This article presents a novel electromyography (EMG)-driven exoneuromusculoskeleton that integrates the neuromuscular electrical stimulation (NMES), soft pneumatic muscle, and exoskeleton techniques, for self-help upper limb training after stroke. The developed system can assist the elbow, wrist, and fingers to perform sequential arm reaching and withdrawing tasks under voluntary effort control through EMG, with a lightweight, compact, and low-power requirement design. The pressure/torque transmission properties of the designed musculoskeletons were quantified, and the assistive capability of the developed system was evaluated on patients with chronic stroke ( n = 10). The designed musculoskeletons exerted sufficient mechanical torque to support joint extension for stroke survivors. Compared with the limb performance when no assistance was provided, the limb performance (measured as the range of motion in joint extension) significantly improved when mechanical torque and NMES were provided ( p < 0.05). A pilot trial was conducted on patients with chronic stroke ( n = 15) to investigate the feasibility of using the developed system in self-help training and the rehabilitation effects of the system. All the participants completed the self-help device-assisted training with minimal professional assistance. After a 20-session training, significant improvements were noted in the voluntary motor function and release of muscle spasticity at the elbow, wrist, and fingers, as indicated by the clinical scores ( p < 0.05). The EMG parameters ( p < 0.05) indicated that the muscular coordination of the entire upper limb improved significantly after training. The results suggested that the developed system can effectively support self-help upper limb rehabilitation after stroke. Register Number NCT03752775.

Background: Surface electromyography (sEMG) based robot-assisted rehabilitation systems have been adopted for chronic stroke survivors to regain upper limb motor function. However, the evaluation of rehabilitation effects during robot-assisted intervention relies on traditional manual assessments. This study aimed to develop a novel sEMG data-driven model for automated assessment.Method: A data-driven model based on a three-layer backpropagation neural network (BPNN) was constructed to map sEMG data to two widely used clinical scales, i.e., the Fugl–Meyer Assessment (FMA) and the Modified Ashworth Scale (MAS). Twenty-nine stroke participants were recruited in a 20-session sEMG-driven robot-assisted upper limb rehabilitation, which consisted of hand reaching and withdrawing tasks. The sEMG signals from four muscles in the paretic upper limbs, i.e., biceps brachii (BIC), triceps brachii (TRI), flexor digitorum (FD), and extensor digitorum (ED), were recorded before and after the intervention. Meanwhile, the corresponding clinical scales of FMA and MAS were measured manually by a blinded assessor. The sEMG features including Mean Absolute Value (MAV), Zero Crossing (ZC), Slope Sign Change (SSC), Root Mean Square (RMS), and Wavelength (WL) were adopted as the inputs to the data-driven model. The mapped clinical scores from the data-driven model were compared with the manual scores by Pearson correlation.Results: The BPNN, with 15 nodes in the hidden layer and sEMG features, i.e., MAV, ZC, SSC, and RMS, as the inputs to the model, was established to achieve the best mapping performance with significant correlations (r &gt; 0.9, P &lt; 0.001), according to the FMA. Significant correlations were also obtained between the mapped and manual FMA subscores, i.e., FMA-wrist/hand and FMA-shoulder/elbow, before and after the intervention (r &gt; 0.9, P &lt; 0.001). Significant correlations (P &lt; 0.001) between the mapped and manual scores of MASs were achieved, with the correlation coefficients r = 0.91 at the fingers, 0.88 at the wrist, and 0.91 at the elbow after the intervention.Conclusion: An sEMG data-driven BPNN model was successfully developed. It could evaluate upper limb motor functions in chronic stroke and have potential application in automated assessment in post-stroke rehabilitation, once validated with large sample sizes.Clinical Trial Registration:www.ClinicalTrials.gov, identifier: NCT02117089.