Decoding of Ankle Joint Movements in Stroke Patients Using Surface Electromyography

Abstract

Stroke is a cerebrovascular disease (CVD), which results in hemiplegia, paralysis, or death. Conventionally, a stroke patient requires prolonged sessions with physical therapists for the recovery of motor function. Various home-based rehabilitative devices are also available for upper limbs and require minimal or no assistance from a physiotherapist. However, there is no clinically proven device available for functional recovery of a lower limb. In this study, we explored the potential use of surface electromyography (sEMG) as a controlling mechanism for the development of a home-based lower limb rehabilitative device for stroke patients. In this experiment, three channels of sEMG were used to record data from 11 stroke patients while performing ankle joint movements. The movements were then decoded from the sEMG data and their correlation with the level of motor impairment was investigated. The impairment level was quantified using the Fugl-Meyer Assessment (FMA) scale. During the analysis, Hudgins time-domain features were extracted and classified using linear discriminant analysis (LDA) and artificial neural network (ANN). On average, 63.86% ± 4.3% and 67.1% ± 7.9% of the movements were accurately classified in an offline analysis by LDA and ANN, respectively. We found that in both classifiers, some motions outperformed others (p < 0.001 for LDA and p = 0.014 for ANN). The Spearman correlation (ρ) was calculated between the FMA scores and classification accuracies. The results indicate that there is a moderately positive correlation (ρ = 0.75 for LDA and ρ = 0.55 for ANN) between the two of them. The findings of this study suggest that a home-based EMG system can be developed to provide customized therapy for the improvement of functional lower limb motion in stroke patients.

Keywords: ankle joint movements; home-based physical therapy; lower limb functional recovery; pattern recognition (PR); stroke rehabilitation; surface electromyography (sEMG).

Figure 1

An illustration of the electromyography (EMG) data recording setup while the patient was performing movements.

Figure 2

Rectified and bandpass-filtered EMG signal (only for understanding and visualization) of all motion classes and all channels separately for subject 3.

Figure 3

A column graph representing the average classification accuracies for all subjects using linear discriminant analysis (LDA) and artificial neural network (ANN) reported in the form of mean ± standard deviation.

Figure 4

The average classification accuracy for all motion classes across all participants. The results are reported as mean ± standard deviation and asterisk denotes significant differences between motion class for each classifier. The asterisk denotes statistically significant difference.

Figure 5

Confusion matrix based on the average classification accuracies of all subjects for LDA with overall average accuracy of 63.86% ± 4.3%. The Highlighted boxes represents the correct percentage of predictions made by the classifier.

Figure 6

Confusion matrix based on the average classification accuracies of all subjects for ANN with overall average accuracy of 67.1% ± 7.9%. The Highlighted boxes represents the correct percentage of predictions made by the classifier.

Figure 7

A regression line fitted to the participants’ data of Limb Fugl-Meyer score and their classification accuracies (LDA) of individual movement and all movements combined.

Figure 8

A regression line fitted to the participants’ data of Limb Fugl-Meyer score and their classification accuracies (ANN) of individual movements and all movements combined.