Neural network estimation of balance control during locomotion
Introduction
As humans age, gait patterns are adjusted to accommodate for reduced function in the balance control system and a general reduction in skeletal muscle strength (Grimby and Saltin, 1983; Fiatarone and Evans, 1993). The temporal-distance (T-D) measures of gait have been widely used in evaluation of overall function and determination of gait dysfunction in the elderly (Heitmann et al., 1989; Ferrandez et al., 1990; Elble et al., 1991; Leiper and Craik, 1991; Judge et al., 1996; Maki, 1997; Menz et al., 2003). These studies showed that while T-D measures of gait do provide an overall impression of walking performance, there is substantial inter-subject variability in the measures. Such variability may contribute to a lack of power in accurately predicting the risk of falling in the elderly. The effect of aging on muscle activation and strength in the elderly has been shown to result in higher electromyographic (EMG) signal amplitudes during gait (Finley et al., 1969; Shiavi, 1985). However, the resulting force production in aged subjects is highly variable (Galganski et al., 1993; Grabiner and Enoka, 1995). None of the previous studies have examined the effect of T-D parameters and EMG activity on control of whole body stability.
Control of whole body stability has been studied in recent years by analyzing motion of the whole-body center of mass (COM), the patterns of which were reported to be quite consistent during locomotion (Jian et al., 1993; MacKinnon and Winter, 1993; Prince et al., 1994; Winter, 1995). More recent studies have demonstrated an ability to distinguish elderly individuals with balance impairment from their age-matched healthy peers, using measures of medio-lateral (M-L) COM motion during obstacle crossing (Chou et al., 2003; Hahn and Chou, 2003). Accurate estimation of the whole-body COM requires three-dimensional reconstruction of a multiple segment biomechanical model. This technical requirement alone may restrict broad application of assessing dynamic instability.
In many clinical settings, gait analysis can be performed with accuracy in measures of gait velocity, stride length, stride time and step width. Additionally, with many brands of inexpensive hardware/software currently available, the relative magnitude of muscle activations may be measured with surface EMG during locomotion and other activities of daily living. Using T-D and EMG data to predict dynamic stability would be advantageous by reducing the necessity for a multiple camera motion analysis system (more costly), and reducing the time commitment of data-processing and analysis. A model is therefore needed which would allow accurate description of whole-body balance control, given simple measures of gait such as EMG and T-D parameters.
One approach for mapping interactions between gait measurements and balance control is to construct a nonlinear model using an artificial neural network (ANN). Biological nervous systems are capable of learning by adjustment of the synaptic connections between individual neurons. The ANN is modeled in a similar fashion, allowing the network to be trained by exposure to a set of input data where the output values are known. Weights of the ANN interconnections are iteratively adjusted to attempt correction of the final processed output to match that of known values. Once a network has been trained to a satisfactory level, the knowledge gained by this learning process is stored in the connection weights (synapses), allowing a trained network to solve new problems similar to the task it was trained on. The primary advantages of ANNs in solving real-world classification problems are (1) their resilience in the face of noise and variability within a dataset, and (2) the ability to map relationships between variables that would not otherwise be noticeable. They have been used with high success in problems that are either too complex for conventional methods or are of an exploratory nature (Chau, 2001).
Applications of ANN models in musculoskeletal biomechanics have dealt primarily with joint angles and joint moment estimations in gait simulation (Sepulveda et al., 1993) and estimation of muscle recruitment in static conditions (Nussbaum et al., 1995). Sepulveda and colleagues used traditional back-propagation algorithms to successfully map the relationship between EMG and joint angles, and between EMG and joint moments during gait. Nussbaum et al. also reported success using a back-propagation algorithm to map lumbar muscle recruitment during moderate static exertions. Koike and Kawato (1995) used an architecturally complex ANN model to estimate isometric joint torques and trajectory from surface EMG in upper limb motions. More recent efforts by Luh et al. (1999) showed promising results with use of a simple, three-layer ANN, using an adaptive learning rate back-propagation algorithm in the determination of elbow joint torque from EMG activity.
Although ANN modeling has been used in studies of human locomotion (Holzreiter and Kohle, 1993; Sepulveda et al., 1993; Lafuente et al., 1998; Prentice et al., 1998; Savelberg and de Lange, 1999; Su and Wu, 2000; Prentice et al., 2001; Wu et al., 2001), no previously published work has addressed the ability of such models to map the interaction between basic gait measurements and descriptions of dynamic balance control. The purpose of this study was to demonstrate the effectiveness of an ANN model in mapping gait measurements (normalized lower extremity EMG signals and basic T-D parameters) onto whole body measures of dynamic stability (motion of the COM). It was hypothesized that a relatively simple ANN architecture would be capable of accurately mapping interactions between these variables.
Section snippets
Methods
Input/output data of the ANN model were obtained from a database of previously collected subjects (Koshida, 2002; Chou et al., 2003; Hahn and Chou (2003), Hahn and Chou (2004)). The subject pool (n=40) consisted of 11 healthy young adults, 19 healthy elderly adults, and 10 elderly adults with complaints of imbalance (Table 1). Inclusion criteria for the young and healthy elderly samples required no histories of significant head trauma, neurological disease (e.g., Parkinson's, post-polio
Results
Comparisons between young and healthy elderly adults showed no significant differences in the measures of M-L COM displacement or peak M-L velocity (Fig. 2). Elderly adults with balance impairment allowed significantly greater M-L displacement and peak velocity, compared to both the young (p<0.001 and 0.014, respectively), and the healthy elderly (p=0.002 and 0.013, respectively). Empirical results of the COM variables were then compiled as target values for the ANN model output.
The model
Discussion
This study sought to demonstrate the ability of an ANN model to accurately map muscular activation levels and T-D parameters onto whole body measures of dynamic stability during gait. Results supported the hypothesis that a relatively simple ANN model architecture is adequate for estimating dynamic stability from the basic measures of normalized EMG activation and T-D parameters.
Given the relatively small size of the sample data set, the model performed reasonably well, with average correlation
Acknowledgements
This study was supported by the National Institutes of Health (AG 022204-01; HD 042039-01A1), the Oregon Medical Research Foundation, and the International Society of Biomechanics Dissertation Matching Grant. We are grateful to Dr. Kai-Nan An for his critical reviews of the project design and manuscript preparation.
References (40)
A review of analytical techniques for gait data. Part 2neural network and wavelet methods
Gait and Posture
(2001)- et al.
Motion of the whole body's center of mass when stepping over obstacles of different heights
Gait and Posture
(2001) - et al.
Medio-lateral motion of the center of mass during obstacle crossing distinguishes elderly individuals with imbalance
Gait and Posture
(2003) - et al.
Stride-dependent changes in gait of older people
Journal of Neurology
(1991) - et al.
Slowness in elderly gait
Experimental Aging Research
(1990) - et al.
The etiology and reversibility of muscle dysfunction in the aged
Journal of Gerontology
(1993) - et al.
Locomotion patterns in elderly women
Archives of Physical Medicine and Rehabilitation
(1969) - et al.
Reduced control of motor output in a human hand muscle of elderly subjects during submaximal contractions
Journal of Neurophysiology
(1993) - et al.
Changes in movement capabilities with aging
- et al.
Mini-reviewthe aging muscle
Clinics in Physiology
(1983)
Can motion of individual body segments identify dynamic instability in the elderly?
Clinical Biomechanics
Age-related reduction in sagittal plane center of mass motion during obstacle crossing
Journal of Biomechanics
Balance performance and step width in non-institutionalized elderly female fallers and nonfallers
Physical Therapy
Assessment of gait patterns using neural networks
Journal of Biomechanics
Trajectory of the body COG and COP during initiation and termination of gait
Gait and Posture
Step length reductions in advanced agethe role of ankle and hip kinetics
Journal of Gerontology
Estimation of dynamic joint torques and trajectory formation from surface electromyography signals using a neural network model
Biological Cybernetics
Is base of support greater in unsteady gait?
Physical Therapy
Cited by (32)
Combined inverse-forward artificial neural networks for fast and accurate estimation of the diffusion coefficients of cartilage based on multi-physics models
2016, Journal of BiomechanicsCitation Excerpt :Artificial neural networks (ANNs) are considered as intelligent tools which can be trained using input data and output target to efficiently fulfill pattern recognition (Arbabi et al., 2015). In biomechanics, ANNs have been applied to problems such as bone remodeling, indentation tests as well as sport/gait mechanics (Campoli et al., 2012; Darling and Guilak, 2008; Hahn et al., 2005; Oh et al., 2013; Zadpoor et al., 2012). Previously, we described a finite-bath finite element model and derived the diffusion coefficients of a neutral solute across cartilage zones using direct scanning of the parameter space as the optimization algorithm (Arbabi et al., 2015).
Comparison among probabilistic neural network, support vector machine and logistic regression for evaluating the effect of subthalamic stimulation in Parkinson disease on ground reaction force during gait
2010, Journal of BiomechanicsCitation Excerpt :Studies have compared the predictive ability of LR and ANN (Dreiseitl and Ohno-Machado, 2002; Song et al., 2005). ANN modeling has been used in gait analysis focusing on pattern recognition (Hahn et al., 2005), as well as for classifying normal and pathological patterns (Lafuente et al., 1997; Su and Wu, 2000). SVM has recently been used for automated identification of gait pathologies (Begg et al., 2005; Lai et al., 2009).
From neuromuscular activation to end-point locomotion: An artificial neural network-based technique for neural prostheses
2009, Journal of BiomechanicsCitation Excerpt :As independent walking is essential for people with SB to obtain quality of life, we propose to improve their locomotion by designing the next-generation neural prostheses with closed-loop control that uses neuromuscular activity as intrinsic feedback (Fig. 1). Artificial neural network (ANN) is one of the most established machine-learning techniques to synthesize a self-adaptable system (Becker and Hinton, 1992; Sepulveda et al., 1993; Principe et al., 1994; Cheron et al., 2003; Popovic et al., 2003; Lin et al., 2004; Hahn et al., 2005; Chang et al., 2008; Krogh, 2008). Its ability to “learn” to recognize complex, unforeseen patterns has been proven effective in the domain of cortical-related hand trajectory prediction (Wessberg et al., 2000) and autonomous robotic motion planning (Yang and Meng, 2000).
Gait classification in children with cerebral palsy by Bayesian approach
2009, Pattern RecognitionThe effect of total knee replacement surgery on gait stability
2008, Gait and PostureCitation Excerpt :While improvement of the TKR level walking spatio-temporal variables may indicate enhanced locomotor ability following surgery, 6 months may be insufficient post-surgical recovery time to allow for resolution of symptoms and attainment of control gait velocity values [13]. During level and obstructed walking, frontal plane COM–COP measures have been used as functional indicators that may distinguish imbalanced patients from healthy controls [20–22]. The results of this study indicate that, prior to and following surgery, TKRs and CONs walked and crossed over an obstacle similarly, suggesting that TKR subjects have the ability to appropriately manage the COM within the BOS during locomotion.
A neural network model for estimation of net joint moments during normal gait
2008, Journal of Musculoskeletal Research
- 1
Current address: Department of Health and Human Development, Montana State University, Bozeman, Montana 59717.