Neuromusculoskeletal Model Research Articles

A Focused Review on Upper and Lower Limb Joint Torque Estimation via Neural Networks

Joint torque estimation is an essential aspect of the control architecture in assistive devices for rehabilitation and aiding movement impairments. Healthy adult torque trajectories serve as a baseline for controllers to determine the level of assistance required by patients, evaluate impaired motion, understand biomechanics, and design treatment plans. Currently, methods of torque estimation include inverse dynamics using gold standard motion capture systems, generic mathematical models based on joint torque-angle relationships, neuromusculoskeletal modelling using surface electromyography, and neural networks. As such, this review provides a focused overview of the recent and existing neural networks tailored for upper and lower limb joint torque estimation. Dataset preparation, data preprocessing, and evaluation metrics are presented along with a detailed description of the developed networks, which are classified by model architecture. It includes artificial neural networks (ANNs), convolution neural networks (CNNs), long short-term memory (LSTM) networks, and hybrid and alternate architectures such as wavelet or explainable convolution (XCM). The performance, benefits, and limitations of the models are discussed, highlighting CNNs and LSTMs as the current optimal models for time series prediction of joint torque. This is due to their ability to capture spatial and temporal dependencies in the data. Additionally, joint kinematics such as angles, angular velocities, and accelerations are considered optimal input parameters due to their ease of measurement using wearable sensors and integration with wearable assistive technology.

Effect of Postoperative Neck-Shaft and Anteversion Angles on Biomechanical Outcomes in Proximal Femoral Osteotomy: An In Silico Study.

Effective surgical planning is crucial for maximizing patient outcomes following complex orthopedic procedures such as proximal femoral osteotomy. In silico simulations can be used to assess how surgical variations in proximal femur geometry, such as femur neck-shaft and anteversion angles, affect postoperative system mechanics. This study investigated the sensitivity of femur mechanics to postoperative neck-shaft angles, anteversion angles, and osteotomy contact areas using patient-specific finite element analysis informed by neuromusculoskeletal models. A sequential neuromusculoskeletal modeling and finite element analysis pipeline was used to simulate postoperative mechanics in three pediatric patients with varying demographic and anatomic features. Nine surgical configurations derived from permutations of the clinical envelope of neck-shaft angles and anteversion angles were simulated for the stance phase of gait. The outcome mechanics assessed were peak von Mises stresses on the bone-implant contact surfaces as well as interfragmentary movement and strain on the osteotomy location. Peak von Mises stress and interfragmentary movement and strain were on average 38% more sensitive to surgical variation in neck-shaft angle compared to anteversion angle. A significant negative correlation was detected between contact area and interfragmentary movement (r = -0.90, p < 0.0001) and strain (r = -0.45, p = 0.017). Overall findings suggest neck-shaft angle significantly influences postoperative femur mechanics and highlight the importance of maximizing contact area to limit interfragmentary motion and foster an optimal mechanical environment for bone healing and callus formation following proximal femoral osteotomy. Between-patient variation in sensitivity to proximal femoral geometry reinforced the importance of patient-specific surgical planning.

Effects of Arthroscopic Surgery and Non-Surgical Therapy on Hip Contact Forces in Femoroacetabular Impingement Syndrome.

We compared the 12-months effects of arthroscopic surgery and physiotherapist-led care for femoroacetabular impingement (FAI) syndrome on the time-varying magnitude of hip contact force and muscle contributions to hip contact force during walking. Secondary analysis was performed on thirty-seven individuals with FAI syndrome who received biomechanical assessment before and 12-months following either arthroscopic surgery (n = 17) or physiotherapist-led care (Personalised Hip Therapy, PHT) (n = 20). At both time points, three-dimensional whole-body motions, ground reaction forces, and surface electromyograms (n = 14) were acquired during overground walking. A neuromusculoskeletal model was used to determine hip contact force and muscle contributions to hip contact force. Two-way repeated measures analyses of variance, implemented through statistical parametric mapping, were used to assess interactions between, and main effects of, treatment (arthroscopy vs. PHT) and time (baseline vs. follow-up) on time-varying magnitude of hip contact force and muscle contributions to hip contact force. Effects were reported as mean differences (normalized to bodyweight, BW) with 95% confidence intervals [95% CI, lower, upper bound]. For both treatment groups, hip contact force was larger at 12-months compared to their respective baseline (mean increase across stride, arthroscopy: 0.97 BW [95% CI 0.49, 1.46] p < .001; PHT: 1.05 BW [95% CI 0.68, 1.43] p < .001), however, no interaction effects were found. For both treatment groups, hip flexor, adductor, and abductor muscle groups made greater contributions to hip contact force after 12-months compared to baseline, while hip extensors made smaller contributions. Compared to baseline, both treatments resulted in 12-months increases in hip contact force during walking caused by larger flexor, adductor, and abductor muscle forces at follow-up. At 12-months, hip contact force magnitude remained different normative values reported for healthy individuals, indicating neither treatment fully restored hip biomechanics.

Effects of foot–ground friction and age-related gait changes on falls during walking: a computational study using a neuromusculoskeletal model

We used a neuromusculoskeletal model of bipedal walking to examine the effects of foot–ground friction conditions and gait patterns on slip- and trip-induced falls. We developed three two-dimensional neuro-musculoskeletal models in a self-organized manner representing young adults, elderly non-fallers, and elderly fallers. We simulated walking under different foot-ground friction conditions. The static friction coefficient between the foot and the ground was varied from 0.05 to 2.0. Under low friction conditions, the three gait models demonstrated slip-induced falls. The elderly faller model experienced the most slip. This is because the RCOF was higher in the elderly faller model due to its short stride length but much smaller foot clearance. Under high friction conditions, only the elderly faller model demonstrated trip-induced falls. Based on the analysis using the margin of stability, the forward postural stability of the model gradually decreased under high-friction conditions, with the toe of the swing foot contacting the ground and subsequently falling forward. These results imply that there is an optimal coefficient of friction for the ground to prevent slip- and trip-induced falls by people with less stable gaits, which may provide new insights into the design of shoes and floor surfaces for the elderly.

The Neuromusculoskeletal Modeling Pipeline: MATLAB-based Model Personalization and Treatment Optimization Functionality for OpenSim.

Neuromusculoskeletal injuries including osteoarthritis, stroke, spinal cord injury, and traumatic brain injury affect roughly 19% of the U.S. adult population. Standardized interventions have produced suboptimal functional outcomes due to the unique treatment needs of each patient. Strides have been made to utilize computational models to develop personalized treatments, but researchers and clinicians have yet to cross the "valley of death" between fundamental research and clinical usefulness. This article introduces the Neuromusculoskeletal Modeling (NMSM) Pipeline, two MATLAB-based toolsets that add Model Personalization and Treatment Optimization functionality to OpenSim. The two toolsets facilitate computational design of individualized treatments for neuromusculoskeletal impairments through the use of personalized neuromusculoskeletal models and predictive simulation. The Model Personalization toolset contains four tools for personalizing 1) joint structure models, 2) muscle-tendon models, 3) neural control models, and 4) foot-ground contact models. The Treatment Optimization toolset contains three tools for predicting and optimizing a patient's functional outcome for different treatment options using a patient's personalized neuromusculoskeletal model with direct collocation optimal control methods. Support for user-defined cost functions and model modification functions facilitate simulation of a vast number of possible treatments. An NMSM Pipeline use case is presented for an individual post-stroke with impaired walking function, where the goal was to predict how the subject's neural control could be changed to improve walking speed without increasing metabolic cost. First the Model Personalization toolset was used to develop a personalized neuromusculoskeletal model of the subject starting from a generic OpenSim full-body model and experimental walking data (video motion capture, ground reaction, and electromyography) collected from the subject at his self-selected speed. Next the Treatment Optimization toolset was used with the personalized model to predict how the subject could recruit existing muscle synergies more effectively to reduce muscle activation disparities between the paretic and non-paretic legs. The software predicted that the subject could increase his walking speed by 60% without increasing his metabolic cost per unit time by modifying existing muscle synergy recruitment. This hypothetical treatment demonstrates how NMSM Pipeline tools could allow researchers working collaboratively with clinicians to develop personalized neuromusculoskeletal models of individual patients and to perform predictive simulations for the purpose of designing personalized treatments that maximize a patient's post-treatment functional outcome.

Inclusion of Muscle Forces Affects Finite Element Prediction of Compression Screw Pullout but Not Fatigue Failure in a Custom Pelvic Implant

Custom implants used for pelvic reconstruction in pelvic sarcoma surgery face a high complication rate due to mechanical failures of fixation screws. Consequently, patient-specific finite element (FE) models have been employed to analyze custom pelvic implant durability. However, muscle forces have often been omitted from FE studies of the post-operative pelvis with a custom implant, despite the lack of evidence that this omission has minimal impact on predicted bone, implant, and fixation screw stress distributions. This study investigated the influence of muscle forces on FE predictions of fixation screw pullout and fatigue failure in a custom pelvic implant. Specifically, FE analyses were conducted using a patient-specific FE model loaded with seven sets of personalized muscle and hip joint contact force loading conditions estimated using a personalized neuromusculoskeletal (NMS) model. Predictions of fixation screw pullout and fatigue failure—quantified by simulated screw axial forces and von Mises stresses, respectively—were compared between analyses with and without personalized muscle forces. The study found that muscle forces had a considerable influence on predicted screw pullout but not fatigue failure. However, it remains unclear whether including or excluding muscle forces would yield more conservative predictions of screw failures. Furthermore, while the effect of muscle forces on predicted screw failures was location-dependent for cortical screws, no clear location dependency was observed for cancellous screws. These findings support the combined use of patient-specific FE and NMS models, including loading from muscle forces, when predicting screw pullout but not fatigue failure in custom pelvic implants.

Enhancing biomechanical outcomes in proximal femoral osteotomy through optimised blade plate sizing: A neuromusculoskeletal-informed finite element analysis

Proximal femoral osteotomy (PFO) is a frequently performed surgical procedure to correct hip deformities in the paediatric population. The optimal size of the blade plate implant in PFO is a critical but underexplored factor influencing biomechanical outcomes. This study introduces a novel approach to refine implant selection by integrating personalized neuromusculoskeletal modelling with finite element analysis. Using computed tomography scans and walking gait data from six paediatric patients with various pathologies and deformities, we assessed the impact of four distinct implant width-to-femoral neck diameter (W-D) ratios (30 %, 40 %, 50 %, and 60 %) on surgical outcomes. The results show that the risk of implant yield generally decreases with increasing W-D ratio, except for Patient P2, where the yield risk remained below 100 % across all ratios. The implant factor of safety (FoS) increased with larger W-D ratios, except for Patients P2 and P6, where the highest FoS was 2.60 (P2) and 0.49 (P6) at a 60 % W-D ratio. Bone-implant micromotion consistently remained below 40 µm at higher W-D ratios, with a 50 % W-D ratio striking the optimal balance for mechanical stability in all patients except P6. Although interfragmentary and principal femoral strains did not display consistent trends across all patients, they highlight the need for patient-specific approaches to ensure effective fracture healing. These findings highlight the importance of patient-specific considerations in implant selection, offering surgeons a more informed pathway to enhance patient outcomes and extend implant longevity. Additionally, the insights gained from this study provide valuable guidance for manufacturers in designing next-generation blade plates tailored to improve biomechanical performance in paediatric orthopaedics.

Neuro-musculoskeletal modelling informed rehabilitation in Parkinson’s disease: Comparison between overground robotic training and physical therapy

Neuro-musculoskeletal modelling informed rehabilitation in Parkinson’s disease: Comparison between overground robotic training and physical therapy

Self-organizing recruitment of compensatory areas maximizes residual motor performance post-stroke.

Whereas the orderly recruitment of compensatory motor cortical areas after stroke depends on the size of the motor cortex lesion affecting arm and hand movements, the mechanisms underlying this reorganization are unknown. Here, we hypothesized that the recruitment of compensatory areas results from the motor system's goal to optimize performance given the anatomical constraints before and after the lesion. This optimization is achieved through two complementary plastic processes: a homeostatic regulation process, which maximizes information transfer in sensory-motor networks, and a reinforcement learning process, which minimizes movement error and effort. To test this hypothesis, we developed a neuro-musculoskeletal model that controls a 7-muscle planar arm via a cortical network that includes a primary motor cortex and a premotor cortex that directly project to spinal motor neurons, and a contra-lesional primary motor cortex that projects to spinal motor neurons via the reticular formation. Synapses in the cortical areas are updated via reinforcement learning and the activity of spinal motor neurons is adjusted through homeostatic regulation. The model replicated neural, muscular, and behavioral outcomes in both non-lesioned and lesioned brains. With increasing lesion sizes, the model demonstrated systematic recruitment of the remaining primary motor cortex, premotor cortex, and contra-lesional cortex. The premotor cortex acted as a reserve area for fine motor control recovery, while the contra-lesional cortex helped avoid paralysis at the cost of poor joint control. Plasticity in spinal motor neurons enabled force generation after large cortical lesions despite weak corticospinal inputs. Compensatory activity in the premotor and contra-lesional motor cortex was more prominent in the early recovery period, gradually decreasing as the network minimized effort. Thus, the orderly recruitment of compensatory areas following strokes of varying sizes results from biologically plausible local plastic processes that maximize performance, whether the brain is intact or lesioned.

Delayed center of mass feedback in elderly humans leads to greater muscle co-contraction and altered balance strategy under perturbed balance: A predictive musculoskeletal simulation study.

Falls are one of the leading causes of non-disease death and injury in the elderly, often due to delayed sensory neural feedback essential for balance. This delay, challenging to measure or manipulate in human studies, necessitates exploration through neuromusculoskeletal modeling to reveal its intricate effects on balance. In this study, we developed a novel three-way muscle feedback control approach, including muscle length feedback, muscle force feedback, and enter of mass feedback, for balancing and investigated specifically the effects of center of mass feedback delay on elderly people's balance strategies. We conducted simulations of cyclic perturbed balance at different magnitudes ranging from 0 to 80 mm and with three center of mass feedback delays (100, 150 & 200 ms). The results reveal two key points: 1) Longer center of mass feedback delays resulted in increased muscle activations and co-contraction, 2) Prolonged center of mass feedback delays led to noticeable shifts in balance strategies during perturbed standing. Under low-amplitude perturbations, the ankle strategy was predominantly used, while higher amplitude disturbances saw more frequent employment of hip and knee strategies. Additionally, prolonged center of mass delays altered balance strategies across different phases of perturbation, with a noticeable increase in overall ankle strategy usage. These findings underline the adverse effects of prolonged feedback delays on an individual's stability, necessitating greater muscle co-contraction and balance strategy adjustment to maintain balance under perturbation. Our findings advocate for the development of training programs tailored to enhance balance reactions and mitigate muscle feedback delays within clinical or rehabilitation settings for fall prevention in elderly people.

Changes in walking function and neural control following pelvic cancer surgery with reconstruction.

Introduction: Surgical planning and custom prosthesis design for pelvic cancer patients are challenging due to the unique clinical characteristics of each patient and the significant amount of pelvic bone and hip musculature often removed. Limb-sparing internal hemipelvectomy surgery with custom prosthesis reconstruction has become a viable option for this patient population. However, little is known about how post-surgery walking function and neural control change from pre-surgery conditions. Methods: This case study combined comprehensive walking data (video motion capture, ground reaction, and electromyography) with personalized neuromusculoskeletal computer models to provide a thorough assessment of pre- to post-surgery changes in walking function (ground reactions, joint motions, and joint moments) and neural control (muscle synergies) for a single pelvic sarcoma patient who received internal hemipelvectomy surgery with custom prosthesis reconstruction. Pre- and post-surgery walking function and neural control were quantified using pre- and post-surgery neuromusculoskeletal models, respectively, whose pelvic anatomy, joint functional axes, muscle-tendon properties, and muscle synergy controls were personalized using the participant's pre-and post-surgery walking and imaging data. For the post-surgery model, virtual surgery was performed to emulate the implemented surgical decisions, including removal of hip muscles and implantation of a custom prosthesis with total hip replacement. Results: The participant's post-surgery walking function was marked by a slower self-selected walking speed coupled with several compensatory mechanisms necessitated by lost or impaired hip muscle function, while the participant's post-surgery neural control demonstrated a dramatic change in coordination strategy (as evidenced by modified time-invariant synergy vectors) with little change in recruitment timing (as evidenced by conserved time-varying synergy activations). Furthermore, the participant's post-surgery muscle activations were fitted accurately using his pre-surgery synergy activations but fitted poorly using his pre-surgery synergy vectors. Discussion: These results provide valuable information about which aspects of post-surgery walking function could potentially be improved through modifications to surgical decisions, custom prosthesis design, or rehabilitation protocol, as well as how computational simulations could be formulated to predict post-surgery walking function reliably given a patient's pre-surgery walking data and the planned surgical decisions and custom prosthesis design.

A sensorimotor enhanced neuromusculoskeletal model for simulating postural control of upright standing.

The human's upright standing is a complex control process that is not yet fully understood. Postural control models can provide insights into the body's internal control processes of balance behavior. Using physiologically plausible models can also help explaining pathophysiological motion behavior. In this paper, we introduce a neuromusculoskeletal postural control model using sensor feedback consisting of somatosensory, vestibular and visual information. The sagittal plane model was restricted to effectively six degrees of freedom and consisted of nine muscles per leg. Physiologically plausible neural delays were considered for balance control. We applied forward dynamic simulations and a single shooting approach to generate healthy reactive balance behavior during quiet and perturbed upright standing. Control parameters were optimized to minimize muscle effort. We showed that our model is capable of fulfilling the applied tasks successfully. We observed joint angles and ranges of motion in physiologically plausible ranges and comparable to experimental data. This model represents the starting point for subsequent simulations of pathophysiological postural control behavior.

Effect of different constraining boundary conditions on simulated femoral stresses and strains during gait

Finite element analysis (FEA) is commonly used in orthopaedic research to estimate localised tissue stresses and strains. A variety of boundary conditions have been proposed for isolated femur analysis, but it remains unclear how these assumed constraints influence FEA predictions of bone biomechanics. This study compared the femoral head deflection (FHD), stresses, and strains elicited under four commonly used boundary conditions (fixed knee, mid-shaft constraint, springs, and isostatic methods) and benchmarked these mechanics against the gold standard inertia relief method for normal and pathological femurs (extreme anteversion and retroversion, coxa vara, and coxa valga). Simulations were performed for the stance phase of walking with the applied femoral loading determined from patient-specific neuromusculoskeletal models. Due to unrealistic biomechanics observed for the commonly used boundary conditions, we propose a novel biomechanical constraint method to generate physiological femur biomechanics. The biomechanical method yielded FHD (< 1 mm), strains (approaching 1000 µε), and stresses (< 60 MPa), which were consistent with physiological observations and similar to predictions from the inertia relief method (average coefficient of determination = 0.97, average normalized root mean square error = 0.17). Our results highlight the superior performance of the biomechanical method compared to current methods of constraint for both healthy and pathological femurs.

Foetus-specific neuromusculoskeletal modelling with MRI-driven vaginal delivery kinematics during the second stage of labor

Childbirth simulations lack realism due to an oversimplification of the foetal model, particularly as most models do not allow joint motion. Foetus-specific neuromusculoskeletal (NMS) model with a detailed articulated skeleton is still not available in the literature. The present work aims at proposing the first-ever foetus-specific NMS model and then simulating the foetal descent during a vaginal delivery by using in vivo medical resonance imaging (MRI) childbirth data. Moreover, the developed model is provided open source for the community. Our foetus-specific NMS model was developed using the geometries reconstructed from a foetal computed tomography (CT) scan (Female, mass = 2.35 kg, length = 50 cm). The model contains 22 joints (64 degrees of freedom) and 65 muscles with a particular attention to the cervical spine level to enable the simulation of the cardinal movements. Then, the skull-to-cervical-spine (S/CP) and cervical-spine-to-torso (CP/T) deflection angles were extracted from in vivo MRI data for motion simulation. The S/CP and CP/T deflexion angles range from 12 degrees of flexion to 2 degrees of extension and from 7 degrees of flexion to 22 degrees of extension respectively. The developed model opens new avenues in more biofidelic childbirth simulations with a complete foetal NMS model. Obtained outcomes with the in vivo MRI data enabled to perform a first simulation of the foetal descent kinematics using real childbirth data. Future works will focus on developing a novel muscle formulation of the foetus and combining such a NMS model with a deformable model to simulate childbirth and associated complication scenarios.

Spectral characterization of human leg EMG signals from an open access dataset for the development of computational models.

Large-scale neuromusculoskeletal models have been used for predicting mechanisms underlying neuromuscular functions in humans. Simulations of such models provide several types of signals of practical interest, such as surface electromyographic signals (EMG), which are compared with experimental data for interpretations of neurophysiological phenomena under study. Specifically, realistic characterization of spectral properties of simulated EMG signals is important for achieving powerful inferences, whereas considerations should be taken for myoelectric signals of different muscles. In this study, we characterized spectral properties of surface interference pattern EMG signals and motor unit action potentials (MUAP) acquired from three plantar flexor muscles: Soleus (SO), Medial Gastrocnemius (MG), and Lateral Gastrocnemius (LG); and one dorsiflexor muscle: Tibialis Anterior (TA). Surface EMG signals were acquired from 20 participants using the same convention for electrode placement. Specifically, interference pattern EMG signals were obtained during isometric constant force contractions at 5%, 10% and 20% of maximum voluntary contraction (MVC), whereas surface MUAPs were decomposed from surface EMG signals obtained at low contraction forces. We compared the spectrum median frequency (MDF) estimated from interference pattern EMG signals across muscles and contraction intensities. Additionally, we compared MDF and durations of MUAPs between muscles. Our results showed that MDF of interference pattern EMG signals acquired from TA were higher compared to SO, MG, and LG for all contraction intensities i.e., 5%, 10%, and 20% MVC. Consistently, MUAPs acquired from TA also had higher MDF values and shorter durations compared to the other leg muscles. We provide herein a dataset with the surface MUAPs waveforms and interference pattern EMG signals obtained for this study, which should be useful for implementing and validating the simulation of myoelectrical signals of leg muscles. Importantly, these results indicate that spectral properties of myoelectrical signals should be considered for improving EMG modeling in large-scale neuromusculoskeletal models.

Neuromusculoskeletal modeling in health and disease

This opinion paper provides an overview of musculoskeletal modeling, revealing insights into muscle-tendon kinematics, forces, and joint contact forces during dynamic movements, thereby advancing our understanding of biomechanics. While subject-specific modeling poses challenges, emerging software tools enable rapid personalization of musculoskeletal geometry and motor control, enhancing physiological accuracy. Advanced predictive simulations and multi-scale modeling expand clinical applications, facilitating surgery outcomes prediction and movement modification for joint diseases. Collaborative interdisciplinary efforts are essential for overcoming challenges, refining workflows, and ultimately enhancing clinical treatment outcomes.

Joint contact forces during semi-recumbent seated cycling

Semi-recumbent cycling performed from a wheelchair is a popular rehabilitation exercise following spinal cord injury (SCI) and is often paired with functional electrical stimulation. However, biomechanical assessment of this cycling modality is lacking, even in unimpaired populations, hindering the development of personalised and safe rehabilitation programs for those with SCI. This study developed a computational pipeline to determine lower limb kinematics, kinetics, and joint contact forces (JCF) in 11 unimpaired participants during voluntary semi-recumbent cycling using a rehabilitation ergometer. Two cadences (40 and 60 revolutions per minute) and three crank powers (15 W, 30 W, and 45 W) were assessed. A rigid body model of a rehabilitation ergometer was combined with a calibrated electromyogram-informed neuromusculoskeletal model to determine JCF at the hip, knee, and ankle. Joint excursions remained consistent across all cadence and powers, but joint moments and JCF differed between 40 and 60 revolutions per minute, with peak JCF force significantly greater at 40 compared to 60 revolutions per minute for all crank powers. Poor correlations were found between mean crank power and peak JCF across all joints. This study provides foundation data and computational methods to enable further evaluation and optimisation of semi-recumbent cycling for application in rehabilitation after SCI and other neurological disorders.

Muscle synergy-informed neuromusculoskeletal modelling to estimate knee contact forces in children with cerebral palsy

Cerebral palsy (CP) includes a group of neurological conditions caused by damage to the developing brain, resulting in maladaptive alterations of muscle coordination and movement. Estimates of joint moments and contact forces during locomotion are important to establish the trajectory of disease progression and plan appropriate surgical interventions in children with CP. Joint moments and contact forces can be estimated using electromyogram (EMG)-informed neuromusculoskeletal models, but a reduced number of EMG sensors would facilitate translation of these computational methods to clinics. This study developed and evaluated a muscle synergy-informed neuromusculoskeletal modelling approach using EMG recordings from three to four muscles to estimate joint moments and knee contact forces of children with CP and typically developing (TD) children during walking. Using only three to four experimental EMG sensors attached to a single leg and leveraging an EMG database of walking data of TD children, the synergy-informed approach estimated total knee contact forces comparable to those estimated by EMG-assisted approaches that used 13 EMG sensors (children with CP, n = 3, R2 = 0.95 ± 0.01, RMSE = 0.40 ± 0.14 BW; TD controls, n = 3, R2 = 0.93 ± 0.07, RMSE = 0.19 ± 0.05 BW). The proposed synergy-informed neuromusculoskeletal modelling approach could enable rapid evaluation of joint biomechanics in children with unimpaired and impaired motor control within a clinical environment.

Hip contact forces can be predicted with a neural network using only synthesised key points and electromyography in people with hip osteoarthritis

ObjectiveTo develop and validate a neural network to estimate hip contact forces (HCF), and lower body kinematics and kinetics during walking in individuals with hip osteoarthritis (OA) using synthesised anatomical key points and electromyography. To assess the capability of the neural network to detect directional changes in HCF resulting from prescribed gait modifications. DesignA calibrated electromyography-informed neuromusculoskeletal model was used to compute lower body joint angles, moments, and HCF for 17 participants with mild-to-moderate hip OA. Anatomical key points (e.g., joint centres) were synthesised from marker trajectories and augmented with bias and noise expected from computer vision-based pose estimation systems. Temporal convolutional and long short-term memory neural networks were trained using leave-one-subject-out validation to predict neuromusculoskeletal modelling outputs from the synthesised key points and measured electromyography data from 5 hip-spanning muscles. ResultsHCF was predicted with an average error of 13.4±7.1% of peak force. Joint angles and moments were predicted with an average root-mean-square-error of 5.3 degrees and 0.10 Nm/kg, respectively. The NN could detect changes in peak HCF that occur due to gait modifications with good agreement with neuromusculoskeletal modelling (r2 = 0.72) and a minimum detectable change of 9.5%. ConclusionThe developed neural network predicted HCF and lower body joint angles and moments in individuals with hip OA using noisy synthesised key point locations with acceptable errors. Changes in HCF magnitude due to gait modifications were predicted with high accuracy. These findings have important implications for implementation of load-modification based gait retraining interventions for people with hip OA in a natural environment (i.e., home, clinic).

Neuro-Musculoskeletal Modeling for Online Estimation of Continuous Wrist Movements from Motor Unit Activities.

Decoding movement intentions from motor unit (MU) activities remains an ongoing challenge, which restricts our comprehension of the intricate transition mechanism from microscopic neural drive to macroscopic movements. This study presents an innovative neuro-musculoskeletal (NMS) model driven by MU activities for online estimation of continuous wrist movements. The proposed model employs a physiological and comprehensive utilization of MU firings and waveforms, thus facilitating the localization of MUs to muscle-tendon units (MTU) as well as the computation of MU-specific neural excitation. Subsequently, the MU-specific neural excitation was integrated to form the MTU-specific neural excitation, which were then inputted into a musculoskeletal model to accomplish the joint angle estimation. To assess the effectiveness of this model, high-density surface electromyography and angular data were collected from the forearms of eight subjects during their performance of wrist flexion-extension task. Two pieces of 8×8 electrode arrays and a motion capture system were employed for data acquisition. Following offline model calibration with a global optimization algorithm, online angle estimation results demonstrated a significant superiority of the proposed model over the state-of-the-art NMS models (p < 0.05), yielding the lowest normalized root mean square error ( 0.10 ± 0.02 ) and the highest determination coefficient ( 0.87 ± 0.06 ). This study provides a novel idea for the decoding of joint movements from MU activities. The research findings hold the potential to advance the development of NMS models towards the control of multiple degrees of freedom, with promising applications in the fields of motor control, biomechanics, and neuro-rehabilitation engineering.