Solving musculoskeletal biomechanics with machine learning

Predicting joint loading in Asian overweight and obese females with flexible flatfoot: a regression analysis of anthropometric parameters and gait dynamics

Current methods for obtaining accurate joint loading data lack simplicity, efficiency, and cost-effectiveness. This study aims to generate joint loading prediction models using anthropometric parameters and walking speed in overweight or obese females with flexible flatfoot. Sixteen participants' motion capture data from walking trails and anthropometric parameters were collected. The lower limb joint contact forces and the walking speed were calculated via a musculoskeletal model. Regression analysis was used to generate the prediction model. The second peak of knee joint contact force revealed a strong negative correlation with hip circumference and a weak positive correlation with age (p < 0.001 and adjusted R2 = 0.720). The peak ankle joint contact force exhibited a strong positive correlation with walking speed while strong negative correlations with waist circumference and lower limb length (p < 0.001 and adjusted R2 = 0.782). The first peak of vertical GRF displayed a medium negative correlation with walking speed (p < 0.001 and adjusted R2 = 0.750). Anthropometric parameters and walking speed are effective predictors of joint loading. This rapid, low-cost estimation method can be applied to areas such as flexible flatfoot that require assessment of joint stress, thereby saving costs and time.

Estimation of the equivalent external force using a musculoskeletal model with muscle coactivation

The present work introduces a novel method to determine the force vector that a subject must exert at the end of a limb in order to achieve the desired muscle force, taking into account muscle coactivation. The obtained force vector is referred to as the equivalent external force, as it represents the exerted force at the end-effector needed to provoke a desired muscle force. By using a musculoskeletal model of the lower limb and applying the Karush-Kuhn-Tucker conditions, a precise solution has been achieved to calculate the equivalent external force at the foot for the desired muscle force. The method has been tested with a four-degree-of-freedom robot, generating optimal activation trajectories for the vasti and confirming that the desired force level is achieved. The results validate the effectiveness of the proposed method and highlight its potential applications in both medical rehabilitation and sports training. This significant advancement in the field of biomechanics would provide a valuable tool for health and sports professionals, improving training and rehabilitation strategies.

Damage explains function in spiking neural networks representing central pattern generator

Objective.Complex biological systems have evolved to control movement dynamics despite noisy and unpredictable inputs and processing delays that necessitate forward predictions. The staple example in vertebrates is the locomotor control emerging from interactions between multiple systems-from passive dynamics of inverted pendulum governing body motion to coupled neural oscillators that integrate predictive forward and sensory feedback signals. These neural dynamic computations are expressed in the rhythmogenic spinal network known as the central pattern generator (CPG). While a system of ordinary differential equations constituting a rate model can accurately reproduce flexor-extensor modulation patterns aligned with experimental data from cats, the equivalent computations performed by thousands of neurons in vertebrates or even in silicon are poorly understood.Approach.We developed a locomotor CPG model expressed as a spiking neural network (SNN) to test how damage affects the distributed computations of a well-defined neural circuit with known dynamics. The SNN-CPG model accurately recreated the input-output relationship of the rate model, describing the modulation of gait phase characteristics.Main Results.The degradation of distributed computation within elements of the SNN-CPG model was further analyzed with progressive simulated lesions. Circuits trained to express flexor or extensor function, with otherwise identical structural organization, were differently affected by lesions mimicking results in experimental observations. The increasing external drive was shown to overcome structural damage and restore function after progressive lesions.Significance.These model results provide theoretical insights into the network dynamics of locomotor control and introduce the concept of degraded computations with applications for restorative technologies.

Real-Time Calibration-Free Musculotendon Kinematics for Neuromusculoskeletal Models

Neuromusculoskeletal (NMS) models enable non-invasive estimation of clinically important internal biomechanics. A critical part of NMS modelling is the estimation of musculotendon kinematics, which comprise musculotendon unit lengths, moment arms, and lines of action. Musculotendon kinematics, which are partially dependent on joint angles, define the non-linear mapping of muscle forces to joint moments and contact forces. Currently, real-time computation of musculotendon kinematics requires creation of a per-individual surrogate model. The computational speed and accuracy of these surrogates degrade with increasing number of coordinates. We developed a feed-forward neural network that completely encodes musculotendon kinematics of a target model across a wide anthropometric range, enabling accurate real-time estimates of musculotendon kinematics without need for a priori creation of a per-individual surrogate model. Compared to reference, the neural network had median normalized errors ~0.1% for musculotendon lengths, <0.4% for moment arms, and <0.10° for line of action orientations. The neural network was employed within an electromyogram-informed NMS model to calculate hip contact forces, demonstrating little difference (normalized root mean square error 1.23±0.15 %) compared to using reference musculotendon kinematics. Finally, execution time was <0.04 ms per frame and constant for increasing number of model coordinates. Our approach to musculoskeletal kinematics may facilitate deployment of complex real-time NMS modelling in computer vision or wearable sensors applications to realize biomechanics monitoring, rehabilitation, and disease management outside the research laboratory.

Neural Networks-Based Approach to Solve Inverse Kinematics Problems for Medical Applications

GOAL

Motion capture is used for recording complex human movements that is increasingly applied in medicine. We describe a novel algorithm of combining a machine learning approach with biomechanics to enable fast and robust analysis of motion capture data to obtain joint angles.

METHODS

A multilayer perceptron and a recurrent neural network were compared in their capacity to estimate the joint angles of the human arm. The networks were pre-trained using data from a kinematic model of the human arm. The data comprised movements of three degrees of freedom, such as wrist flexion/extension, wrist ulnar/radial deviation, and hand pronation/supination.

RESULTS

A recurrent neural network model with long short-term memory architecture can solve the inverse kinematics problem for three rotational degrees of freedom with the least error; it performed faster than real time. The predictions were robust against noise.

CONCLUSIONS

This shows that it is feasible to rely on pre-trained neural networks for real-time calculation of joint angles.

Pole balancing on the fingertip: model-motivated machine learning forecasting of falls

Introduction: There is increasing interest in developing mathematical and computational models to forecast adverse events in physiological systems. Examples include falls, the onset of fatal cardiac arrhythmias, and adverse surgical outcomes. However, the dynamics of physiological systems are known to be exceedingly complex and perhaps even chaotic. Since no model can be perfect, it becomes important to understand how forecasting can be improved, especially when training data is limited. An adverse event that can be readily studied in the laboratory is the occurrence of stick falls when humans attempt to balance a stick on their fingertips. Over the last 20 years, this task has been extensively investigated experimentally, and presently detailed mathematical models are available. Methods: Here we use a long short-term memory (LTSM) deep learning network to forecast stick falls. We train this model to forecast stick falls in three ways: 1) using only data generated by the mathematical model (synthetic data), 2) using only stick balancing recordings of stick falls measured using high-speed motion capture measurements (human data), and 3) using transfer learning which combines a model trained using synthetic data plus a small amount of human balancing data. Results: We observe that the LTSM model is much more successful in forecasting a fall using synthetic data than it is in forecasting falls for models trained with limited available human data. However, with transfer learning, i.e., the LTSM model pre-trained with synthetic data and re-trained with a small amount of real human balancing data, the ability to forecast impending falls in human data is vastly improved. Indeed, it becomes possible to correctly forecast 60%-70% of real human stick falls up to 2.35 s in advance. Conclusion: These observations support the use of model-generated data and transfer learning techniques to improve the ability of computational models to forecast adverse physiological events.

Glenohumeral joint force prediction with deep learning

Deep learning models (DLM) are efficient replacements for computationally intensive optimization techniques. Musculoskeletal models (MSM) typically involve resource-intensive optimization processes for determining joint and muscle forces. Consequently, DLM could predict MSM results and reduce computational costs. Within the total shoulder arthroplasty (TSA) domain, the glenohumeral joint force represents a critical MSM outcome as it can influence joint function, joint stability, and implant durability. Here, we aimed to employ deep learning techniques to predict both the magnitude and direction of the glenohumeral joint force. To achieve this, 959 virtual subjects were generated using the Markov-Chain Monte-Carlo method, providing patient-specific parameters from an existing clinical registry. A DLM was constructed to predict the glenohumeral joint force components within the scapula coordinate system for the generated subjects with a coefficient of determination of 0.97, 0.98, and 0.98 for the three components of the glenohumeral joint force. The corresponding mean absolute errors were 11.1, 12.2, and 15.0 N, which were about 2% of the maximum glenohumeral joint force. In conclusion, DLM maintains a comparable level of reliability in glenohumeral joint force estimation with MSM, while drastically reducing the computational costs.

Artificial physics engine for real-time inverse dynamics of arm and hand movement

Simulating human body dynamics requires detailed and accurate mathematical models. When solved inversely, these models provide a comprehensive description of force generation that considers subject morphology and can be applied to control real-time assistive technology, for example, orthosis or muscle/nerve stimulation. Yet, model complexity hinders the speed of its computations and may require approximations as a mitigation strategy. Here, we use machine learning algorithms to provide a method for accurate physics simulations and subject-specific parameterization. Several types of artificial neural networks (ANNs) with varied architecture were tasked to generate the inverse dynamic transformation of realistic arm and hand movement (23 degrees of freedom). Using a physical model, we generated representative limb movements with bell-shaped end-point velocity trajectories within the physiological workspace. This dataset was used to develop ANN transformations with low torque errors (less than 0.1 Nm). Multiple ANN implementations using kinematic sequences solved accurately and robustly the high-dimensional kinematic Jacobian and inverse dynamics of arm and hand. These results provide further support for the use of ANN architectures that use temporal trajectories of time-delayed values to make accurate predictions of limb dynamics.

Does joint impedance improve dynamic leg simulations with explicit and implicit solvers?

The nervous system predicts and executes complex motion of body segments actuated by the coordinated action of muscles. When a stroke or other traumatic injury disrupts neural processing, the impeded behavior has not only kinematic but also kinetic attributes that require interpretation. Biomechanical models could allow medical specialists to observe these dynamic variables and instantaneously diagnose mobility issues that may otherwise remain unnoticed. However, the real-time and subject-specific dynamic computations necessitate the optimization these simulations. In this study, we explored the effects of intrinsic viscoelasticity, choice of numerical integration method, and decrease in sampling frequency on the accuracy and stability of the simulation. The bipedal model with 17 rotational degrees of freedom (DOF)-describing hip, knee, ankle, and standing foot contact-was instrumented with viscoelastic elements with a resting length in the middle of the DOF range of motion. The accumulation of numerical errors was evaluated in dynamic simulations using swing-phase experimental kinematics. The relationship between viscoelasticity, sampling rates, and the integrator type was evaluated. The optimal selection of these three factors resulted in an accurate reconstruction of joint kinematics (err < 1%) and kinetics (err < 5%) with increased simulation time steps. Notably, joint viscoelasticity reduced the integration errors of explicit methods and had minimal to no additional benefit for implicit methods. Gained insights have the potential to improve diagnostic tools and accurize real-time feedback simulations used in the functional recovery of neuromuscular diseases and intuitive control of modern prosthetic solutions.

Modern three-dimensional digital methods for studying locomotor biomechanics in tetrapods

Here, we review the modern interface of three-dimensional (3D) empirical (e.g. motion capture) and theoretical (e.g. modelling and simulation) approaches to the study of terrestrial locomotion using appendages in tetrapod vertebrates. These tools span a spectrum from more empirical approaches such as XROMM, to potentially more intermediate approaches such as finite element analysis, to more theoretical approaches such as dynamic musculoskeletal simulations or conceptual models. These methods have much in common beyond the importance of 3D digital technologies, and are powerfully synergistic when integrated, opening a wide range of hypotheses that can be tested. We discuss the pitfalls and challenges of these 3D methods, leading to consideration of the problems and potential in their current and future usage. The tools (hardware and software) and approaches (e.g. methods for using hardware and software) in the 3D analysis of tetrapod locomotion have matured to the point where now we can use this integration to answer questions we could never have tackled 20 years ago, and apply insights gleaned from them to other fields.

Does joint impedance improve dynamic leg simulations with explicit and implicit solvers?

The nervous system predicts and executes complex motion of body segments actuated by the coordinated action of muscles. When a stroke or other traumatic injury disrupts neural processing, the impeded behavior has not only kinematic but also kinetic attributes that require interpretation. Biomechanical models could allow medical specialists to observe these dynamic variables and instantaneously diagnose mobility issues that may otherwise remain unnoticed. However, the real-time and subject-specific dynamic computations necessitate the optimization these simulations. In this study, we explored the effects of intrinsic viscoelasticity, choice of numerical integration method, and decrease in sampling frequency on the accuracy and stability of the simulation. The bipedal model with 17 rotational degrees of freedom (DOF)-describing hip, knee, ankle, and standing foot contact-was instrumented with viscoelastic elements with a resting length in the middle of the DOF range of motion. The accumulation of numerical errors was evaluated in dynamic simulations using swing-phase experimental kinematics. The relationship between viscoelasticity, sampling rates, and the integrator type was evaluated. The optimal selection of these three factors resulted in an accurate reconstruction of joint kinematics (err < 1%) and kinetics (err < 5%) with increased simulation time steps. Notably, joint viscoelasticity reduced the integration errors of explicit methods and had minimal to no additional benefit for implicit methods . Gained insights have the potential to improve diagnostic tools and accurize real-time feedback simulations used in the functional recovery of neuromuscular diseases and intuitive control of modern prosthetic solutions.

Evaluation of feature projection techniques in object grasp classification using electromyogram signals from different limb positions

A myoelectric prosthesis is manipulated using electromyogram (EMG) signals from the existing muscles for performing the activities of daily living. A feature vector that is formed by concatenating data from many EMG channels may result in a high dimensional space, which may cause prolonged computation time, redundancy, and irrelevant information. We evaluated feature projection techniques, namely principal component analysis (PCA), linear discriminant analysis (LDA), t-Distributed Stochastic Neighbor Embedding (t-SNE), and spectral regression extreme learning machine (SRELM), applied to object grasp classification. These represent feature projections that are combinations of either linear or nonlinear, and supervised or unsupervised types. All pairs of the four types of feature projection with seven types of classifiers were evaluated, with data from six EMG channels and an IMU sensors for nine upper limb positions in the transverse plane. The results showed that SRELM outperformed LDA with supervised feature projections, and t-SNE was superior to PCA with unsupervised feature projections. The classification errors from SRELM and t-SNE paired with the seven classifiers were from 1.50% to 2.65% and from 1.27% to 17.15%, respectively. A one-way ANOVA test revealed no statistically significant difference by classifier type when using the SRELM projection, which is a nonlinear supervised feature projection (p = 0.334). On the other hand, we have to carefully select an appropriate classifier for use with t-SNE, which is a nonlinear unsupervised feature projection. We achieved the lowest classification error 1.27% using t-SNE paired with a k-nearest neighbors classifier. For SRELM, the lowest 1.50% classification error was obtained when paired with a neural network classifier.