A machine learning approach to quantify individual gait responses to ankle exoskeletons.
A machine learning approach to quantify individual gait responses to ankle exoskeletons.
复制标题
一种机器学习方法，用于量化个体对脚踝外骨骼的步态反应。
DOI：
10.1101/2023.01.20.524757
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Steele,KatherineM
中科院分区：
文献类型：
--
作者：
Ebers,MeganR;Rosenberg,MichaelC;Kutz,JNathan;Steele,KatherineM
预测个体对外骨骼的反应并理解需要什么数据来表征反应仍然具有挑战性。具体来说，我们缺乏一个理论框架，能够量化的异质性反应外骨骼干预。我们利用基于神经网络的差异建模框架来量化非残疾成年人被动踝关节外骨骼步态的复杂变化。离散建模旨在解决模型预测和真实世界测量之间的动态不一致。神经网络识别（i）标称步态，（ii）外骨骼（Exo）步态和（iii）它们之间的离散（即，响应）的模型。如果增强（标称+离散）模型捕获外骨骼响应，则其预测应考虑与Exo模型相当的Exo步态数据方差量。离散建模成功地量化了个体的外骨骼响应，而不需要关于生理结构或运动控制的知识：用离散响应模型增强的标称步态模型在Exo步态中占显著更多的方差（运动学的中值R 2（0. 928-0。963)和肌电图（0. 665-0。788），（p< 0. 042））比名义模型（运动学的中位数R 2（0. 863-0。939)和肌电图（0. 516 - 0。664））。然而，需要额外的测量模态和/或改进的分辨率来表征Exo步态，因为由于Exo步态中无法解释的变化，差异可能无法全面捕获响应（运动学的中值R 2（0. 954-0。977)和肌电图（0. 724-0。815））。这些技术可用于加速发现驱动外骨骼反应的个体特异性机制，从而实现个性化康复。
Predicting an individual’s response to an exoskeleton and understanding what data are needed to characterize responses remains challenging. Specifically, we lack a theoretical framework capable of quantifying heterogeneous responses to exoskeleton interventions. We leverage a neural network-based discrepancy modeling framework to quantify complex changes in gait in response to passive ankle exoskeletons in nondisabled adults. Discrepancy modeling aims to resolve dynamical inconsistencies between model predictions and real-world measurements. Neural networks identified models of (i) Nominal gait,(ii) Exoskeleton (Exo) gait, and (iii) the Discrepancy (ie, response) between them. If an Augmented (Nominal+ Discrepancy) model captured exoskeleton responses, its predictions should account for comparable amounts of variance in Exo gait data as the Exo model. Discrepancy modeling successfully quantified individuals’ exoskeleton responses without requiring knowledge about physiological structure or motor control: a model of Nominal gait augmented with a Discrepancy model of response accounted for significantly more variance in Exo gait (median R 2 for kinematics (0. 928− 0. 963) and electromyography (0. 665− 0. 788),(p< 0. 042)) than the Nominal model (median R 2 for kinematics (0. 863− 0. 939) and electromyography (0. 516− 0. 664)). However, additional measurement modalities and/or improved resolution are needed to characterize Exo gait, as the discrepancy may not comprehensively capture response due to unexplained variance in Exo gait (median R 2 for kinematics (0. 954− 0. 977) and electromyography (0. 724− 0. 815)). These techniques can be used to accelerate the discovery of individual-specific mechanisms driving exoskeleton responses, thus enabling personalized rehabilitation.