Discovering individual-specific gait signatures from data-driven models of neuromechanical dynamics.
Discovering individual-specific gait signatures from data-driven models of neuromechanical dynamics.
复制标题
DOI：
10.1371/journal.pcbi.1011556
复制
发表时间：
2023-10
影响因子：
4.3
通讯作者：
中科院分区：
文献类型：
--
作者：
运动是高度非线性的神经和生物力学动力学相互作用的结果。因此，基于对潜在神经机械系统的详细建模，理解跨行为条件和个体的步态动力学被证明是困难的。在这里，我们开发了一种数据驱动和生成式建模方法，概括了步态行为的动力学特征，以便能够更全面和可解释地描述和比较步态动力学。具体地说，多个个体的步态动力学通过一个动力学模型来预测，该模型定义了一个共同的低维潜在空间来比较群体和个体的差异。我们发现，健康老年人和中风幸存者在跑步机步行过程中的高度个性化动力学--即步态特征--在步态速度方面是保守的。步态特征进一步揭示了步态动力学的个体差异，即使在具有类似功能缺陷的个体中也是如此。此外，步态特征的组成部分可以被生物力学解释和操纵，以揭示它们与观察到的时空关节协调模式的关系。最后，步态动力学模型可以预测基于初始静态姿势的关节协调的时间演化。因此，我们的步态特征框架提供了一种可概括的整体方法，用于描述和预测循环的、动态的运动行为，这些行为可以跨物种、病理和步态扰动进行概括。在这份手稿中，我们介绍了一个新颖的，基于机器学习的框架，用于量化、表征和修改驱动独特步态模式的潜在神经机械动力学。评估运动的标准方法通常侧重于提取离散步态变量，而忽略了步态过程中出现的复杂的肢体间和关节间的时空依赖关系。流行的生理真实感建模方法编码了这些时空依赖关系，但太复杂了，无法表征驱动独特步态模式或紊乱的因素中的个体差异。为了避免这些建模的复杂性，我们开发了一个步态的现象学模型，该模型能够更全面和更可解释地描述步态，编码这些由关节神经和生物力学约束产生的人类关节角度之间的复杂时空依赖关系。我们创造的“步态特征”框架为理解运动的神经力学提供了一条途径。这一框架对临床研究人员或对动物运动或其他周期性运动感兴趣的生物机械师开出个性化治疗处方具有潜在的实用价值，这些运动涉及不同的病理、神经扰动和/或条件。
Locomotion results from the interactions of highly nonlinear neural and biomechanical dynamics. Accordingly, understanding gait dynamics across behavioral conditions and individuals based on detailed modeling of the underlying neuromechanical system has proven difficult. Here, we develop a data-driven and generative modeling approach that recapitulates the dynamical features of gait behaviors to enable more holistic and interpretable characterizations and comparisons of gait dynamics. Specifically, gait dynamics of multiple individuals are predicted by a dynamical model that defines a common, low-dimensional, latent space to compare group and individual differences. We find that highly individualized dynamics–i.e., gait signatures–for healthy older adults and stroke survivors during treadmill walking are conserved across gait speed. Gait signatures further reveal individual differences in gait dynamics, even in individuals with similar functional deficits. Moreover, components of gait signatures can be biomechanically interpreted and manipulated to reveal their relationships to observed spatiotemporal joint coordination patterns. Lastly, the gait dynamics model can predict the time evolution of joint coordination based on an initial static posture. Our gait signatures framework thus provides a generalizable, holistic method for characterizing and predicting cyclic, dynamical motor behavior that may generalize across species, pathologies, and gait perturbations. In this manuscript, we introduce a novel, machine learning-based framework for quantifying, characterizing, and modifying the underlying neuromechanical dynamics that drive unique gait patterns. Standard methods for evaluating movement typically focus on extracting discrete gait variables ignoring the complex inter-limb and inter-joint spatiotemporal dependencies that occur during gait. Popular physiologically realistic modeling approaches encode these spatiotemporal dependencies but are too complex to characterize individual differences in the factors driving unique gait patterns or disorders. To circumvent these modeling complications, we develop a phenomenological model of gait that enables more holistic and interpretable characterizations of gait, encoding these complex spatiotemporal dependencies between humans’ joint angles arising from joint neural and biomechanical constraints. Our coined ‘gait signature’ framework provides a path towards understanding the neuromechanics of locomotion. This framework has potential utility for clinical researchers prescribing individualized therapies for pathologies or biomechanists interested in animal locomotion or other periodic movements assessed across different pathologies, neural perturbations, and or conditions.
登录
查看更多内容
DOI：
10.1016/j.jstrokecerebrovasdis.2020.105174
发表时间：
2020-10-01
影响因子：
2.5
作者：
D'souza, Jennifer;Natarajan, Manikandan;Kumaran, Senthil D.
通讯作者：
Kumaran, Senthil D.
影响因子：
4.2
作者：
Bowden, Mark G.;Balasubramanian, Chitralakshmi K.;Kautz, Steven A.
通讯作者：
Kautz, Steven A.
影响因子：
4.2
作者：
Awad LN;Palmer JA;Pohlig RT;Binder-Macleod SA;Reisman DS
通讯作者：
Reisman DS
影响因子：
19.6
作者：
Ahamed, Tosif;Costa, Antonio C.;Stephens, Greg J.
通讯作者：
Stephens, Greg J.
影响因子：
2.4
作者：
Correa, Tomas A.;Baker, Richard;Pandy, Marcus G.
通讯作者：
Pandy, Marcus G.