Prediction of muscle activity during loaded movements of the upper limb.

Robert Tibold,Andrew J Fuglevand

doi:10.1186/1743-0003-12-6

Robert Tibold, Andrew J Fuglevand

Open Access

https://doi.org/10.1186/1743-0003-12-6

Copy DOI

Abstract

BackgroundAccurate prediction of electromyographic (EMG) signals associated with a variety of motor behaviors could, in theory, serve as activity templates needed to evoke movements in paralyzed individuals using functional electrical stimulation. Such predictions should encompass complex multi-joint movements and include interactions with objects in the environment.MethodsHere we tested the ability of different artificial neural networks (ANNs) to predict EMG activities of 12 arm muscles while human subjects made free movements of the arm or grasped and moved objects of different weights and dimensions. Inputs to the trained ANNs included hand position, hand orientation, and thumb grip force.ResultsThe ability of ANNs to predict EMG was equally as good for tasks involving interactions with external loads as for unloaded movements. The ANN that yielded the best predictions was a feed-forward network consisting of a single hidden layer of 30 neural elements. For this network, the average coefficient of determination (R2 value) between predicted and actual EMG signals across all nine subjects and 12 muscles during movements that involved episodes of moving objects was 0.43.ConclusionThis reasonable accuracy suggests that ANNs could be used to provide an initial estimate of the complex patterns of muscle stimulation needed to produce a wide array of movements, including those involving object interaction, in paralyzed individuals.

Highlights

Accurate prediction of electromyographic (EMG) signals associated with a variety of motor behaviors could, in theory, serve as activity templates needed to evoke movements in paralyzed individuals using functional electrical stimulation
Artificial neural network structures Previously, we demonstrated the applicability of using artificial neural networks (ANN) for predicting EMG patterns from kinematics in the absence of external forces [19]
Here we have shown, as has been demonstrated previously [30,31,32,19], that EMG patterns associated with complex limb movements can be predicted with good fidelity from kinematics using artificial neural networks (ANNs)

Summary

Introduction

Accurate prediction of electromyographic (EMG) signals associated with a variety of motor behaviors could, in theory, serve as activity templates needed to evoke movements in paralyzed individuals using functional electrical stimulation. Such predictions should encompass complex multi-joint movements and include interactions with objects in the environment. Only a few pre-programmed movements are permitted by most existing systems. This limitation is related to two major challenges. Even if a flexible system were developed that could deliver appropriate patterns of muscle stimulation associated with a wide array of movements, the challenge remains as to how a paralyzed individual would provide the command signal needed to specify the desired behavior

Methods

Results

Discussion

Conclusion