Search Results (266)

Accurate estimation of upper-limb joint angles is essential in biomechanics, rehabilitation, and wearable robotics. While inertial measurement units (IMUs) offer portability and flexibility, systems requiring multiple inertial sensors can be intrusive and complex to deploy. In contrast, optical motion capture (MoCap) systems provide precise tracking but are constrained to controlled laboratory environments. This study presents a deep learning-based approach for estimating shoulder and elbow joint angles using only three IMU sensors positioned on the chest and both wrists, validated against reference angles obtained from a MoCap system. The input data includes Euler angles, accelerometer, and gyroscope data, synchronized and segmented into sliding windows. Two recurrent neural network architectures, Convolutional Neural Network with Long-short Term Memory (CNN-LSTM) and Bidirectional LSTM (BLSTM), were trained and evaluated using identical conditions. The CNN component enabled the LSTM to extract spatial features that enhance sequential pattern learning, improving angle reconstruction. Both models achieved accurate estimation performance: CNN-LSTM yielded lower Mean Absolute Error (MAE) in smooth trajectories, while BLSTM provided smoother predictions but underestimated some peak movements, especially in the primary axes of rotation. These findings support the development of scalable, deep learning-based wearable systems and contribute to future applications in clinical assessment, sports performance analysis, and human motion research. Full article

Sexuality and intimacy are essential aspects of the human experience for all people, contributing significantly to physical and emotional connections, well-being, and quality of life. Despite their importance, these topics are frequently overlooked in stroke rehabilitation, especially for those with cognitive and perceptual impairments. Existing research on post-stroke sexual rehabilitation tends to focus on sexual dysfunction and the secondary physical and psychological stroke symptoms, with little attention to cognitive and perceptual impairments. Cognitive deficits, such as decreased memory, generalized attention, and executive function not only can hinder sexual participation but also raise the complex issue of capacity to consent. This paper argues that it is imperative for researchers and healthcare practitioners to address cognitive and perceptual challenges, understand consent laws in their respective regions, and consider the influence of culture and social norms in order to support the sexual rights and well-being of all stroke survivors. Furthermore, this article provides some practical recommendations, from an occupational therapy perspective, that healthcare practitioners can provide to clients and their partners. Full article

Objectives: To investigate whether a Multimodal Rehabilitation Program (MRP) affects the change in visual–spatial abilities, especially attention, information-processing speed, visual–spatial learning, the severity of depression, and strategies for coping with pain in Complex Regional Pain Syndrome (CRPS) participants. Methods: The study was conducted between October 2021 and February 2023, with a 4-week rehabilitation program that included individual physiotherapy, manual and physical therapy, and psychological intervention such as psychoeducation, relaxation, and Graded Motor Imagery therapy. Twenty participants with CRPS and twenty healthy participants, forming a control group, were enlisted. The study was a 2-arm parallel: a CRPS group with MRP intervention and a healthy control group matched to the CRPS group according to demographic variables. Before and after, the MRP participants in the CRPS group were assessed for visual–spatial learning, attention abilities, severity of depression, and pain-coping strategy. The healthy control group underwent the same assessment without intervention before two measurements. The primary outcome measure was Reproduction on Rey–Osterrieth’s Complex Figure Test assessing visual–spatial learning. Results: In the post-test compared to the pre-test, the participants with CRPS obtained a significantly high score in visual–spatial learning (p < 0.01) and visual information-processing speed (p = 0.01). They made significantly fewer omission mistakes in visual working memory (p = 0.01). After the MRP compared to the pre-test, the CRPS participants indicated a decrease in the severity of depression (p = 0.04) and used a task-oriented strategy for coping with pain more often than before the rehabilitation program (p = 0.02). Conclusions: After a 4-week MRP, the following outcomes were obtained: an increase in visual–spatial learning, visual information-processing speed, a decrease in severity of depression, and a change in the pain-coping strategies—which became more adaptive. Full article

Human Activity Recognition (HAR) using wearable sensor data is increasingly important in healthcare, rehabilitation, and smart monitoring. This study systematically compared three dynamic neural network architectures—Finite Impulse Response Neural Network (FIRNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU)—to examine their suitability and specificity for HAR tasks. A controlled experimental setup was applied, training 16,500 models across different delay lengths and hidden neuron counts. The investigation focused on classification accuracy, computational cost, and model interpretability. LSTM achieved the highest classification accuracy (98.76%), followed by GRU (97.33%) and FIRNN (95.74%), with FIRNN offering the lowest computational complexity. To improve model transparency, Layer-wise Relevance Propagation (LRP) was applied to both input and hidden layers. The results showed that gyroscope Y-axis data was consistently the most informative, while accelerometer Y-axis data was the least informative. LRP analysis also revealed that GRU distributed relevance more broadly across hidden units, while FIRNN relied more on a small subset. These findings highlight trade-offs between performance, complexity, and interpretability and provide practical guidance for applying explainable neural wearable sensor-based HAR. Full article

This paper presents a Self-Learning Robotic System (SLRS) for healthcare assistance using Deep Imitation Learning (DIL). The proposed SLRS solution can observe and replicate human demonstrations, thereby acquiring complex skills without the need for explicit task-specific programming. It incorporates modular components for perception (i.e., advanced computer vision methodologies), actuation (i.e., dynamic interaction with patients and healthcare professionals in real time), and learning. The innovative approach of implementing a hybrid model approach (i.e., deep imitation learning and pose estimation algorithms) facilitates autonomous learning and adaptive task execution. The environmental awareness and responsiveness were also enhanced using both a Convolutional Neural Network (CNN)-based object detection mechanism using YOLOv8 (i.e., with 94.3% accuracy and 18.7 ms latency) and pose estimation algorithms, alongside a MediaPipe and Long Short-Term Memory (LSTM) framework for human action recognition. The developed solution was tested and validated in healthcare, with the aim to overcome some of the current challenges, such as workforce shortages, ageing populations, and the rising prevalence of chronic diseases. The CAD simulation, validation, and verification tested functions (i.e., assistive functions, interactive scenarios, and object manipulation) of the system demonstrated the robot’s adaptability and operational efficiency, achieving an 87.3% task completion success rate and over 85% grasp success rate. This approach highlights the potential use of an SLRS for healthcare assistance. Further work will be undertaken in hospitals, care homes, and rehabilitation centre environments to generate complete holistic datasets to confirm the system’s reliability and efficiency. Full article

Stroke is one of the leading causes of long-term disability worldwide, often resulting in motor impairments that limit the ability to perform daily activities independently. Conventional rehabilitation exoskeletons, while effective, are typically rigid, bulky, and expensive, limiting their usability outside of clinical settings. In response to these challenges, this work presents the development and validation of a novel soft exosuit designed for elbow flexion rehabilitation, incorporating a multi-wire Shape Memory Alloy (SMA) actuator capable of both position and force control. The proposed system features a lightweight and ergonomic textile-based design, optimized for user comfort, ease of use, and low manufacturing cost. A sequential activation strategy was implemented to improve the dynamic response of the actuator, particularly during the cooling phase, which is typically a major limitation in SMA-based systems. The performance of the multi-bundle actuator was compared with a single-bundle configuration, demonstrating superior trajectory tracking and reduced thermal accumulation. Surface electromyography tests confirmed a decrease in muscular effort during assisted flexion, validating the device’s assistive capabilities. With a total weight of 0.6 kg and a fabrication cost under EUR 500, the proposed exosuit offers a promising solution for accessible and effective home-based rehabilitation. Full article

Stroke-induced hand dysfunction substantially impairs patients’ quality of life, creating an urgent need for portable, adaptive rehabilitation devices. This study introduces a smart rehabilitation glove actuated by shape-memory alloy (SMA) wires, leveraging their high power-to-weight ratio, controllable strain recovery, and reversible phase transformation to overcome the limitations of conventional motor-driven or pneumatic gloves. The glove incorporates SMA-based actuation units achieving 50 mm contraction (5% strain) within 7 s, enabling finger flexion to ~34° for personalized rehabilitation protocols. A mobile application provides wireless regulation of SMA actuation modes and facilitates real-time telemedicine consultations. The prototype demonstrates an ultra-lightweight, compact design enabled by SMA’s intrinsic properties, offering a promising solution for home-based post-stroke rehabilitation. This work establishes the transformative potential of SMAs in wearable biomedical technologies. Full article

Background/Objective: Parkinson’s disease (PD) is characterized by motor and cognitive impairments that significantly affect quality of life. Robotic-assisted therapies, such as the AMADEO^® system, have shown potential in rehabilitating upper limb function but are underexplored in PD. This study aimed to assess the effects of Robotic-Assisted Therapy (RAT) compared to Conventional Physical Therapy (CPT) on cognitive, motor, and functional outcomes in PD patients. Methods: A single-blind, randomized controlled trial was conducted with PD patients allocated to RAT or CPT. Participants were assessed at baseline (T0) and post-intervention (T1) using measures including MoCA, FAB, UPDRS-III, 9-Hole Peg Test, FMA-UE, FIM, and PDQ-39. Statistical analyses included ANCOVA and regression models. Results: RAT led to significant improvements in global cognition (MoCA, p < 0.001) and executive functioning (FAB, p = 0.0002) compared to CPT. Motor function improved, particularly in wrist and hand control (FMA-UE), whereas changes in fine motor dexterity (9-Hole Peg Test) were less consistent and did not reach robust significance. No significant improvements were observed in broader quality of life domains, depressive symptoms, or memory-related cognitive measures. However, quality of life improved significantly in the stigma subdomain of the PDQ-39 (p = 0.0075). Regression analyses showed that baseline motor impairment predicted cognitive outcomes. Conclusions: RAT demonstrated superior cognitive and motor benefits in PD patients compared to CPT. These results support the integration of robotic rehabilitation into PD management. Further studies with larger sample sizes and long-term follow-up are needed to validate these findings and assess their sustainability. Full article

Background/Objectives: This study explores the integration of wearable sensors and artificial intelligence (AI) for Human Activity Recognition (HAR) in the diagnosis and rehabilitation of Parkinson’s disease (PD). The objective was to develop a proof-of-concept model based on internal reproducibility, without external generalization, that is capable of distinguishing pathological movements from healthy ones while ensuring clinical relevance and patient safety. Methods: Nine subjects, including eight patients with Parkinson’s disease and one healthy control, were included. Motion data were collected using the Motigravity platform, which integrates inertial sensors in a controlled environment. The signals were automatically segmented into fixed-length windows, with poor-quality segments excluded through preprocessing. A hybrid CNN-LSTM (Convolutional Neural Networks—Long Short-Term Memory) model was trained to classify motion patterns, leveraging convolutional layers for spatial feature extraction and LSTM layers for temporal dependencies. The Motigravity system provided a controlled hypogravity environment for data collection and rehabilitation exercises. Results: The proposed CNN-LSTM model achieved a validation accuracy of 100%, demonstrating classification potential. The Motigravity system contributed to improved data reliability and ensured patient safety. Despite increasing class imbalance in extended experiments, the model consistently maintained perfect accuracy, suggesting strong generalizability after external validation to overcome the limitations. Conclusions: Integrating AI and wearable sensors has significant potential to improve the HAR-based classification of movement impairments and guide rehabilitation strategies in PD. While challenges such as dataset size remain, expanding real-world validation and enhancing automated segmentation could further improve clinical impact. Future research should explore larger cohorts, extend the model to other neurodegenerative diseases, and evaluate its integration into clinical rehabilitation workflows. Full article

Chronic pain is a significant burden affecting more than 30% of people worldwide. Within the multiple biopsychosocial factors affected in people suffering from chronic pain, neurocognitive impairments represent a significant but often under-recognized aspect of the chronic pain experience that impacts daily life and healthcare. Multiple neurocognitive domains, including attention, executive function, learning, and memory, have been commonly associated with chronic pain. Within novel approaches, extended reality (XR) has been highlighted for its potential in chronic pain management. XR offers unique features to enhance traditional neurocognitive interventions, including dual tasks, gamification, ecological validity, and enriched experience, to increase engagement and motivation in rehabilitation. This systematic–narrative hybrid literature review aims to shed light on the potential benefits, challenges, and future directions of XR technology to address neurocognitive impairments associated with chronic pain. While preliminary evidence suggests that XR-based neurocognitive training may be beneficial in overcoming neurocognitive impairments found in chronic pain, some challenges still need to be addressed for effective translation into clinical practice. Within a transdiagnostic approach, XR-based neurocognitive training appears to be valuable across different diagnoses in chronic pain, wherein XR may emerge as a promising first-line intervention toward personalized multimodal management for chronic pain. Despite the rapid development of substantial growing evidence for XR, enhanced methodological rigor and reporting quality are recommended in future studies. More research is needed to fully understand the mechanisms and optimal application of XR-based neurocognitive training in different chronic pain conditions. Full article

Upper limb assistive exoskeletons help stroke patients by assisting arm movement in impaired individuals. However, effective control of these systems to help stroke survivors is a complex task. In this paper, a novel approach is proposed to enhance the control of upper limb assistive exoskeletons by using torque estimation and prediction in a proportional–integral–derivative (PID) controller loop to more optimally integrate the torque of the exoskeleton robot, which aims to eliminate system uncertainties. First, a model for torque estimation from Electromyography (EMG) signals and a predictive torque model for the upper limb exoskeleton robot for the elbow are trained. The trained data consisted of two-dimensional high-density surface EMG (HD-sEMG) signals to record myoelectric activity from five upper limb muscles (biceps brachii, triceps brachii, anconeus, brachioradialis, and pronator teres) during voluntary isometric contractions for twelve healthy subjects performing four different isometric tasks (supination/pronation and elbow flexion/extension) for one minute each, which were trained on long short-term memory (LSTM), bidirectional LSTM (BLSTM), and gated recurrent units (GRU) deep neural network models. These models estimate and predict torque requirements. Finally, the estimated and predicted torque from the trained network is used online as input to a PID control loop and robot dynamic, which aims to control the robot optimally. The results showed that using the proposed method creates a strong and innovative approach to greater independence and rehabilitation improvement. Full article

Background/Objectives: Mild Cognitive Impairment (MCI) represents a clinical syndrome characterized by cognitive decline greater than expected for an individual’s age and education level but not severe enough to significantly interfere with daily activities, with variable trajectories that may remain stable, progress to dementia, or occasionally revert to normal cognition. This systematic review examines neurotechnological approaches to cognitive rehabilitation in MCI populations, including neuromodulation, electroencephalography (EEG), virtual reality (VR), cognitive training, physical exercise, and artificial intelligence (AI) applications. Methods: A systematic review following PRISMA guidelines was conducted on 34 empirical studies published between 2014 and 2024. Studies were identified through comprehensive database searches and included if they employed neurotechnological interventions targeting cognitive outcomes in individuals with MCI. Results: Evidence indicates promising outcomes across multiple intervention types. Neuromodulation techniques showed beneficial effects on memory and executive function. EEG analyses identified characteristic neurophysiological markers of MCI with potential for early detection and monitoring. Virtual reality enhanced assessment sensitivity and rehabilitation engagement through ecologically valid environments. Cognitive training demonstrated the most excellent efficacy with multi-domain, adaptive approaches. Physical exercise interventions yielded improvements through multiple neurobiological pathways. Emerging AI applications showed potential for personalized assessment and intervention through predictive modeling and adaptive algorithms. Conclusions: Neurotechnological approaches offer promising avenues for MCI rehabilitation, with the most substantial evidence for integrated interventions targeting multiple mechanisms. Neurophysiological monitoring provides valuable biomarkers for diagnosis and treatment response. Future research should focus on more extensive clinical trials, standardized protocols, and accessible implementation models to translate these technological advances into clinical practice. Full article

Background: Chronic pain affects a significant proportion of the population in the United States and poses a significant public health concern. Beyond physical discomfort, chronic pain has been increasingly linked to cognitive dysfunction, including impairments in memory, attention, executive function, and decision-making. The relationship is particularly pronounced in older adults and may contribute to the onset or progression of neurodegenerative diseases. Objective: This comprehensive review explores the relationship between chronic pain and cognitive function, emphasizing the underlying neurobiological mechanisms, structural brain changes, and associated comorbidities. Methods: A review was conducted using peer-reviewed studies that began with the earliest pain and cognition mechanisms, followed by further investigation of cognitive effects of chronic pain, neuroimaging findings, and comorbid neuropsychiatric and neurodegenerative conditions. Sources included large-scale cohort studies, functional MRI analyses, and neurobiological investigations focusing on prefrontal cortex activity, default mode network alterations, and gray matter atrophy. Results: Chronic pain is associated with cognitive deficits through multiple converging pathways. It contributes to measurable impairments in cognitive function and is linked to structural and functional brain alterations. Regions of interest include the dorsolateral prefrontal cortex, medial prefrontal cortex, and default mode network, which can be connected to the neural resource hypothesis because of their cognitive domain impairments. A better understanding of these mechanisms highlights the importance of early recognition and multidisciplinary management strategies, including neuromodulation and cognitive rehabilitation. Future research should prioritize longitudinal studies and integrated interventions targeting both pain and cognitive health. Full article

Fibromyalgia is a condition that primarily affects women and compromises the quality of life (QoL), life satisfaction (SWL), mental health and cognitive function of sufferers. This study aimed to analyze the effects of a physical activity program based on Virtual Square Step Exercise on the above conditions in women with FM. A 12-week randomized controlled trial was designed with 61 women with FM assigned to a control group (CTL) and an experimental group (VSEE). The VSSE group performed VSSE sessions three times a week for 12 weeks, while the CTL continued with their usual treatment. The applicability and safety of the program was tested in this population. In addition, the participants’ QoL, SWL, mental health status, and cognitive function were assessed before and after the intervention program using different questionnaires and tests. VSEE was found to be applicable (with adherence greater than 85%) and safe (with no accidents, injuries, or health-compromising incidents) in women with FM. The VSEE showed a significant reduction in self-perceived depressive symptoms compared to the control group (p < 0.05). In contrast, no significant changes in QoL, SWL, mental health and cognitive function were observed in the VSEE compared to the CTL (p > 0.05). Therefore, even though our VSEE-based intervention was found to be applicable and safe in women with FM, it did not produce significant changes in improving QoL, SWL, mental health, and cognitive function in our sample. The small sample size and post-pandemic context may have affected the findings. More research with a larger sample size is needed to confirm the effects and applicability of VSEE in women with FM. Full article

Recent technological advances have introduced novel therapeutic interventions for Alzheimer’s disease (AD). This study introduces a novel virtual reality (VR) intervention consisting of aesthetically pleasing and relaxing immersive videos paired with evocative music for patients with or without cognitive decline. The goal of this intervention is to improve the mood, evoke autobiographical memories in, and enhance the overall well-being of elderly individuals, across stages of cognitive decline (from absent to severe). Twenty-one elderly participants (5 cognitively healthy, 13 with a mild cognitive decline, 2 with a moderate decline, and 1 with a severe decline) were exposed to immersive 360-degree videos depicting both familiar and unfamiliar, pleasant and calming environments, accompanied by emotionally evocative, pleasant, and soothing music. The results demonstrated high levels of immersion and predominantly positive emotional responses, with several participants reporting autobiographical memory recall triggered by the VR stimulation. Statistical analysis revealed a significant improvement in mood over time, regardless of cognitive status, supporting the effectiveness of the intervention. While there were some side effects of fatigue or transient anxiety, the experience was generally perceived as engaging and meaningful. This feasibility study adds to the acceptability and potential clinical utility of VR interventions and provides a justification for future larger trials aimed at the integration of immersive technologies into cognitive rehabilitation interventions for individuals at different stages of cognitive decline. Full article