Computational models of the neuromuscular system hold the potential to allow us to reach a deeper understanding of neuromuscular function and clinical rehabilitation by complementing experimentation. By serving as a means to distill and explore specific hypotheses, computational models emerge from prior experimental data and motivate future experimental work. Here we review computational tools used to understand neuromuscular function including musculoskeletal modeling, machine learning, control theory, and statistical model analysis. We conclude that these tools, when used in combination, have the potential to further our understanding of neuromuscular function by serving as a rigorous means to test scientific hypotheses in ways that complement and leverage experimental data.

Computationally efficient modeling of complex neuromuscular systems for dynamics and control simulations often requires accurate analytical expressions for moment arms over the entire range of motion. Conventionally, polynomial expressions are regressed from experimental data. But these polynomial regressions can fail to extrapolate, may require large datasets to train, are not robust to noise, and often have numerous free parameters. We present a novel method that simultaneously estimates both the form and parameter values of arbitrary analytical expressions for tendon excursions and moment arms over the entire range of motion from sparse datasets. This symbolic regression method based on genetic programming has been shown to find the appropriate form of mathematical expressions that capture the physics of mechanical systems. We demonstrate this method by applying it to (i) experimental data from a physical tendon-driven robotic system with arbitrarily routed multiarticular tendons and (ii) synthetic data from musculoskeletal models. We show it outperforms polynomial regressions in the amount of training data, ability to extrapolate, robustness to noise, and representation containing fewer parameters – all critical to realistic and efficient computational modeling of complex musculoskeletal systems.

Forces generated by the muscles actuating the fingers are transmitted through a complex network of tendons. Current models of the hand either ignore or simplify the structure of these networks [1]. It has been shown that the deformable nature of these tendinous networks results in a nonlinear transformation of muscle forces [2]. Our long-term objective is to understand how the topology of this network affects the control of finger force and motion. To achieve this, we will use a machine learning approach to evolve models of this network that can best replicate experimental results [3]. Here we present an anatomically realistic solver developed to model mechanical force transmission by a network of tendons in the human fingers. While most existing solvers neglect mechanics of tendon networks, there has been recent work on dynamic simulators accounting for tendon-bone interactions [4]. The solver we present here advances work in this field by being able to simulate mechanics of complex networks wrapped on arbitrarily shaped objects (like bones), and can be effectively used to model isometric force production in complex biomechanical systems. Its speed makes it an ideal simulation engine for the evolutionary algorithms we use to infer complex anatomical structures from sparse experimentation [3].

Estimating tendon excursion-joint angle relationships that define moment arm variations is a critical part of biomechanical modeling. The conventional approach has been to assume a specific mathematical form for these relationships and use experimental data to regress the parameters of these assumed mathematical functions. In contrast, here we propose a novel method that uses symbolic regression to simultaneously determine both the appropriate topology, i.e. the form of the mathematical expression, and the parameter values that best fit the experimental data. We demonstrate this method with synthetic data generated using a known model of the human index finger. Cross validation with realistic noise levels shows that this method can extract the correct form and parameter values for nonlinear tendon excursion-joint angle relationships even in the presence of noise.