MEFFNet: Forecasting Myoelectric Indices of Muscle Fatigue in Healthy and Post-Stroke During Voluntary and FES-Induced Dynamic Contractions.

Myoelectric indices forecasting is important for muscle fatigue monitoring in wearable technologies, adaptive control of assistive devices like exoskeletons and prostheses, functional electrical stimulation (FES)-based Neuroprostheses, and more. Non-stationary temporal development of these indices in dynamic contractions makes forecasting difficult. This study aims at incorporating transfer learning into a deep learning model, Myoelectric Fatigue Forecasting Network (MEFFNet), to forecast myoelectric indices of fatigue (both time and frequency domain) obtained during voluntary and FES-induced dynamic contractions in healthy and post-stroke subjects respectively. Different state-of-the-art deep learning models along with the novel MEFFNet architecture were tested on myoelectric indices of fatigue obtained during [Formula: see text] voluntary elbow flexion and extension with four different weights (1 kg, 2 kg, 3 kg, and 4 kg) in sixteen healthy subjects, and [Formula: see text] FES-induced elbow flexion in sixteen healthy and seventeen post-stroke subjects under three different stimulation patterns (customized rectangular, trapezoidal, and muscle synergy-based). A version of MEFFNet, named as pretrained MEFFNet, was trained on a dataset of sixty thousand synthetic time series to transfer its learning on real time series of myoelectric indices of fatigue. The pretrained MEFFNet could forecast up to 22.62 seconds, 60 timesteps, in future with a mean absolute percentage error of 15.99 ± 6.48% in voluntary and 11.93 ± 4.77% in FES-induced contractions, outperforming the MEFFNet and other models under consideration. The results suggest combining the proposed model with wearable technology, prosthetics, robotics, stimulation devices, etc. to improve performance. Transfer learning in time series forecasting has potential to improve wearable sensor predictions.

Muscle Synergy-Based Functional Electrical Stimulation Reduces Muscular Fatigue in Post-Stroke Patients: A Systematic Comparison.

Muscle synergy-based functional electrical stimulation had improved movement kinematics instantly and in long-term use in post-stroke patients. However, the therapeutic benefits and efficacy of muscle synergy-based functional electrical stimulation patterns over traditional stimulation patterns need exploration. This paper presents the therapeutic benefits of muscle synergy-based functional electrical stimulation compared to traditional stimulation patterns from the perspective of muscular fatigue and kinematic performance produced. Three stimulation waveforms/envelopes: customized rectangular, trapezoidal, and muscle synergy-based FES patterns were administered on six healthy and six post-stroke patients to achieve full elbow flexion. The muscular fatigue was measured through evoked-electromyography, and the kinematic outcome was measured through angular displacement during elbow flexion. The time domain (peak-to-peak amplitude, mean absolute value, root-mean-square) and frequency domain (mean frequency, median frequency) myoelectric indices of fatigue were calculated from evoked-electromyography. Myoelectric indices of fatigue and peak angular displacements of elbow joint were compared across waveforms. The presented study found that the muscle synergy-based stimulation pattern sustained the kinematic output for longer durations and induced less muscular fatigue followed by trapezoidal and customized rectangular patterns in healthy and post-stroke participants. These findings imply that the therapeutic effect of muscle synergy-based functional electrical stimulation stems from not only being biomimetic but also due to it being efficient in inducing less fatigue. The slope of current injection was a crucial factor in determining the performance of muscle synergy-based FES waveforms. The presented research methodology and outcomes would help researchers and physiotherapists in choosing effective stimulation patterns for maximizing post-stroke rehabilitation benefits. Note: FES waveform/ pattern/ stimulation pattern all refers to FES envelop in this paper.