A Review of Hand Function Rehabilitation Systems Based on Hand Motion Recognition Devices and Artificial Intelligence

Continuous reach-to-grasp motion recognition based on an extreme learning machine algorithm using sEMG signals

Recognizing user intention in reach-to-grasp motions is a critical challenge in rehabilitation engineering. To address this, a Machine Learning (ML) algorithm based on the Extreme Learning Machine (ELM) was developed for identifying motor actions using surface Electromyography (sEMG) during continuous reach-to-grasp movements, involving multiple Degrees of Freedom (DoFs). This study explores feature extraction methods based on time domain and autoregressive models to evaluate ELM performance under different conditions. The experimental setup encompassed variations in neuron size, time windows, validation with each muscle, increase in the number of features, comparison with five conventional ML-based classifiers, inter-subjects variability, and temporal dynamic response. To evaluate the efficacy of the proposed ELM-based method, an openly available sEMG dataset containing data from 12 participants was used. Results highlight the method's performance, achieving Accuracy above 85%, F-score above 90%, Recall above 85%, Area Under the Curve of approximately 84% and compilation times (computational cost) of less than 1 ms. These metrics significantly outperform standard methods (p < 0.05). Additionally, specific trends were found in increasing and decreasing performance in identifying specific tasks, as well as variations in the continuous transitions in the temporal dynamics response. Thus, the ELM-based method effectively identifies continuous reach-to-grasp motions through myoelectric data. These findings hold promise for practical applications. The method's success prompts future research into implementing it for more reliable and effective Human-Machine Interface (HMI) control. This can revolutionize real-time upper limb rehabilitation, enabling natural and complex Activities of Daily Living (ADLs) like object manipulation. The robust results encourages further research and innovative solutions to improve people's quality of life through more effective interventions.

Three-Dimensional Magnetic Rehabilitation, Robot-Enhanced Hand-Motor Recovery after Subacute Stroke: A Randomized Controlled Trial

We developed an end-effector-type rehabilitation robot that can uses electro- and permanent magnets to generate a three-way magnetic field to assist hand movements and perform rehabilitation therapy. This study aimed to investigate the therapeutic effect of a rehabilitation program using a three-dimensional (3D) magnetic force-based hand rehabilitation robot on the motor function recovery of the paralyzed hands of patients with stroke. This was a double-blind randomized controlled trial in which 36 patients with subacute stroke were assigned to intervention and control groups of 18 patients each. The intervention group received 30 min of rehabilitation therapy per day for a month using a 3D magnetic force-driven hand rehabilitation robot, whereas the control group received 30 min of conventional occupational therapy to restore upper-limb function. The patients underwent three behavioral assessments at three time points: before starting treatment (T0), after 1 month of treatment (T1), and at the follow-up 1-month after treatment completion (T2). The primary outcome measure was the Wolf Motor Function Test (WMFT), and secondary outcome measures included the Fugl-Meyer Assessment of the Upper Limb (FMA_U), Modified Barthel Index (MBI), and European Quality of Life Five Dimensions (EQ-5D) questionnaire. No participant safety issues were reported during the intervention. Analysis using repeated measures analysis of variance showed significant interaction effects between time and group for both the WMFT score (p = 0.012) and time (p = 0.010). In post hoc analysis, the WMFT scores and time improved significantly more in the patients who received robotic rehabilitation at T1 than in the controls (p = 0.018 and p = 0.012). At T2, we also consistently found improvements in both the WMFT scores and times for the intervention group that were superior to those in the control group (p = 0.024 and p = 0.018, respectively). Similar results were observed for FMA_U, MBI, and EQ-5D. Rehabilitation using the 3D hand-rehabilitation robot effectively restored hand function in the patients with subacute stroke, contributing to improvement in daily independence and quality of life.

The Use of Sports Rehabilitation Robotics to Assist in the Recovery of Physical Abilities in Elderly Patients with Degenerative Diseases: A Literature Review

The increase in the number of elderly patients with degenerative diseases has brought additional medical and financial pressures, which are adding to the burden on society. The development of sports rehabilitation robotics (SRR) is becoming increasingly sophisticated at the technical level of its application; however, few studies have analyzed how it works and how effective it is in aiding rehabilitation, and fewer individualized exercise rehabilitation programs have been developed for elderly patients. The purpose of this study was to analyze the working methods and the effects of different types of SRR and then to suggest the feasibility of applying SRR to enhance the physical abilities of elderly patients with degenerative diseases. The researcher's team searched 633 English-language journal articles, which had been published over the past five years, and they selected 38 of them for a narrative literature review. Our summary found the following: (1) The current types of SRR are generally classified as end-effector robots, smart walkers, intelligent robotic rollators, and exoskeleton robots-exoskeleton robots were found to be the most widely used. (2) The current working methods include assistant tools as the main intermediaries-i.e., robots assist patients to participate; patients as the main intermediaries-i.e., patients dominate the assistant tools to participate; and sensors as the intermediaries-i.e., myoelectric-driven robots promote patient participation. (3) Better recovery was perceived for elderly patients when using SRR than is generally achieved through the traditional single-movement recovery methods, especially in strength, balance, endurance, and coordination. However, there was no significant improvement in their speed or agility after using SRR.

Artificial Intelligence in Public Health: Current Trends and Future Possibilities

Artificial intelligence (AI) is a discipline that studies whether and how intelligent computer systems that can simulate the capacity and behaviour of human thought can be created [...]