Machine-learning-based coordination of powered ankle-foot orthosis and functional electrical stimulation for gait control

This study proposes a novel gait rehabilitation method that uses a hybrid system comprising a powered ankle-foot orthosis (PAFO) and FES, and presents its coordination control. The developed system provides assistance to the ankle joint in accordance with the degree of volitional participation of patients with post-stroke hemiplegia. The PAFO adopts the desired joint angle and impedance profile obtained from biomechanical simulation. The FES patterns of the tibialis anterior and soleus muscles are derived from predetermined electromyogram patterns of healthy individuals during gait and personalized stimulation parameters. The CNN-based estimation model predicts the volitional joint torque from the electromyogram of the patient, which is used to coordinate the contributions of the PAFO and FES. The effectiveness of the developed hybrid system was tested on healthy individuals during treadmill walking with and without considering the volitional muscle activity of the individual. The results showed that consideration of the volitional muscle activity significantly lowers the energy consumption by the PAFO and FES while providing adaptively assisted ankle motion depending on the volitional muscle activities of the individual. The proposed system has potential use as an assist-as-needed rehabilitation system, where it can improve the outcome of gait rehabilitation by inducing active patient participation depending on the stage of rehabilitation.

An Adaptive Spatial Filtering Method for Multi-Channel EMG Artifact Removal During Functional Electrical Stimulation With Time-Variant Parameters

Removing the stimulation artifacts evoked by the functional electrical stimulation (FES) in electromyogram (EMG) signals is a challenge. Previous researches on stimulation artifact removal have focused on FES modulation with time-constant parameters, which has limitations when there are time-variant parameters. Therefore, considering the synchronism of muscle activation induced by FES and the asynchronism of muscle activation induced by proprioceptive nerves, we proposed a novel adaptive spatial filtering method called G-S-G. It entails fusing the Gram-Schmidt orthogonalization (G-S) and Grubbs criterion (G) algorithms to remove the FES-evoked stimulation artifacts in multi-channel EMG signals. To verify this method, we constructed a series of simulation data by fusing the FES signal with time-variant parameters and the voluntary EMG (vEMG) signal, and applied the G-S-G method to remove any FES artifacts from the simulation data. After that, we calculated the root mean square (RMS) value for both preprocessed simulation data and the vEMG data, and then compared them. The simulation results showed that the G-S-G method was robust and effective at removing FES artifacts in simulated EMG signals, and the correlation coefficient between the preprocessed EMG data and the recorded vEMG data yielded a good performance, up to 0.87. Furthermore, we applied the proposed method to the experimental EMG data with FES-evoked stimulation artifact, and also achieved good performance with both the time-constant and time-variant parameters. This study provides a new and accessible approach to resolving the problem of removing FES-evoked stimulation artifacts.

EMG-Informed Neuromusculoskeletal Modelling Estimates Muscle Forces and Joint Moments During Electrical Stimulation

This study implemented an electromyogram (EMG)-informed neuromusculoskeletal (NMS) model evaluating the volitional contributions to muscle forces and joint moments during functional electrical stimulation (FES). The NMS model was calibrated using motion and EMG (biceps brachii and triceps brachii) data recorded from able-bodied participants (n=3) performing weighted elbow flexion and extension cycling movements while equipped with an EMG-controlled closed-loop FES system. Models were executed using three computational approaches (i) EMG-driven, (ii) EMG-hybrid and (iii) EMG-assisted to estimate muscle forces and joint moments. Both EMG-hybrid and EMG-assisted modes were able estimate the elbow moment (root mean squared error and coefficient of determination), but the EMG-hybrid method also enabled quantifying the volitional contributions to muscle forces and elbow moments during FES. The proposed modelling method allows for assessing volitional contributions of patients to muscle force during FES rehabilitation, and could be used as biomarkers of recovery, biofeedback, and for real-time control of combined FES and robotic systems.

Isolating Transcutaneous Spinal Cord Stimulation Artifact to Identify Motor Response during Walking

The objective of this investigation was to demonstrate the applicability of a custom-developed EMD-Notch filtering algorithm to isolate the scTS-induced artifact from sEMG signals during walking in an individual with motor-incomplete SCI. Overall, the EMD-Notch filtering algorithm provides an effective approach to isolate the scTS artifact, extract the sEMG data, and further study the modulation of the spinal neuronal networks during dynamic activities.Clinical Relevance- This investigation will help with the modification of individualized scTS parameters to achieve task-specific neuromodulatory effects.

A hybrid method for real-time stimulation artefact removal during functional electrical stimulation with time-variant parameters

Objective. In this study, a hybrid method combining hardware and software architecture is proposed to remove stimulation artefacts (SAs) and extract the volitional surface electromyography (sEMG) in real time during functional electrical stimulations (FES) with time-variant parameters.Approach. First, an sEMG detection front-end (DFE) combining fast recovery, detector and stimulator isolation and blanking is developed and is capable of preventing DFE saturation with a blanking time of 7.6 ms. The fragment between the present stimulus and previous stimulus is set as an SA fragment. Second, an SA database is established to provide six high-similarity templates with the current SA fragment. The SA fragment will be de-artefacted by a 6th-order Gram-Schmidt (GS) algorithm, a template-subtracting method, using the provided templates, and this database-based GS algorithm is called DBGS. The provided templates are previously collected SA fragments with the same or a similar evoking FES intensity to that of the current SA fragment, and the lengths of the templates are longer than that of the current SA fragment. After denoising, the sEMG will be extracted, and the current SA fragment will be added to the SA database. The prototype system based on DBGS was tested on eight able-bodied volunteers and three individuals with stroke to verify its capacity for stimulation removal and sEMG extraction.Results.The average stimulus artefact attenuation factor, SA index and correlation coefficient between clean sEMG and extracted sEMG for 6th-order DBGS were 12.77 ± 0.85 dB, 1.82 ± 0.37 dB and 0.84 ± 0.33 dB, respectively, which were significantly higher than those for empirical mode decomposition combined with notch filters, pulse-triggered GS algorithm, 1st-order and 3rd-order DBGS. The sEMG-torque correlation coefficients were 0.78 ± 0.05 and 0.48 ± 0.11 for able-bodied volunteers and individuals with stroke, respectively.Significance.The proposed hybrid method can extract sEMG during dynamic FES in real time.

Active proportional electromyogram controlled functional electrical stimulation system

Neurophysiological theories and past studies suggest that intention driven functional electrical stimulation (FES) could be effective in motor neurorehabilitation. Proportional control of FES using voluntary EMG may be used for this purpose. Electrical artefact contamination of voluntary electromyogram (EMG) during FES application makes the technique difficult to implement. Previous attempts to date either poorly extract the voluntary EMG from the artefacts, require a special hardware or are unsuitable for online application. Here we show an implementation of an entirely software-based solution that resolves the current problems in real-time using an adaptive filtering technique with an optional comb filter to extract voluntary EMG from muscles under FES. We demonstrated that unlike the classic comb filter approach, the signal extracted with the present technique was coherent with its noise-free version. Active FES, the resulting EMG-FES system was validated in a typical use case among fifteen patients with tetraplegia. Results showed that FES intensity modulated by the Active FES system was proportional to intentional movement. The Active FES system may inspire further research in neurorehabilitation and assistive technology.