Commercial device-based hand rehabilitation systems for stroke patients: State of the art and future prospects

Continuous Prediction of Wrist Joint Kinematics Using Surface Electromyography From the Perspective of Muscle Anatomy and Muscle Synergy Feature Extraction

Post-stroke upper limb dysfunction severely impacts patients' daily life quality. Utilizing sEMG signals to predict patients' motion intentions enables more effective rehabilitation by precisely adjusting the assistance level of rehabilitation robots. Employing the muscle synergy (MS) features can establish more accurate and robust mappings between sEMG and motion intentions. However, traditional matrix factorization algorithms based on blind source separation still exhibit certain limitations in extracting MS features. This paper proposes four deep learning models to extract MS features from four distinct perspectives: spatiotemporal convolutional kernels, compression and reconstruction of sEMG, graph topological structure, and the anatomy of target muscles. Among these models, the one based on 3DCNN predicts motion intentions from the muscle anatomy perspective for the first time. It reconstructs 1D sEMG samples collected at each time point into 2D sEMG frames based on the anatomical distribution of target muscles and sEMG electrode placement. These 2D frames are then stacked as video segments and input into 3DCNN for MS feature extraction. Experimental results on both our wrist motion dataset and public Ninapro DB2 dataset demonstrate that the proposed 3DCNN model outperforms other models in terms of prediction accuracy, robustness, training efficiency, and MS feature extraction for continuous prediction of wrist flexion/extension angles. Specifically, the average nRMSE and R2 values of 3DCNN on these two datasets are (0.14/0.93) and (0.04/0.95), respectively. Furthermore, compared to existing studies, the 3DCNN outperforms musculoskeletal models based on direct collocation optimization, physics-informed GANs, and CNN-LSTM-based deep Kalman filter models when evaluated on our dataset.

Deep Learning Based Post-stroke Myoelectric Gesture Recognition: From Feature Construction to Network Design

Recently, robot-assisted rehabilitation has emerged as a promising solution to increase the training intensity of stroke patients while reducing workload on therapists, whilst surface electromyography (sEMG) is expected to serve as a viable control source. In this paper, we delve into the potential of deep learning (DL) for post-stroke hand gesture recognition by collecting the sEMG signals of eight chronic stroke subjects, focusing on three primary aspects: feature domains of sEMG (time, frequency, and wavelet), data structures (one or two-dimensional images), and neural network architectures (CNN, CNN-LSTM, and CNN-LSTM-Attention). A total of 18 DL models were comprehensively evaluated in both intra-subject testing and inter-subject transfer learning tasks, with two post-processing algorithms (Model Voting and Bayesian Fusion) analysed subsequently. Experiment results infer that for intra-subject testing, the average accuracy of CNN-LSTM using two-dimensional frequency features is the highest, reaching 72.95%. For inter-subject transfer learning, the average accuracy of CNN-LSTM-Attention using one-dimensional frequency features is the highest, reaching 68.38%. Through these two experiments, it was found that frequency features had significant advantages over other features in gesture recognition after stroke. Moreover, the post-processing algorithm can further improve the recognition accuracy, and the recognition effect can be increased by 2.03% through the model voting algorithm.

Improvement of Motor Imagination and Manual Ability Through Virtual Reality and Selective and Nonselective Functional Electrical Stimulation: Protocol for a Randomized Controlled Trial

BACKGROUND

Motor imagery (MI) is a cognitive process that has been shown to be useful in the rehabilitation process after brain injury. Moreover, functional electrical stimulation (FES) and virtual reality (VR) have also been shown to be effective interventions in many parameters, and there is some evidence of their contribution to the improvement of MI capacity.

OBJECTIVE

This study aimed to compare the improvements in MI parameters, grip strength, and manual dexterity obtained using VR, FES, and selective FES based on multifield electrodes in healthy people.

METHODS

This clinical randomized controlled trial (RCT)with 4 branches will involve 80 healthy university students, with blinded third-party assessment. Participants will be divided into 4 groups: control (no intervention), selective FES (Fesia Grasp), traditional FES (Globus Elite), and Virtual Rehab Hands (Leap Motion sensor). Each group will receive 5 daily sessions, and assessments will be conducted at baseline, postintervention, and follow-up. The Movement Imagery Questionnaire-Revised (MIQ-RS) and chronometry will be used to assess MI, strength will be measured with a digital dynamometer, and manual dexterity will be evaluated with the Nine Hole Peg Test (NHPT) and the Box and Block Test (BBT). Statistical analyses will include 2-way repeated-measures ANOVA with post hoc Bonferroni correction to compare group differences over time, with nonparametric tests (eg, Kruskal-Wallis) being used if normality or variance assumptions are violated. The study will be organized into 3 phases: preparation, data collection, and analysis. The preparation phase will involve finalizing project protocols and obtaining ethical approvals. The data collection phase will consist of recruiting participants, randomizing them into 4 intervention groups, and conducting baseline assessments, followed by intervention sessions. Finally, the analysis phase will focus on evaluating the data collected from all groups and compiling the results for presentation.

RESULTS

The study received approval in July 2023, with recruitment and data collection starting in September 2023. The recruitment phase was expected to conclude by July 2024, and the entire study, including the 2-week follow-up, was set to finish in September 2024. As of July 2024, we had enrolled 100% of the sample (N=80 students). We plan to publish the study findings by the end of 2024.

CONCLUSIONS

Improvements in MI and upper limb functionality are expected, particularly in the selective FES group. This RCT will identify which intervention is most effective in enhancing these skills, with potential benefits for patients with neurological motor disorders.

TRIAL REGISTRATION

ClinicalTrials.gov NCT06109025; https://clinicaltrials.gov/study/NCT06109025.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/63329.

The Design and Adaptive Control of a Parallel Chambered Pneumatic Muscle-Driven Soft Hand Robot for Grasping Rehabilitation

The widespread application of exoskeletons driven by soft actuators in motion assistance and medical rehabilitation has proven effective for patients who struggle with precise object grasping and suffer from insufficient hand strength due to strokes or other conditions. Repetitive passive flexion/extension exercises and active grasp training are known to aid in the restoration of motor nerve function. However, conventional pneumatic artificial muscles (PAMs) used for hand rehabilitation typically allow for bending in only one direction, thereby limiting multi-degree-of-freedom movements. Moreover, establishing precise models for PAMs is challenging, making accurate control difficult to achieve. To address these challenges, we explored the design and fabrication of a bidirectionally bending PAM. The design parameters were optimized based on actual rehabilitation needs and a finite element analysis. Additionally, a dynamic model for the PAM was established using elastic strain energy and the Lagrange equation. Building on this, an adaptive position control method employing a radial basis function neural network, optimized for parameters and hidden layer nodes, was developed to enhance the accuracy of these soft PAMs in assisting patients with hand grasping. Finally, a wearable soft hand rehabilitation exoskeleton was designed, offering two modes, passive training and active grasp, aimed at helping patients regain their grasp ability.

TouchMark: Partial Tactile Feedback Design for Upper Limb Rehabilitation in Virtual Reality

The use of Virtual Reality (VR) technology, especially in medical rehabilitation, has expanded to include tactile cues along with visual stimuli. For patients with upper limb hemiplegia, tangible handles with haptic stimuli could improve their ability to perform daily activities. Traditional VR controllers are unsuitable for patient rehabilitation in VR, necessitating the design of specialized tangible handles with integrated tracking devices. Besides, matching tactile stimulation with corresponding virtual visuals could strengthen users' embodiment (i.e., owning and controlling virtual bodies) in VR, which is crucial for patients' training with virtual hands. Haptic stimuli have been shown to amplify the embodiment in VR, whereas the effect of partial tactile stimulation from tangible handles on embodiment remains to be clarified. This research, including three experiments, aims to investigate how partial tactile feedback of tangible handles impacts users' embodiment, and we proposed a design concept called TouchMark for partial tactile stimuli that could help users quickly connect the physical and virtual worlds. To evaluate users' tactile and comfort perceptions when grasping tangible handles in a non-VR setting, various handles with three partial tactile factors were manipulated in Study 1. In Study 2, we explored the effects of partial feedback using three forms of TouchMark on the embodiment of healthy users in VR, with various tangible handles, while Study 3 focused on similar investigations with patients. These handles were utilized to complete virtual food preparation tasks. The tactile and comfort perceptions of tangible handles and users' embodiment were evaluated in this research using questionnaires and interviews. The results indicate that TouchMark with haptic line and ring forms over no stimulation would significantly enhance users' embodiment, especially for patients. The low-cost and innovative TouchMark approach may assist users, particularly those with limited VR experience, in achieving the embodiment and enhancing their virtual interactive experience.

Addressing Data Absenteeism and Technology Chauvinism in the Use of Gamified Wearable Gloves Among Older Adults: Moderated Usability Study

BACKGROUND

Digital health technologies have the potential to improve health outcomes for older adults, especially for those recovering from stroke. However, there are challenges to developing these technologies, such as data absenteeism (where older adults' views are often underrepresented in research and development) and technology chauvinism (the belief that sophisticated technology alone is the panacea to addressing health problems), which hinder their effectiveness.

OBJECTIVE

In this study, we aimed to address these challenges by developing a wearable glove integrated with culturally relevant exergames to motivate older adults to exercise and, for those recovering from stroke, to adhere to rehabilitation.

METHODS

We conducted a moderated usability study with 19 older adults, of which 11 (58%) had a history of stroke. Our participants engaged in a 30-minute gameplay session with the wearable glove integrated with exergames, followed by a quantitative survey and an in-depth interview. We used descriptive analysis to compare responses to the System Usability Scale between those who had a history of stroke and those who did not. In addition, we analyzed the qualitative interviews using a bottom-up thematic analysis to identify key themes related to the motivations and barriers regarding the use of wearable gloves for rehabilitation and exercise.

RESULTS

Our study generated several key insights. First, making the exergames exciting and challenging could improve exercise and rehabilitation motivation, but it could also have a boomerang effect, where participants may become demotivated if the games were very challenging. Second, the comfort and ease of use of the wearable gloves were important for older adults, regardless of their stroke history. Third, for older adults with a history of stroke, the functionality and purpose of the wearable glove were important in helping them with specific exercise movements.

CONCLUSIONS

Our findings highlight the importance of providing contextual support for the effective use of digital technologies, particularly for older adults recovering from stroke. In addition to technology and usability factors, other contextual factors such as gamification and social support (from occupational therapists or caregivers) should be considered to provide a comprehensive approach to addressing health problems. To overcome data absenteeism and technology chauvinism, it is important to develop digital health technologies that are tailored to the needs of underserved communities. Our study provides valuable insights for the development of digital health technologies that can motivate older adults recovering from stroke to exercise and adhere to rehabilitation.

Continuous Motion Intention Prediction Using sEMG for Upper-Limb Rehabilitation: A Systematic Review of Model-Based and Model-Free Approaches

Upper limb functional impairments persisting after stroke significantly affect patients' quality of life. Precise adjustment of robotic assistance levels based on patients' motion intentions using sEMG signals is crucial for active rehabilitation. This paper systematically reviews studies on continuous prediction of upper limb single joints and multi-joint combinations motion intention using Model-Based (MB) and Model-Free (MF) approaches over the past decade, based on 186 relevant studies screened from six major electronic databases. The findings indicate ongoing challenges in terms of subject composition, algorithm robustness and generalization, and algorithm feasibility for practical applications. Moreover, it suggests integrating the strengths of both MB and MF approaches to improve existing algorithms. Therefore, future research should further explore personalized MB-MF combination methods incorporating deep learning, attention mechanisms, muscle synergy features, motor unit features, and closed-loop feedback to achieve precise, real-time, and long-duration prediction of multi-joint complex movements, while further refining the transfer learning strategy for rapid algorithm deployment across days and subjects. Overall, this review summarizes the current research status, significant findings, and challenges, aiming to inspire future research on predicting upper limb motion intentions based on sEMG.

A review on EMG/EEG based control scheme of upper limb rehabilitation robots for stroke patients

Stroke is a common worldwide health problem and a crucial contributor to gained disability. The abilities of people, who are subjected to stroke, to live independently are significantly affected since affected upper limbs' functions are essential for our daily life. This review article focuses on emerging trends in BCI-controlled rehabilitation techniques based on EMG, EEG, or EGM + EEG signals in the last few years. Working on developing rehabilitation robotics, is considered a wealthy scientific area for researchers in the last period. There is a significant advantage that the human acquires from the interaction between the machine and his body, rehabilitation for a patient's limb is very important to get the body limb recovery, and this is what is provided mostly by applying robotic devices.

Virtual and Augmented Reality in Post-stroke Rehabilitation: A Narrative Review

Virtual reality (VR) and augmented reality (AR) are noble adjunctive technologies currently being studied for the neuro-rehabilitation of post-stroke patients, potentially enhancing conventional therapy. We explored the literature to find if VR/AR improves neuroplasticity in stroke rehabilitation for a better quality of life. This modality can lay the foundation for telerehabilitation services in remote areas. We analyzed four databases, namely Cochrane Library, PubMed, Google Scholar, and Science Direct, by searching the following keywords: ("Stroke Rehabilitation" [Majr]) AND ("Augmented Reality" [Majr]), Virtual Augmented Reality in Stroke Rehabilitation. All the available open articles were reviewed and outlined. The studies conclude that VR/AR can help in early rehabilitation and yield better results in post-stroke patients in adjunct to conventional therapy. However, due to the limited research on this subject, we cannot conclude that this information is absolute. Moreover, VR/AR was seldom customized according to the needs of stroke survivors, which would have given us the full extent of its application. Around the world, stroke survivors are being studied to verify the accessibility and practicality of these innovative technologies. Observations conclude that further exploration of the extent of the implementations and efficacy of VR and AR, combined with conventional rehabilitation, is fundamental.

Patient-Therapist Cooperative Hand Telerehabilitation through a Novel Framework Involving the Virtual Glove System

Telerehabilitation is important for post-stroke or post-surgery rehabilitation because the tasks it uses are reproducible. When combined with assistive technologies, such as robots, virtual reality, tracking systems, or a combination of them, it can also allow the recording of a patient's progression and rehabilitation monitoring, along with an objective evaluation. In this paper, we present the structure, from actors and functionalities to software and hardware views, of a novel framework that allows cooperation between patients and therapists. The system uses a computer-vision-based system named virtual glove for real-time hand tracking (40 fps), which is translated into a light and precise system. The novelty of this work lies in the fact that it gives the therapist quantitative, not only qualitative, information about the hand's mobility, for every hand joint separately, while at the same time providing control of the result of the rehabilitation by also quantitatively monitoring the progress of the hand mobility. Finally, it also offers a strategy for patient-therapist interaction and therapist-therapist data sharing.