Predicting Neuromuscular Engagement to Improve Gait Training With a Robotic Ankle Exoskeleton
Predicting Neuromuscular Engagement to Improve Gait Training With a Robotic Ankle Exoskeleton
复制标题
使用机器人踝外骨骼预测神经肌肉参与以改善步态训练
DOI：
10.1109/lra.2023.3291919
复制
发表时间：
2023
影响因子：
5.2
通讯作者：
Lerner, Zachary F.
中科院分区：
文献类型：
--
作者：
Harshe, Karl;Williams, Jack R.;Hocking, Toby D.;Lerner, Zachary F.
机器人康复干预的临床疗效取决于患者适当的神经肌肉招募。本研究的第一个目的是评估使用监督机器学习技术来预测脑瘫（CP）患者在踝关节外骨骼阻力行走期间踝跖屈肌的神经肌肉募集。本研究的第二个目标是利用足底屈肌募集的预测模型来设计旨在改善（即，增加）当有阻力行走时的用户参与。首先，我们开发并训练了多层感知器（MLP），这是一种人工神经网络（ANN），利用专门从外骨骼的板载传感器中提取的特征，并在从肌电图测量中预测肌肉招募方面平均表现出85-87%的准确性。接下来，我们的参与者完成了步态训练课程，同时从在线MLP接收他们的个性化实时平面屈肌募集预测的视听生物反馈。我们发现，与单独的阻力相比，将生物反馈添加到阻力中使跖屈肌募集增加了24 ± 16%。这项研究强调了在线机器学习框架在提高机器人康复系统在临床人群中的有效性和交付方面的潜力。
The clinical efficacy of robotic rehabilitation interventions hinges on appropriate neuromuscular recruitment from the patient. The first purpose of this study was to evaluate the use of supervised machine learning techniques to predict neuromuscular recruitment of the ankle plantar flexors during walking with ankle exoskeleton resistance in individuals with cerebral palsy (CP). The second goal of this study was to utilize the predictive models of plantar flexor recruitment in the design of a personalized biofeedback framework intended to improve (i.e., increase) user engagement when walking with resistance. First, we developed and trained multilayer perceptrons (MLPs), a type of artificial neural network (ANN), utilizing features extracted exclusively from the exoskeleton's onboard sensors, and demonstrated 85–87% accuracy, on average, in predicting muscle recruitment from electromyography measurements. Next, our participants completed a gait training session while receiving audio-visual biofeedback of their personalized real-time planar flexor recruitment predictions from the online MLP. We found that adding biofeedback to resistance elevated plantar flexor recruitment by 24 ± 16% compared to resistance alone. This study highlights the potential for online machine learning frameworks to improve the effectiveness and delivery of robotic rehabilitation systems in clinical populations.
登录
查看更多内容
影响因子：
2.4
作者：
L. V. van Gelder;A. Booth;Ingrid G. L. van de Port;A. Buizer;J. Harlaar;M. M. van der Krogt
通讯作者：
M. M. van der Krogt
小腿三头肌肌电图对脑瘫儿童步态的反馈：一项对照研究。
影响因子：
4.3
作者：
G. Robert Colborne;F.Virginia Wright;Stephen Naumann
通讯作者：
Stephen Naumann
在步态分析中使用无量纲缩放策略。
影响因子：
2.1
作者：
C. Carty;M. Bennett
通讯作者：
M. Bennett
影响因子：
2.8
作者：
Baram, Yoram;Lenger, Ruben
通讯作者：
Lenger, Ruben
影响因子：
2.2
作者：
Dursun, E;Dursun, N;Alican, D
通讯作者：
Alican, D