysfunction of the pacing system and recorded tracheal sounds could give a feedback of the electro-ventilation quality. The next step is to record patient's tracheal sounds signals and test if the same algorithm could still work well in this context (the protocol 4).Monitoring tracheal sounds could provide a non-invasive way to approximate inspiratory flow that would be useful in all patients requiring respiratory monitoring in acute situations (e.g. as a safety measure during the administration of morphine for acute pain) and in chronic situations (e.g. home mechanical ventilation). And in the construction of smart house, especially for nursing/retirement home, application of tracheal sounds monitoring could provide convenient, robust multi-vital signals monitoring., Introduction : Les patients dépendant d’une ventilation artificielle sont principalement placés sous ventilation mécanique. Si leur nerf phrénique et leur diaphragme demeurent fonctionnels, un implant de stimulation du diaphragme (DP) peut permettre une respiration plus naturelle. Mais les systèmes DP existants ne peuvent monitorer la respiration induite du patient et ne permettent que de stimuler à intensité et à fréquence constantes. Ajouter une capacité d’adaptation à ces systèmes pourrait améliorer l’efficacité de la stimulation. Une méthode de monitoring respiratoire basée sur l’enregistrement de sons trachéaux via un microphone a été introduite dans cette thèse. Cette méthode a été conçue pour être portable et non-invasive, et capable de fonctionner une journée complète et en temps réel.Méthodes : Les sons trachéaux ont été enregistrés à l’aide d’un microphone placé dans un support en forme de cloche réalisé par impression 3D, et placé sur le cou du patient. Les signaux récupérés ont été filtrés et pré-amplifiés puis enregistrés et traités sur ordinateur. Quatre protocoles ont été conçus pour enregistrer des sons trachéaux dans divers contextes : (1) 15 sujets sains ; (2) 1 patient ayant une tétraplégie haute sous IT-PNS ; (3) 13 sujets sains assis puis couchés, avec des signaux de référence ; (4) 30 patients souffrant d’apnée du sommeil et 10 patients avec un système IT-PNS implanté seront includes prochainement. Un algorithme de traitement du signal en temps réel a permis de détecter toutes les phases d’inspiration et d’expiration par détection d’enveloppe dans les domaines temporel, fréquentiel, et également une détection à partir du PDR (PCG-derived respiration : la variation d’amplitude des pics cardiaques correspond à la respiration). La combinaison de ces trois détections permet une meilleure spécificité du système (moins de faux-positifs).Résultats : L’application de l’algorithme aux données des protocoles 1 et 3 a conduit à de bons résultats de détection qui satisfont le minimum requis pour système. Ces résultats ont aussi montré que les bruits tels que la parole ou l’environnement extérieur, et les différentes position du corps n’influencent pas le résultat de la détection. La nouvelle méthode d’évaluation de l’effort respiratoire proposé – PDR montre une bonne corrélation avec EDR, ce qui démontre la faisabilité de l’utilisation de PDR pour le monitoring de la respiration. Une bonne corrélation entre des intervalles R-R et S-S montre également qu'il serait donc également possible de monitorer l’activité du cœur à partir des sons trachéaux.Conclusions : Cette thèse a démontré la faisabilité de détecter des épisodes d’apnée à partir de sons trachéaux et de monitorer l’activité cardiaque. Le signal extrait PDR peut permettre d’identifier le type d’apnée (obstructive / centrale). De plus, le système d’enregistrement par microphone peut permettre d’observer les signaux de stimulation électrique chez les patients implantés et indiquer un dysfonctionnement éventuel du système implanté. Les sons trachéaux peuvent aussi fournir un retour sur la qualité de l’électroventilation. La prochaine étape sera donc d’obtenir les enregistrements de patients et de tester si ce même algorithme fonctionne dans ce cas (protocole 4). Le monitoring des sons trachéaux peut fournir une méthode non-invasive pour estimer le flux inspiratoire dans le cas de patients nécessitant un monitoring respiratoire dans les situations extrêmes (e.g. comme une mesure de sécurité pour l’administration de morphine pour les douleurs aiguës) et dans les situations chroniques (e.g. la ventilation mécanique à domicile). Et dans le cas de maisons connectées, en particulier pour les maisons de retraite, les applications de monitoring des sons trachéaux peut permettre un monitoring robuste et efficace des signes multi-vitaux.

International audience; This paper presents a wireless distributed Functional Electrical Stimulation (FES) architecture. It is based on a set of, potentially heterogeneous, distributed stimulation and measurement units managed by a wearable controller. Through a proof-of-concept application, the characterization of the wireless network performances was assessed to check the adequacy of this solution with open-loop and closed-loop control requirements. We show the guaranteed time performances over the network through the control of quadriceps and hamstrings stimulation parameters based on the monitoring of the knee joint angle. Our solution intends to be a tool for researchers and therapists to develop closed-loop control algorithms and strategies for rehabilitation, allowing the design of wearable systems for a daily use context.

Background: Partial arterial pressure of carbon dioxide ( C O 2 ) modulates cerebral blood flow through a vasoreactivity mechanism. Near infrared spectroscopy (NIRS) can be used to record these changes in cerebral hemodynamics. However, no laterality comparison of the NIRS signal has been performed despite being a prerequisite for the use of such a method in a vasoreactivity monitoring context. We propose to investigate the NIRS signal laterality in response to a C O 2 -inhalation-based hypercapnia paradigm in healthy volunteers. Methods: Eleven healthy volunteers (6 women, 5 men, mean age: 31 ± 11) underwent a 3-block-design inhalation paradigm: normoxia (5min, “baseline”) – hypercapnia (2min, “stimulation”) – normoxia (5min, “post-stimulation”). NIRS signal was measured using a two-channel oximeter (INVOS 5100C, Medtronic, USA) with sensors placed symmetrically on both left and right sides on each subject’s forehead. Additional heart rate (HR) monitoring was performed simultaneously. Based on the NIRS mean signal pattern, an a priori model of parametric identification was applied for each channel to quantify parameters of interest (amplitude, time delay, excitation and post-stimulation time) for each inhalation block. Results: HR increased significantly during the stimulation block. The quality of the model was satisfactory: mean absolute errors between modelled and experimental signals were lower than the resolution of the device. No significant lateralization was found between left and right values of most of the parameters. Conclusion: Due to the lack of lateralization, this parametric identification of NIRS responses to hypercapnia could bring light to a potential asymmetry and be used as a biomarker in patients with cerebrovascular diseases.

This study aims to present the design, selection and testing of commercial ropes (artificial tendons) used on robotic orthosis to perform the hand movements for stroke individuals over upper limb rehabilitation. It was determined the load applied in the rope would through direct measurements performed on four individuals after stroke using a bulb dynamometer. A tensile strength test was performed using eight commercial ropes in order to evaluate the maximum breaking force and select the most suitable to be used in this application. Finally, a pilot test was performed with a user of the device to ratify the effectiveness of the rope. The load on the cable was 12.38 kgf (121.4 N) in the stroke-affected hand, which is the maximum tensile force that the rope must to supports. Paragliding rope (DuPont&trade, Kevlar &reg, ) supporting a load of 250 N at a strain of 37 mm was selected. The clinical test proved the effectiveness of the rope, supporting the requested efforts, without presenting permanent deformation, effectively performing the participant&rsquo, s finger opening.

International audience; Implanted stimulation restores hand movement in patients with complete spinal cord injuries. However, assessing the response by surface evoked EMG recordings is challenging because the forearm muscles are small and overlapping. Moreover, M-waves are dependent because they are induced by a single stimulation paradigm. We hypothesized that the M-waves of each muscle has a specific time–frequency signature and we have developed a method to reconstruct the recruitment curves using the energy of this specific time–frequency signature. Orthogonal wavelets are used to analyze individual M-waves. As the selection of the wavelet family and the determination of the time–frequency signature were not trivial, the impact of these choices was evaluated. First, we were able to discriminate the 2 relevant M-waves related to the studied muscles thanks to their specific time–frequency representations. Second, the Meyer family, compared to the Daubechies 2 and 4 families, is the most robust choice against the uncertainty of the time–frequency region definition. Finally, the results are consistent with the semi-quantitative evaluation performed with the MRC scoring. The Meyer wavelet transform combined with the definition of a specific area of interest for each individual muscle allows us to quantitatively and objectively evaluate the evoked EMG in a robust manner.

International audience; Background: Direct electrical stimulation (DES) is used to perform functional brain mapping during awake surgery but its electrophysiological effects remain by far unknown.Hypothesis: DES may be coupled with the measurement of Evoked Potentials (EPs) to study the conductive and integrative properties of activated neural ensembles and probe the spatiotemporal dynamics of short- and long- range networks.Methods: We recorded ECoG signals on two patients undergoing awake brain surgery and measured EPs on functional sites after cortical stimulations, using combinations of stimulation parameters.Results: EPs were similar in shape but delayed in time and attenuated in amplitude when elicited from a different gyrus or remotely from the recording site. We were able to trigger remote EPs using low stimulation intensities.Conclusion: We propose different activation and electrophysiological propagation mechanisms following DES based on activated neural elements.

International audience; Objective: Direct electrical stimulation (DES) at 60 Hz is used to perform real-time functional mapping of the brain, and guide tumour resection during awake neurosurgery. Nonetheless, the electrophysiological effects of DES remain largely unknown, both locally and remotely.Approach: In this study, we lowered the DES frequency to 1-10 Hz and we used a differential recording mode of electro-corticographic (ECoG) signals to improve the focality with a simple algorithm to remove the artefacts due to the response of the acquisition chain.Main results: Doing so, we were able to observe different components in the evoked potentials triggered by simulating the cortex or the subcortical white matter pathways near the recording electrodes and by stimulating the cortex remotely from the recording site. More particularly, P0 and N1 components were repeatedly observed on raw ECoG signals without the need to average the data.Significance: This new methodology is important to probe the electrophysiological states and the connectivity of the brain in vivo and in real time, namely to perform electrophysiological brain mapping on human patients operated in the neurosurgical room and to better understand the electrophysiological spreading of DES.

Robot-Assisted Therapy (RT) is an innovative approach to neurological rehabilitation that uses intensive, repetitive, interactive, and individualized practice. This systematic review aimed to investigate the effectiveness of RT on the body function and structure of people with upper limb impairments (PROSPERO registration: CRD42017054982). A search strategy conducted on seven databases identified randomized controlled studies. Methodological quality was assessed using the PEDro scale. When possible, the data were pooled, the strength of evidence was assessed using the GRADE system, and the effect sizes were assessed using Cohen coefficient. Subgroup analyses investigated the impact on the estimated effects of the following parameters: methodological quality; portion of the assessed upper limb; duration of stroke; and intervention dose and duration. Thirty-eight studies involving 1174 participants were included. Pooled estimates revealed small effects of RT on motor control and medium effects on strength compared with other intervention (OI) at a short-term follow-up. Standardized differences in means were as follows: 0.3 (95% CI 0.1 to 0.4) and 0.5 (95% CI 0.2 to 0.8). Effects at other time points and on other investigated outcomes related to body function and structure were not found (p>0.05). The strength of the current evidence was usually low quality. Subgroup analyses suggested that the methodological quality, and duration and dose of RT may influence the estimated effects. In conclusion, RT has small effects on motor control and medium effects on strength in people with limited upper limb function. Poor methodological quality, and lower treatment dose and duration may impact negatively the estimated effects.

Objective. We present the design, implementation, and evaluation of a wearable multichannel haptic system. The device is a wireless closed-loop armband driven by surface electromyography (EMG) and provides sensory feedback encoding proprioception. The study is motivated by restoring proprioception information in upper limb prostheses. Approach. The armband comprises eight vibrotactile actuators that generate distributed patterns of mechanical waves around the limb to stimulate perception and to transfer proportional information on the arm motion. An experimental study was conducted to assess: the sensory threshold in eight locations around the forearm, the user adaptation to the sensation provided by the device, the user performance in discriminating multiple stimulation levels, and the device performance in coding proprioception using four spatial patterns of stimulation. Eight able-bodied individuals performed reaching tasks by controlling a cursor with an EMG interface in a virtual environment. Vibrotactile patterns were tested with and without visual information on the cursor position with the addition of a random rotation of the reference control system to disturb the natural control and proprioception. Main results. The sensation threshold depended on the actuator position and increased over time. The maximum resolution for stimuli discrimination was four. Using this resolution, four patterns of vibrotactile activation with different spatial and magnitude properties were generated to evaluate their performance in enhancing proprioception. The optimal vibration pattern varied among the participants. When the feedback was used in closed-loop control with the EMG interface, the task success rate, completion time, execution efficiency, and average target-cursor distance improved for the optimal stimulation pattern compared to the condition without visual or haptic information on the cursor position. Significance. The results indicate that the vibrotactile device enhanced the participants’ perceptual ability, suggesting that the proposed closed-loop system has the potential to code proprioception and enhance user performance in the presence of perceptual perturbation.

International audience; Working towards the development of robust motion recognition systems for assistive technology control, the widespread approach has been to use a plethora of, often times, multi-modal sensors. In this paper, we develop single-sensor motion recognition systems. Utilising the peripheral nature of surface electromyography (sEMG) data acquisition, we optimise the information extracted from sEMG sensors. This allows the reduction in sEMG sensors or provision of contingencies in a system with redundancies. In particular, we process the sEMG readings captured at the trapezius descendens and platysma muscles. We demonstrate that sEMG readings captured at one muscle contain distinct information on movements or contractions of other agonists. We used the trapezius and platysma muscle sEMG data captured in able-bodied participants and participants with tetraplegia to classify shoulder movements and platysma contractions using white-box supervised learning algorithms. Using the trapezius sensor, shoulder raise is classified with an accuracy of 99%. Implementing subject-specific multi-class classification, shoulder raise, shoulder forward and shoulder backward are classified with a 94% accuracy amongst object raise and shoulder raise-and-hold data in able bodied adults. A three-way classification of the platysma sensor data captured with participants with tetraplegia achieves a 95% accuracy on platysma contraction and shoulder raise detection.