Subject-specific myoelectric pattern classification of functional hand movements for stroke survivors

A system for accelerometer-based gesture classification using artificial neural networks

A great many people suffer from neurological movement disorders that render typical hardware interface devices ineffective. A need exists for a universal interface device that can be trained to accept a wide range of inputs across varying types and severities of movement disorders. In this regard, this paper details the design, testing and optimization of an accelerometer-based gesture identification system. A Bluetooth-enabled IMU mounted on the wrist provides hand motion trajectory information to a local terminal. Several techniques are applied to decrease the intra-class variance and reduce classifier complexity including filtering, segmentation and temporal scaling. Datasets consisted of 520 training samples, 260 validation samples and a further 520 testing samples. A multi-layer feed forward artificial neural network (ML-FFNN) was used to classify the input space into 26 different classes. Initial system accuracy, using arbitrary hyperparameters was 77.69% with final optimized accuracy at 99.42%.

Reducing the Impact of Shoulder Abduction Loading on the Classification of Hand Opening and Grasping in Individuals with Poststroke Flexion Synergy

Application of neural machine interface in individuals with chronic hemiparetic stroke is regarded as a great challenge, especially for classification of the hand opening and grasping during a functional upper extremity movement such as reach-to-grasp. The overall accuracy of classifying hand movements, while actively lifting the paretic arm, is subject to a significant reduction compared to the accuracy when the arm is fully supported. Such a reduction is believed to be due to the expression of flexion synergy, which couples shoulder abduction (SABD) with elbow/wrist and finger flexion, and is common in up to 60% of the stroke population. Little research has been done to develop methods to reduce the impact of flexion synergy on the classification of hand opening and grasping. In this study, we proposed a novel approach to classify hand opening and grasping in the context of the flexion synergy using a wavelet coherence-based filter. We first identified the frequency ranges where the coherence between the SABD muscle and wrist/finger flexion muscles is significant in each participant, and then removed the synergy-induced electromyogram (EMG) component with a subject-specific and muscle-specific coherence-based filter. The new approach was tested in 21 stroke individuals with moderate to severe motor impairments. Employing the filter, 14 participants gained improvement in classification accuracy with a range of 0.1 to 14%, while four showed 0.3 to 1.2% reduction. The remaining three participants were excluded from comparison due to the lack of significant coherence, thus no filters were applied. The improvement in classification accuracy is significant (p = 0.017) when the SABD loading equals 50% of the maximal torque. Our findings suggest that the coherence-based filters can reduce the impact of flexion synergy by removing the synergy-induced EMG component and have the potential to improve the overall classification accuracy of hand movements in individuals with poststroke flexion synergy.

Supplemental vibrotactile feedback control of stabilization and reaching actions of the arm using limb state and position error encodings

Background

Deficits of kinesthesia (limb position and movement sensation) commonly limit sensorimotor function and its recovery after neuromotor injury. Sensory substitution technologies providing synthetic kinesthetic feedback might re-establish or enhance closed-loop control of goal-directed behaviors in people with impaired kinesthesia.

Methods

As a first step toward this goal, we evaluated the ability of unimpaired people to use vibrotactile sensory substitution to enhance stabilization and reaching tasks. Through two experiments, we compared the objective and subjective utility of two forms of supplemental feedback – limb state information or hand position error – to eliminate hand position drift, which develops naturally during stabilization tasks after removing visual feedback.

Results

Experiment 1 optimized the encoding of limb state feedback; the best form included hand position and velocity information, but was weighted much more heavily toward position feedback. Upon comparing optimal limb state feedback vs. hand position error feedback in Experiment 2, we found both encoding schemes capable of enhancing stabilization and reach performance in the absence of vision. However, error encoding yielded superior outcomes - objective and subjective - due to the additional task-relevant information it contains.

Conclusions

The results of this study have established the immediate utility and relative merits of two forms of vibrotactile kinesthetic feedback in enhancing stabilization and reaching actions performed with the arm and hand in neurotypical people. These findings can guide future development of vibrotactile sensory substitution technologies for improving sensorimotor function after neuromotor injury in survivors who retain motor capacity, but lack proprioceptive integrity in their more affected arm.

Electronic supplementary material

The online version of this article (doi:10.1186/s12984-017-0248-8) contains supplementary material, which is available to authorized users.

Advanced Myoelectric Control for Robotic Hand-Assisted Training: Outcome from a Stroke Patient

A hand exoskeleton driven by myoelectric pattern recognition was designed for stroke rehabilitation. It detects and recognizes the user’s motion intent based on electromyography (EMG) signals, and then helps the user to accomplish hand motions in real time. The hand exoskeleton can perform six kinds of motions, including the whole hand closing/opening, tripod pinch/opening, and the “gun” sign/opening. A 52-year-old woman, 8 months after stroke, made 20× 2-h visits over 10 weeks to participate in robot-assisted hand training. Though she was unable to move her fingers on her right hand before the training, EMG activities could be detected on her right forearm. In each visit, she took 4× 10-min robot-assisted training sessions, in which she repeated the aforementioned six motion patterns assisted by our intent-driven hand exoskeleton. After the training, her grip force increased from 1.5 to 2.7 kg, her pinch force increased from 1.5 to 2.5 kg, her score of Box and Block test increased from 3 to 7, her score of Fugl–Meyer (Part C) increased from 0 to 7, and her hand function increased from Stage 1 to Stage 2 in Chedoke–McMaster assessment. The results demonstrate the feasibility of robot-assisted training driven by myoelectric pattern recognition after stroke.

Wavelet Packet Feature Assessment for High-Density Myoelectric Pattern Recognition and Channel Selection toward Stroke Rehabilitation

This study presents wavelet packet feature assessment of neural control information in paretic upper limb muscles of stroke survivors for myoelectric pattern recognition, taking advantage of high-resolution time–frequency representations of surface electromyogram (EMG) signals. On this basis, a novel channel selection method was developed by combining the Fisher’s class separability index and the sequential feedforward selection analyses, in order to determine a small number of appropriate EMG channels from original high-density EMG electrode array. The advantages of the wavelet packet features and the channel selection analyses were further illustrated by comparing with previous conventional approaches, in terms of classification performance when identifying 20 functional arm/hand movements implemented by 12 stroke survivors. This study offers a practical approach including paretic EMG feature extraction and channel selection that enables active myoelectric control of multiple degrees of freedom with paretic muscles. All these efforts will facilitate upper limb dexterity restoration and improved stroke rehabilitation.

Artificial neural network EMG classifier for functional hand grasp movements prediction

Objective To design and implement an electromyography (EMG)-based controller for a hand robotic assistive device, which is able to classify the user's motion intention before the effective kinematic movement execution. Methods Multiple degrees-of-freedom hand grasp movements (i.e. pinching, grasp an object, grasping) were predicted by means of surface EMG signals, recorded from 10 bipolar EMG electrodes arranged in a circular configuration around the forearm 2-3 cm from the elbow. Two cascaded artificial neural networks were then exploited to detect the patient's motion intention from the EMG signal window starting from the electrical activity onset to movement onset (i.e. electromechanical delay). Results The proposed approach was tested on eight healthy control subjects (4 females; age range 25-26 years) and it demonstrated a mean ± SD testing performance of 76% ± 14% for correctly predicting healthy users' motion intention. Two post-stroke patients tested the controller and obtained 79% and 100% of correctly classified movements under testing conditions. Conclusion A task-selection controller was developed to estimate the intended movement from the EMG measured during the electromechanical delay.

RECOGNITION OF FINGER/HAND GRIP MECHANISM BY COMPUTING S-TRANSFORM FEATURES OF SURFACE ELECTROMYOGRAM SIGNAL FROM HEALTHY AND AMPUTEE

Accurate identification of intended grip actions using the myoelectric signal recorded from the surface of the residual muscles can facilitate natural control of a prosthetic hand for an amputee. However, this is not trivial due to the complexity of the hand muscles. To overcome these shortcomings, there is the need for determining features of the myoelectric recordings that can be used for accurate identification of the grip actions. This study reports the use of S-transform (ST) of the surface myoelectric recordings for recognizing the intent of the user to generate a set of grip patterns. Surface Electromyogram (sEMG) recorded while performing five different hand/finger grip patterns was analyzed. ST of the signal was computed to analyze the signal in a windowed time–frequency domain. The energy and mean amplitude of the transformed signal were classified using a neural network. The method was tested for able-hand and trans-radial amputee subjects. The results show that ST showed improved sensitivity, specificity and accuracy for both healthy and amputee people.

Muscle Synergies in Cycling after Incomplete Spinal Cord Injury: Correlation with Clinical Measures of Motor Function and Spasticity

Background: After incomplete spinal cord injury (iSCI), patients suffer important sensorimotor impairments, such as abnormal locomotion patterns and spasticity. Complementary to current clinical diagnostic procedures, the analysis of muscle synergies has emerged as a promising tool to study muscle coordination, which plays a major role in the control of multi-limb functional movements.

Objective: Based on recent findings suggesting that walking and cycling share similar synergistic control, the analysis of muscle synergies during cycling might be explored as an early descriptor of gait-related impaired control. This idea was split into the following two hypotheses: (a) iSCI patients present a synergistic control of muscles during cycling; (b) muscle synergies outcomes extracted during cycling correlate with clinical measurements of gait performance and/or spasticity.

Methods: Electromyographic (EMG) activity of 13 unilateral lower limb muscles was recorded in a group of 10 healthy individuals and 10 iSCI subjects during cycling at four different cadences. A non-negative matrix factorization (NNMF) algorithm was applied to identify synergistic components (i.e., activation coefficients and muscle synergy vectors). Reconstruction goodness scores (VAF and r²) were used to evaluate the ability of a given number of synergies to reconstruct the EMG signals.

A set of metrics based on the similarity between pathologic and healthy synergies were correlated with clinical scales of gait performance and spasticity.

Results: iSCI patients preserved a synergistic control of muscles during cycling. The similarity with the healthy reference was consistent with the degree of the impairment, i.e., less impaired patients showed higher similarities with the healthy reference. There was a strong correlation between reconstruction goodness scores at 42 rpm and motor performance scales (TUG, 10-m test and WISCI II). On the other hand, the similarity between the healthy and affected synergies presented correlation with some spasticity symptoms measured by Penn, Modified Ashworth and SCATS scales.

Conclusion: Overall, the results of this study support the hypothesis that the analysis of muscle synergies during cycling can provide detailed quantitative assessment of functional motor impairments and symptoms of spasticity caused by abnormal spatiotemporal muscle co-activation following iSCI.

Cardinality as a highly descriptive feature in myoelectric pattern recognition for decoding motor volition

Accurate descriptors of muscular activity play an important role in clinical practice and rehabilitation research. Such descriptors are features of myoelectric signals extracted from sliding time windows. A wide variety of myoelectric features have been used as inputs to pattern recognition algorithms that aim to decode motor volition. The output of these algorithms can then be used to control limb prostheses, exoskeletons, and rehabilitation therapies. In the present study, cardinality is introduced and compared with traditional time-domain (Hudgins' set) and other recently proposed myoelectric features (for example, rough entropy). Cardinality was found to consistently outperform other features, including those that are more sophisticated and computationally expensive, despite variations in sampling frequency, time window length, contraction dynamics, type, and number of movements (single or simultaneous), and classification algorithms. Provided that the signal resolution is kept between 12 and 14 bits, cardinality improves myoelectric pattern recognition for the prediction of motion volition. This technology is instrumental for the rehabilitation of amputees and patients with motor impairments where myoelectric signals are viable. All code and data used in this work is available online within BioPatRec.

Residual Upper Arm Motor Function Primes Innervation of Paretic Forearm Muscles in Chronic Stroke after Brain-Machine Interface (BMI) Training

Background

Abnormal upper arm-forearm muscle synergies after stroke are poorly understood. We investigated whether upper arm function primes paralyzed forearm muscles in chronic stroke patients after Brain-Machine Interface (BMI)-based rehabilitation. Shaping upper arm-forearm muscle synergies may support individualized motor rehabilitation strategies.

Methods

Thirty-two chronic stroke patients with no active finger extensions were randomly assigned to experimental or sham groups and underwent daily BMI training followed by physiotherapy during four weeks. BMI sessions included desynchronization of ipsilesional brain activity and a robotic orthosis to move the paretic limb (experimental group, n = 16). In the sham group (n = 16) orthosis movements were random. Motor function was evaluated with electromyography (EMG) of forearm extensors, and upper arm and hand Fugl-Meyer assessment (FMA) scores. Patients performed distinct upper arm (e.g., shoulder flexion) and hand movements (finger extensions). Forearm EMG activity significantly higher during upper arm movements as compared to finger extensions was considered facilitation of forearm EMG activity. Intraclass correlation coefficient (ICC) was used to test inter-session reliability of facilitation of forearm EMG activity.

Results

Facilitation of forearm EMG activity ICC ranges from 0.52 to 0.83, indicating fair to high reliability before intervention in both limbs. Facilitation of forearm muscles is higher in the paretic as compared to the healthy limb (p<0.001). Upper arm FMA scores predict facilitation of forearm muscles after intervention in both groups (significant correlations ranged from R = 0.752, p = 0.002 to R = 0.779, p = 0.001), but only in the experimental group upper arm FMA scores predict changes in facilitation of forearm muscles after intervention (R = 0.709, p = 0.002; R = 0.827, p<0.001).

Conclusions

Residual upper arm motor function primes recruitment of paralyzed forearm muscles in chronic stroke patients and predicts changes in their recruitment after BMI training. This study suggests that changes in upper arm-forearm synergies contribute to stroke motor recovery, and provides candidacy guidelines for similar BMI-based clinical practice.

Application of wavelet packet transform on myoelectric pattern recognition for upper limb rehabilitation after stroke

Myoelectric pattern recognition applied to high-density surface electromyographic (sEMG) recordings from paretic muscles has been proven to identify various movement intents of stroke survivors, thus facilitating the design of myoelectrically controlled robotic systems for recovery of upper-limb dexterity. Aiming at effectively decoding neural control information under the condition of neurological injury following stroke, this paper further investigates the application of wavelet packet transform (WPT) on myoelectric feature extraction to identify 20 functional movements performed by the paretic upper limb of 4 chronic stroke subjects. The WPT was used to decompose the original sEMG signals via a tree of subspaces, where optimal ones were selected in term of the classification efficacy. The energies in the selected subspaces were calculated as optimal wavelet packet features, which were finally fed into a linear discriminant classifier. The WPT-based myoelectric feature extraction approach achieved accuracies above 94% for all subjects in a user-specific condition, demonstrating its potential applications in upper limb rehabilitation after stroke.

Decoding upper limb residual muscle activity in severe chronic stroke

Objective

Stroke is a leading cause of long-term motor disability. Stroke patients with severe hand weakness do not profit from rehabilitative treatments. Recently, brain-controlled robotics and sequential functional electrical stimulation allowed some improvement. However, for such therapies to succeed, it is required to decode patients' intentions for different arm movements. Here, we evaluated whether residual muscle activity could be used to predict movements from paralyzed joints in severely impaired chronic stroke patients.

Methods

Muscle activity was recorded with surface-electromyography (EMG) in 41 patients, with severe hand weakness (Fugl-Meyer Assessment [FMA] hand subscores of 2.93 ± 2.7), in order to decode their intention to perform six different motions of the affected arm, required for voluntary muscle activity and to control neuroprostheses. Decoding of paretic and nonparetic muscle activity was performed using a feed-forward neural network classifier. The contribution of each muscle to the intended movement was determined.

Results

Decoding of up to six arm movements was accurate (>65%) in more than 97% of nonparetic and 46% of paretic muscles.

Interpretation

These results demonstrate that some level of neuronal innervation to the paretic muscle remains preserved and can be used to implement neurorehabilitative treatments in 46% of patients with severe paralysis and extensive cortical and/or subcortical lesions. Such decoding may allow these patients for the first time after stroke to control different motions of arm prostheses through muscle-triggered rehabilitative treatments.

An augmented reality system for upper-limb post-stroke motor rehabilitation: a feasibility study

PURPOSE

To determine the clinical feasibility of a system based on augmented reality for upper-limb (UL) motor rehabilitation of stroke participants.

METHOD

A physiotherapist instructed the participants to accomplish tasks in augmented reality environment, where they could see themselves and their surroundings, as in a mirror. Two case studies were conducted. Participants were evaluated pre- and post-intervention. The first study evaluated the UL motor function using Fugl-Meyer scale. Data were compared using non-parametric sign tests and effect size. The second study used the gain of motion range of shoulder flexion and abduction assessed by computerized biophotogrammetry.

RESULTS

At a significance level of 5%, Fugl-Meyer scores suggested a trend for greater UL motor improvement in the augmented reality group than in the other. Moreover, effect size value 0.86 suggested high practical significance for UL motor rehabilitation using the augmented reality system.

CONCLUSION

System provided promising results for UL motor rehabilitation, since enhancements have been observed in the shoulder range of motion and speed. Implications for Rehabilitation Gain of range of motion of flexion and abduction of the shoulder of post-stroke patients can be achieved through an augmented reality system containing exercises to promote the mental practice. NeuroR system provides a mental practice method combined with visual feedback for motor rehabilitation of chronic stroke patients, giving the illusion of injured upper-limb (UL) movements while the affected UL is resting. Its application is feasible and safe. This system can be used to improve UL rehabilitation, an additional treatment past the traditional period of the stroke patient hospitalization and rehabilitation.

Feature dimensionality reduction for myoelectric pattern recognition: a comparison study of feature selection and feature projection methods

This study investigates the effect of the feature dimensionality reduction strategies on the classification of surface electromyography (EMG) signals toward developing a practical myoelectric control system. Two dimensionality reduction strategies, feature selection and feature projection, were tested on both EMG feature sets, respectively. A feature selection based myoelectric pattern recognition system was introduced to select the features by eliminating the redundant features of EMG recordings instead of directly choosing a subset of EMG channels. The Markov random field (MRF) method and a forward orthogonal search algorithm were employed to evaluate the contribution of each individual feature to the classification, respectively. Our results from 15 healthy subjects indicate that, with a feature selection analysis, independent of the type of feature set, across all subjects high overall accuracies can be achieved in classification of seven different forearm motions with a small number of top ranked original EMG features obtained from the forearm muscles (average overall classification accuracy >95% with 12 selected EMG features). Compared to various feature dimensionality reduction techniques in myoelectric pattern recognition, the proposed filter-based feature selection approach is independent of the type of classification algorithms and features, which can effectively reduce the redundant information not only across different channels, but also cross different features in the same channel. This may enable robust EMG feature dimensionality reduction without needing to change ongoing, practical use of classification algorithms, an important step toward clinical utility.

Extraction of neural control commands using myoelectric pattern recognition: a novel application in adults with cerebral palsy

This study investigates an electromyogram (EMG)-based neural interface toward hand rehabilitation for patients with cerebral palsy (CP). Forty-eight channels of surface EMG signals were recorded from the forearm of eight adult subjects with CP, while they tried to perform six different hand grasp patterns. A series of myoelectric pattern recognition analyses were performed to identify the movement intention of each subject with different EMG feature sets and classifiers. Our results indicate that across all subjects high accuracies (average overall classification accuracy > 98%) can be achieved in classification of six different hand movements, suggesting that there is substantial motor control information contained in paretic muscles of the CP subjects. Furthermore, with a feature selection analysis, it was found that a small number of ranked EMG features can maintain high classification accuracies comparable to those obtained using all the EMG features (average overall classification accuracy > 96% with 16 selected EMG features). The findings of the study suggest that myoelectric pattern recognition may be a useful control strategy for promoting hand rehabilitation in CP patients.

Treatment of phantom limb pain (PLP) based on augmented reality and gaming controlled by myoelectric pattern recognition: a case study of a chronic PLP patient

A variety of treatments have been historically used to alleviate phantom limb pain (PLP) with varying efficacy. Recently, virtual reality (VR) has been employed as a more sophisticated mirror therapy. Despite the advantages of VR over a conventional mirror, this approach has retained the use of the contralateral limb and is therefore restricted to unilateral amputees. Moreover, this strategy disregards the actual effort made by the patient to produce phantom motions. In this work, we investigate a treatment in which the virtual limb responds directly to myoelectric activity at the stump, while the illusion of a restored limb is enhanced through augmented reality (AR). Further, phantom motions are facilitated and encouraged through gaming. The proposed set of technologies was administered to a chronic PLP patient who has shown resistance to a variety of treatments (including mirror therapy) for 48 years. Individual and simultaneous phantom movements were predicted using myoelectric pattern recognition and were then used as input for VR and AR environments, as well as for a racing game. The sustained level of pain reported by the patient was gradually reduced to complete pain-free periods. The phantom posture initially reported as a strongly closed fist was gradually relaxed, interestingly resembling the neutral posture displayed by the virtual limb. The patient acquired the ability to freely move his phantom limb, and a telescopic effect was observed where the position of the phantom hand was restored to the anatomically correct distance. More importantly, the effect of the interventions was positively and noticeably perceived by the patient and his relatives. Despite the limitation of a single case study, the successful results of the proposed system in a patient for whom other medical and non-medical treatments have been ineffective justifies and motivates further investigation in a wider study.

Several practical issues toward implementing myoelectric pattern recognition for stroke rehabilitation

High density surface electromyogram (sEMG) recording and pattern recognition techniques have demonstrated that substantial motor control information can be extracted from neurologically impaired muscles. In this study, a series of pattern recognition parameters were investigated in classification of 20 different movements involving the affected limb of 12 chronic stroke subjects. The experimental results showed that classification performance could be improved with spatial filtering and be maintained with a limited number of electrodes. It was also found that appropriate adjustment of analysis window length, sampling rate, and high-pass cut-off frequency in sEMG conditioning and processing would be potentially useful in reducing computational cost and meanwhile ensuring classification performance. The quantitative analyses are useful for practical myoelectric control toward improved stroke rehabilitation.

Brain-machine interface in chronic stroke rehabilitation: a controlled study

OBJECTIVE

Chronic stroke patients with severe hand weakness respond poorly to rehabilitation efforts. Here, we evaluated efficacy of daily brain-machine interface (BMI) training to increase the hypothesized beneficial effects of physiotherapy alone in patients with severe paresis in a double-blind sham-controlled design proof of concept study.

METHODS

Thirty-two chronic stroke patients with severe hand weakness were randomly assigned to 2 matched groups and participated in 17.8 ± 1.4 days of training rewarding desynchronization of ipsilesional oscillatory sensorimotor rhythms with contingent online movements of hand and arm orthoses (experimental group, n = 16). In the control group (sham group, n = 16), movements of the orthoses occurred randomly. Both groups received identical behavioral physiotherapy immediately following BMI training or the control intervention. Upper limb motor function scores, electromyography from arm and hand muscles, placebo-expectancy effects, and functional magnetic resonance imaging (fMRI) blood oxygenation level-dependent activity were assessed before and after intervention.

RESULTS

A significant group × time interaction in upper limb (combined hand and modified arm) Fugl-Meyer assessment (cFMA) motor scores was found. cFMA scores improved more in the experimental than in the control group, presenting a significant improvement of cFMA scores (3.41 ± 0.563-point difference, p = 0.018) reflecting a clinically meaningful change from no activity to some in paretic muscles. cFMA improvements in the experimental group correlated with changes in fMRI laterality index and with paretic hand electromyography activity. Placebo-expectancy scores were comparable for both groups.

INTERPRETATION

The addition of BMI training to behaviorally oriented physiotherapy can be used to induce functional improvements in motor function in chronic stroke patients without residual finger movements and may open a new door in stroke neurorehabilitation.

The effect of involuntary motor activity on myoelectric pattern recognition: a case study with chronic stroke patients

OBJECTIVE

This study investigates the effect of the involuntary motor activity of paretic-spastic muscles on the classification of surface electromyography (EMG) signals.

APPROACH

Two data collection sessions were designed for 8 stroke subjects to voluntarily perform 11 functional movements using their affected forearm and hand at relatively slow and fast speeds. For each stroke subject, the degree of involuntary motor activity present in the voluntary surface EMG recordings was qualitatively described from such slow and fast experimental protocols. Myoelectric pattern recognition analysis was performed using different combinations of voluntary surface EMG data recorded from the slow and fast sessions.

MAIN RESULTS

Across all tested stroke subjects, our results revealed that when involuntary surface EMG is absent or present in both the training and testing datasets, high accuracies (>96%, >98%, respectively, averaged over all the subjects) can be achieved in the classification of different movements using surface EMG signals from paretic muscles. When involuntary surface EMG was solely involved in either the training or testing datasets, the classification accuracies were dramatically reduced (<89%, <85%, respectively). However, if both the training and testing datasets contained EMG signals with the presence and absence of involuntary EMG interference, high accuracies were still achieved (>97%).

SIGNIFICANCE

The findings of this study can be used to guide the appropriate design and implementation of myoelectric pattern recognition based systems or devices toward promoting robot-aided therapy for stroke rehabilitation.

Impairment in task-specific modulation of muscle coordination correlates with the severity of hand impairment following stroke

Significant functional impairment of the hand is commonly observed in stroke survivors. Our previous studies suggested that the inability to modulate muscle coordination patterns according to task requirements may be substantial after stroke, but these limitations have not been examined directly. In this study, we aimed to characterize post-stroke impairment in the ability to modulate muscle coordination patterns across tasks and its correlation with hand impairment. Fourteen stroke survivors, divided into a group with severe hand impairment (8 subjects) and a group with moderate hand impairment (6 subjects) according to their clinical functionality score, participated in the experiment. Another four neurologically intact subjects participated in the experiment to serve as a point of comparison. Activation patterns of nine hand and wrist muscles were recorded using surface electromyography while the subjects performed six isometric tasks. Patterns of covariation in muscle activations across tasks, i.e., muscle modules, were extracted from the muscle activation data. Our results showed that the degree of reduction in the inter-task separation of the multi-muscle activation patterns was indicative of the clinical functionality score of the subjects (mean value = 26.2 for severely impaired subjects, 38.1 for moderately impaired subjects). The values for moderately impaired subjects were much closer to those of the impaired subjects (mean value = 46.1). The number of muscle modules extracted from the muscle activation patterns of a subject across six tasks, which represents the degree of motor complexity, was found to be correlated with the clinical functionality score (R = 0.68). Greater impairment was also associated with a change in the muscle module patterns themselves, with greater muscle coactivation. A substantial reduction in the degrees-of-freedom of the multi-muscle coordination post-stroke was apparent, and the extent of the reduction, assessed by the stated metrics, was strongly associated with the level of clinical impairment.

EMG-based pattern recognition approach in post stroke robot-aided rehabilitation: a feasibility study

Background

Several studies investigating the use of electromyographic (EMG) signals in robot-based stroke neuro-rehabilitation to enhance functional recovery. Here we explored whether a classical EMG-based patterns recognition approach could be employed to predict patients’ intentions while attempting to generate goal-directed movements in the horizontal plane.

Methods

Nine right-handed healthy subjects and seven right-handed stroke survivors performed reaching movements in the horizontal plane. EMG signals were recorded and used to identify the intended motion direction of the subjects. To this aim, a standard pattern recognition algorithm (i.e., Support Vector Machine, SVM) was used. Different tests were carried out to understand the role of the inter- and intra-subjects’ variability in affecting classifier accuracy. Abnormal muscular spatial patterns generating misclassification were evaluated by means of an assessment index calculated from the results achieved with the PCA, i.e., the so-called Coefficient of Expressiveness (CoE).

Results

Processing the EMG signals of the healthy subjects, in most of the cases we were able to build a static functional map of the EMG activation patterns for point-to-point reaching movements on the horizontal plane. On the contrary, when processing the EMG signals of the pathological subjects a good classification was not possible. In particular, patients’ aimed movement direction was not predictable with sufficient accuracy either when using the general map extracted from data of normal subjects and when tuning the classifier on the EMG signals recorded from each patient.

Conclusions

The experimental findings herein reported show that the use of EMG patterns recognition approach might not be practical to decode movement intention in subjects with neurological injury such as stroke. Rather than estimate motion from EMGs, future scenarios should encourage the utilization of these signals to detect and interpret the normal and abnormal muscle patterns and provide feedback on their correct recruitment.

Myoelectrically controlled wrist robot for stroke rehabilitation

BACKGROUND

Robot-assisted rehabilitation is an advanced new technology in stroke rehabilitation to provide intensive training. Post-stroke motor recovery depends on active rehabilitation by voluntary participation of patient's paretic motor system as early as possible in order to promote reorganization of brain. However, voluntary residual motor efforts to the affected limb have not been involved enough in most robot-assisted rehabilitation for patients after stroke. The objective of this study is to evaluate the feasibility of robot-assisted rehabilitation using myoelectric control on upper limb motor recovery.

METHODS

In the present study, an exoskeleton-type rehabilitation robotic system was designed to provide voluntarily controlled assisted torque to the affected wrist. Voluntary intention was involved by using the residual surface electromyography (EMG) from flexor carpi radialis(FCR) and extensor carpi radialis (ECR)on the affected limb to control the mechanical assistance provided by the robotic system during wrist flexion and extension in a 20-session training. The system also applied constant resistant torque to the affected wrist during the training. Sixteen subjects after stroke had been recruited for evaluating the tracking performance and therapeutical effects of myoelectrically controlled robotic system.

RESULTS

With the myoelectrically-controlled assistive torque, stroke survivors could reach a larger range of motion with a significant decrease in the EMG signal from the agonist muscles. The stroke survivors could be trained in the unreached range with their voluntary residual EMG on the paretic side. After 20-session rehabilitation training, there was a non-significant increase in the range of motion and a significant decrease in the root mean square error (RMSE) between the actual wrist angle and target angle. Significant improvements also could be found in muscle strength and clinical scales.

CONCLUSIONS

These results indicate that robot-aided therapy with voluntary participation of patient's paretic motor system using myoelectric control might have positive effect on upper limb motor recovery.

Corticomuscular coherence analysis on hand movement distinction for active rehabilitation

Active rehabilitation involves patient's voluntary thoughts as the control signals of restore device to assist stroke rehabilitation. Although restoration of hand opening stands importantly in patient's daily life, it is difficult to distinguish the voluntary finger extension from thumb adduction and finger flexion using stroke patients' electroencephalography (EMG) on single muscle activity. We propose to implement corticomuscular coherence analysis on electroencephalography (EEG) and EMG signals on Extensor Digitorum to extract their intention involved in hand opening. EEG and EMG signals of 8 subjects are simultaneously collected when executing 4 hand movement tasks (finger extension, thumb adduction, finger flexion, and rest). We explore the spatial and temporal distribution of the coherence and observe statistically significant corticomuscular coherence appearing at left motor cortical area and different patterns within beta frequency range for 4 movement tasks. Linear discriminate analysis is applied on the coherence pattern to distinguish finger extension from thumb adduction, finger flexion, and rest. The classification results are greater than those by EEG only. The results indicate the possibility to detect voluntary hand opening based on coherence analysis between single muscle EMG signal and single EEG channel located in motor cortical area, which potentially helps active hand rehabilitation for stroke patients.

Pattern recognition based forearm motion classification for patients with chronic hemiparesis

To make full use of electromyography (EMG) that contains rich information of muscular activities in active rehabilitation for motor hemiparetic patients, a couple of recent studies have explored the feasibility of applying pattern recognition technique to the classification of multiple motion classes for stroke survivors and reported some promising results. However, it still remains unclear if kinematics signals could also bring good motion classification performance, particularly for patients after traumatic brain damage. In this study, the kinematics signals was used for motion classification analysis in three stroke survivors and two patients after traumatic brain injury, and compared with EMG. The results showed that an average classification error of 7.9 ± 6.8% for the affected arm over all subjects could be achieved with a linear classifier when they performed multiple fine movements, 7.9% lower than that when using EMG. With either kind of signals, the motor control ability of the affected arm degraded significantly in comparison to the intact side. The preliminary results suggested the great promise of kinematics information as well as the biological signals in detecting user's conscious effort for robot-aided active rehabilitation.

Two-channel surface electromyography for individual and combined finger movements

This paper proposes the pattern recognition system for individual and combined finger movements by using two channel electromyography (EMG) signals. The proposed system employs Spectral Regression Discriminant Analysis (SRDA) for dimensionality reduction, Extreme Learning Machine (ELM) for classification and the majority vote for the classification smoothness. The advantage of the SRDA is its speed which is faster than original LDA so that it could deal with multiple features. In addition, the use of ELM which is fast and has similar classification performance to well-known SVM empowers the classification system. The experimental results show that the proposed system was able to recognize the individual and combined fingers movements with up to 98 % classification accuracy by using only just two EMG channels.

A novel myoelectric pattern recognition strategy for hand function restoration after incomplete cervical spinal cord injury

This study presents a novel myoelectric pattern recognition strategy towards restoration of hand function after incomplete cervical spinal cord Injury (SCI). High density surface electromyogram (EMG) signals comprised of 57 channels were recorded from the forearm of nine subjects with incomplete cervical SCI while they tried to perform six different hand grasp patterns. A series of pattern recognition algorithms with different EMG feature sets and classifiers were implemented to identify the intended tasks of each SCI subject. High average overall accuracies (> 97%) were achieved in classification of seven different classes (six intended hand grasp patterns plus a hand rest pattern), indicating that substantial motor control information can be extracted from partially paralyzed muscles of SCI subjects. Such information can potentially enable volitional control of assistive devices, thereby facilitating restoration of hand function. Furthermore, it was possible to maintain high levels of classification accuracy with a very limited number of electrodes selected from the high density surface EMG recordings. This demonstrates clinical feasibility and robustness in the concept of using myoelectric pattern recognition techniques toward improved function restoration for individuals with spinal injury.