Search Results (1,286)

Wearable electronics, particularly dry epidermal electrodes, provide human-connected interfaces for recording biopotential signals. However, their practical utility is often hindered by their limited operational longevity and the resulting environmental burden of electronic waste, as most conventional electrodes are discarded after a single use because of performance degradation. Herein, a reusable, soft, and conductive epidermal electrode is reported, fabricated through the precise incorporation of functional additives. By intentionally modulating the polymer chain architecture, a homogeneous composite is developed that exhibits exceptional flexibility, high conductivity (~100 S/cm), softness (~649 kPa), and stretchability (~234%). This molecular-level design promotes strong intermolecular interactions at the skin–electrode interface, facilitating persistent adhesion and conformability to challenging surfaces, including wet, wrinkled, and stretched skin. These properties enable reliable electrocardiography acquisition through 50 repeated attachment and detachment cycles, over which a commercial Ag/AgCl gel electrode became unmeasurable after 20. The applicability of the electrode to human–machine interfaces is further demonstrated by capturing clear electromyography signals of muscle activity during a rock–paper–scissors game. This low-modulus electrode platform offers a route towards repeated-use wearable healthcare systems and soft-robotics applications, with the potential to reduce the waste associated with single-use electrodes. Full article

Hydrogel-and-nanomaterial-integrated wearable biosensor networks are promising platforms for real-time biomedical monitoring because they combine soft biointerfaces, sensitive signal transduction, and wireless data connectivity. Hydrogels provide tissue-like softness, hydration, adhesion, permeability, and biocompatibility, whereas nanomaterials such as graphene, carbon nanotubes, MXenes, metallic nanoparticles, and conductive polymers enhance conductivity, electrochemical activity, optical responsiveness, mechanical durability, and signal amplification. This review summarizes recent advances in hydrogel-and-nanomaterial-integrated wearable biosensors, ranging from soft material interfaces and stand-alone sensing devices to wireless wearable nodes, IoT-connected platforms, and emerging closed-loop sensor–actuator systems. Because these platforms differ substantially in their level of integration and validation, this review distinguishes enabling material and device concepts from fully connected or closed-loop systems. The distinctive contribution of this review is a materials-to-systems, evidence-graded framework that links hydrogel and nanomaterial interface design with sensing mechanisms, wearable sensor-node integration, wireless and IoT connectivity, and closed-loop actuation while distinguishing device-level proof of concept from clinically validated performance. We discuss functional hydrogel design, nanomaterial-based conductive networks, hybrid hydrogel–nanomaterial structures, and key requirements for skin compatibility, adhesion, stretchability, and long-term stability. Major sensing mechanisms and biomedical targets are reviewed, including electrochemical and optical biosensing, mechanical and physiological signal sensing, and sweat biomarker monitoring. We further highlight system-level integration strategies involving wearable sensor nodes, wireless communication, smartphone and cloud connectivity, data processing, power management, security, and reliability. Representative biomedical applications are summarized, including sweat-based metabolic monitoring, smart wound monitoring, hydrogel-based wound dressings, cardiovascular and respiratory monitoring, and motion sensing. Finally, current technical and translational challenges are discussed with emphasis on the distinction between analytical sensing performance, physiological correlation, and clinical validation. Disease-management and closed-loop healthcare applications are discussed as emerging directions that require appropriate human studies, reference-method comparison, agreement analysis, long-term monitoring, and safety validation before clinical implementation. Full article

The convergence of Large Language Models (LLMs) with the Internet of Things (IoT) is driving a transformative shift toward a continuous, context-aware smart healthcare ecosystem. Due to its novelty, existing research in this domain remains fragmented, leaving a critical gap in unified frameworks that synthesize domain applications, functional AI deployment roles, network architectures, and security boundaries. Following PRISMA 2020 guidelines, this paper presents a systematic literature review and quantitative analysis evaluating a selected corpus of 61 peer-reviewed and 14 preprint papers in this domain. Methodologically, we assess a novel hybrid article discovery strategy, finding that an AI-powered prompt-based literature search strategy achieves higher precision than traditional keyword-based Boolean queries (86% vs. 42%) on the evaluated search sample, which may reduce screening workloads. We found that the major limitation of AI-based literature search is non-determinism, which is also an inherent property of LLM-powered applications. To address this, we propose methodological guidelines for using an AI-assisted hybrid literature search strategy. Based on the selected literature, we establish a multi-layer taxonomy organizing the IoT-LLM advances in the healthcare domain across four pillars: application domain, LLM role, IoT device type, and architectural deployment pattern. Quantitative synthesis reveals a heavy research concentration in remote patient monitoring and personal health management (representing 59% of the corpus combined), primarily driven by the data accessibility of wearable sensors (64%). Cross-tabulation uncovers a distinct capability–constraint spectrum: cloud-based deployments lean on heavyweight state-of-the-art models (mainly GPT-family models) for complex semantic reasoning, whereas edge, federated, and blockchain-based hybrid systems leverage localized models (BERT and LLaMA families). Patient data privacy and reduced communication overhead were among the main reasons for choosing localized models. Crucially, our assessment reveals a pervasive neglect of LLM-specific vulnerabilities such as prompt injection and jailbreak attacks and a tendency to treat regulatory frameworks (e.g., HIPAA, GDPR) as design features rather than empirically validated compliance metrics. Finally, we propose an actionable future research agenda prioritizing multi-device system orchestration, emergency care integration, privacy-preserving LLMs, and deployment-scale clinical validation. Full article

Patient recovery prediction and hospital length of stay estimation remain critical challenges in healthcare resource allocation and clinical decision-making. Inaccurate discharge planning drives substantial avoidable hospital costs, while existing machine learning models remain limited by narrow, single-domain data that fail to capture the multimodal complexity of modern smart ward environments. This study proposes IoT-ClinXAI, an explainable multimodal framework that fuses IoT environmental data, wearable physiological signals, and clinical records for accurate and transparent patient recovery prediction in smart hospital wards. A Multi-domain Hierarchical Consensus Feature-Selection method groups features into structured domains, applies Borda–Kemeny weighted consensus within each domain, and reduces cross-domain redundancy while preserving complementary information. A Snake Optimization–tuned Random Forest Regressor optimizes predictive performance through adaptive hyperparameter search, while a multi-scale SHAP framework provides global and patient-level explanations for transparent clinical inference. Experiments were conducted on a real-world IoT-enabled smart ward dataset comprising patient data and recovery duration. The proposed framework achieved strong predictive performance on the held-out test set, with $R^2$ of 0.964, RMSE of 0.476 days, MAE of 0.342 days, and MAPE of 3.13%, yielding a 23.3% RMSE reduction over the unselected baseline and outperforming all feature-selection methods by 10.9–17.6% in RMSE. Statistical superiority was consistently confirmed across all pairwise comparisons using Wilcoxon signed-rank tests with Bonferroni correction ($p<0.001$). SHAP analysis identified ward allocation, respiratory rate, and oxygen saturation as the dominant recovery predictors, while environmental IoT variables showed minimal predictive contribution. These results highlight IoT-ClinXAI as a reliable and useful framework for supporting bed management, discharge planning, and hospital resource optimization in resource-constrained healthcare settings. Full article

Wearable robotics has expanded beyond conventional exoskeletons and prosthetic devices toward compact systems that attach to or move along the human body. Within this field, on-body mobile robots have emerged as a promising platform for healthcare monitoring, haptic interaction, assistance with daily activities, rehabilitation support, and dynamic wearable interfaces. However, on-body locomotion remains challenging because local curvature changes continuously, limb diameters vary, contact is compliant, and the system must preserve user comfort while ensuring safe physical human–robot interaction. A recent study introduced an open on-limb locomotion mechanism based on spherical rollers and passive diameter adaptation. That work also revealed the need to integrate sensing, control electronics, and actuation more tightly within the wearable platform. These limitations motivate the present study, which advances a validated locomotion concept into an embedded wearable mechatronic system evaluated under more anthropomorphic conditions. To overcome these limitations, this paper presents an integrated, second-generation open on-limb robot that incorporates active steering for real-time locomotion and contact alignment. Moving beyond previous passive compliance and rigid 2D bilateral symmetry constraints, we introduce a generalized differential kinematic framework based on a complete Jacobian of the roller centers and coordinate-independent circumradius estimation. This mathematical foundation enables the system to actively leverage the geometric alignment variable as feedback for closed-loop steering corrections. Experimental results on variable-diameter surfaces demonstrate the platform’s ability to maintain longitudinal locomotion, handle non-symmetric link deflections, and perform online diameter estimation. To support reproducibility, all 3D-printable components are made openly available. Full article

PA is associated with numerous physical and mental health benefits, while self-efficacy is an important associated factor of health-related behaviors. However, evidence of the relationship between general self-efficacy and PA among healthcare students remains limited. This cross-sectional study included 747 healthcare students who completed an online survey comprising the General Self-Efficacy Scale (GSES), IPAQ-SF, and measures of PA habits. A subsample of 50 participants additionally completed one week of activity monitoring using a Fitbit Versa 4. Associations were examined using non-parametric tests, Spearman’s rank correlation analyses, and multivariable linear regression models. Higher general self-efficacy was associated with greater self-reported PA, more frequent PA habits, and better self-rated physical fitness. Self-efficacy was also weakly associated with lower sitting time during weekends, but not during working days. Bivariate associations between self-efficacy and physical activity-related measures were weak (|ρ| ≤ 0.284). Total self-reported PA remained independently associated with self-efficacy in multivariable models, while the association with exercise frequency was attenuated after accounting for self-rated physical fitness. Model explanatory power was modest (adjusted R² = 0.054–0.073). No clear associations were observed between self-efficacy and objectively measured weekly steps or active zone minutes. The agreement between self-reported and device-based measures was partial. General self-efficacy was associated with self-reported PA and perceived physical fitness, although associations were modest. Findings should be interpreted cautiously given the cross-sectional design, small monitoring subgroup, and multiple exploratory comparisons. Longitudinal studies are needed to clarify temporal relationships. Full article

With the growing demand for continuous health assessment and early disease screening, biofluids have attracted increasing attention because they provide molecular information that cannot be obtained from conventional physical signals alone. However, practical biofluid analysis remains constrained by limited sample volumes, unstable wet interfaces, complex fluid transport, and dependence on external power sources. Triboelectric nanogenerators and triboelectric nanosensors offer a promising solution by combining mechanical energy harvesting with direct signal transduction. This review provides a critical overview of the theoretical basis of triboelectric biofluid sensing, including working modes, figures of merit, charge-transfer mechanisms, and the differences between solid–solid and solid–liquid electrification. Material selection, interfacial functionalization, fluid collection, wearable configurations, and multimodal integration are further discussed. Recent applications involving sweat, tears, saliva, urine, interstitial fluid, blood, and wound exudate are summarized to clarify how triboelectric devices function as either power sources or active sensing interfaces. Particular attention is given to their potential in early screening, risk assessment, and auxiliary diagnosis. Current limitations associated with biofouling, charge dissipation, individual variability, biosafety, durability, calibration, and clinical validation are also evaluated. Finally, future directions are proposed to improve analytical reliability and accelerate the translation of self-powered biofluid sensors from laboratory prototypes to clinically meaningful healthcare platforms. Full article

Background/Objectives: Wearable devices, such as smartwatches, represent an emerging digital health tool that can enhance patient engagement, support patient-provider communication, and enable more personalized, patient-centered care. Understanding public willingness to share health-generated data with healthcare providers is essential for informing digital health implementation strategies that prioritize patient trust and active participation in the care process. This study aimed to address this gap by assessing the willingness of a sample of smartwatch users in Riyadh to share their health-generated data and identifying factors associated with this willingness. Methods: A cross-sectional study was conducted using venue-based convenience sampling at a large public venue in Riyadh, Saudi Arabia. Data were collected using an electronic self-administered questionnaire. Descriptive statistics summarized participant characteristics, while bivariate analyses and multivariable logistic regression were used to examine factors associated with willingness to share health-generated data. Results: Among the 391 participants, 168 reported owning a smartwatch and comprised the population for the primary analysis of willingness to share health-generated data. Among smartwatch owners (n = 168), 104 (62%; 95% CI: 54–69%) expressed willingness to share their health-generated data. Among those willing to share, healthcare providers were the most preferred recipients (95%, 99/104), followed by family members and friends (63%, 66/104). Most demographic, socioeconomic, health-related, and behavioral characteristics were not significantly associated with willingness to share; however, in bivariate analysis, previous use of online support groups was significantly associated with greater willingness to share health-generated data (OR 5.00; 95% CI: 1.66–15.10; p = 0.002). None of the predictors included in the multivariable model was independently associated with willingness to share. Conclusions: Most smartwatch users were willing to share their health-generated data with healthcare providers, reflecting positive public attitudes toward integrating this data into healthcare systems. These findings support Saudi Arabia’s digital health transformation initiatives, while highlighting the need to address privacy, trust, and data governance to enable successful implementation. Full article

Non-contact vital sign monitoring using millimeter-wave radar has emerged as a promising alternative to contact-based devices for continuous healthcare and elderly care applications. However, accurate heart rate estimation remains challenging because the weak cardiac-induced chest displacement is approximately an order of magnitude smaller than respiratory motion, and its fundamental frequency is frequently masked by higher-order respiratory harmonics. Here we propose a signal processing framework that addresses this challenge through three integrated stages: a slow-time phase correlation method that enhances the signal-to-noise ratio by coherently aggregating vital sign energy from adjacent range bins; an adaptive harmonic matching filtering approach based on complementary ensemble empirical mode decomposition that isolates and suppresses respiratory harmonic interference; and autocorrelation-based heart rate estimation. Experimental results obtained with a 77 GHz FMCW radar demonstrate that the proposed method achieves heart rate estimates within 5% error of reference wearable sensors in the presence of respiratory harmonics, with robustness confirmed through long-duration testing. This framework provides a practical solution for reliable radar-based heart rate monitoring without requiring subject-specific calibration or specialized hardware modifications. Full article

Soft mechanical inductive (SMI) sensors are emerging as a promising solution for advanced robotics, healthcare, and wearable devices, offering high precision, adaptability, and environmental robustness. These sensors leverage coil-based designs to achieve resilience against temperature variations, humidity, and mechanical wear, making them suitable for long-term operation in challenging environments. Existing reviews tend to focus narrowly on specific applications of coil-based inductive sensors, such as soft-robotic tactile sensing or biomedical devices, without systematically comparing design methodologies, fabrication techniques, or broader use cases, thereby lacking a unified perspective on the field. This review addresses this gap by analyzing recent developments in SMI sensors from theoretical concepts and practical design to their use cases. The review focuses on the working principles, design strategies, fabrication techniques, electronic interfaces, and, finally, the applications of coil-based SMI sensors. Key applications in soft robotics, prosthetics, and haptic devices are examined, highlighting the transformative potential of these sensors across diverse domains. Finally, the review discusses critical challenges, including sensitivity optimization, durability, and environmental interference, and outlines future directions to further advance this promising technology. Full article

Human Activity Recognition (HAR) using wearable sensor data is widely applied in healthcare, smart environments, and mobile systems. Support Vector Machines (SVMs) are commonly used for HAR due to their strong generalization ability. However, traditional approaches often rely on single kernels and may not fully capture complex motion patterns. This research presents a comparative analysis of seven SVM-based methods, including Multiclass SVMs, Radial Basis Function (RBF) SVMs, Kernel Engineering SVMs, Multiple Kernel Learning (MKL) SVMs, Class-Weighted SVMs, Least Squares SVM approximation, and Online Incremental SVMs. A unified experimental framework with consistent preprocessing and hyperparameter tuning using Grid Search with cross-validation is employed to ensure fair evaluation. Results show that kernel-based methods outperform linear and approximate models. The MKL SVM achieves the highest accuracy, slightly surpassing the RBF baseline, by combining multiple kernels to capture diverse data characteristics. Kernel Engineering SVM also improves performance, while Fuzzy and LS-SVM provide competitive results with enhanced robustness. In contrast, Multiclass and Online SVM exhibit lower accuracy. Thes results demonstrate that improving feature representation through advanced kernel design is key to enhancing HAR performance. Full article

This paper presents a wearable soft strain sensor based on a commercially available conductive thermoplastic polyurethane (cTPU) 3D-printed as an auxetic soft metamaterial for human activity recognition. The growing demand for flexible and wearable electronics, driven by advances in artificial intelligence, highlights the importance of such sensors in healthcare, medical rehabilitation, soft robotics, and human–machine interfaces. The auxetic cTPU sensor was mechanically and electrically characterized through empirical measurements and validated against numerical simulations. A single sensor mounted on a knee brace was used to collect gait signals across four activities: running, walking, standing, and sitting. Two classification approaches were investigated. A Long Short-Term Memory (LSTM) network was trained directly on the raw time-series signal, with the best configuration achieving 96% accuracy using Relative Standard Deviation Normalization with 50 hidden units. Traditional machine learning models, namely Random Forest and XGBoost, were trained on 30 extracted time-domain and frequency-domain features per motion cycle, achieving 100% and 97.33% accuracy, respectively, under five-fold cross-validation. To enhance model transparency, explainability analysis using SHAP identified power spectral density and the first harmonic frequency as the most consistently influential features across both models, with dynamic activities driven by frequency characteristics and stationary activities distinguished by signal mean amplitude. The results demonstrate that auxetic cTPU soft strain sensors combined with machine learning and explainable artificial intelligence provide an accurate and interpretable solution for wearable human activity recognition, highlighting their potential for applications in robotics, healthcare, and human–robot interfaces. Full article

Neurological disorders like Alzheimer’s disease, Parkinson’s disease, and epilepsy are becoming major causes of disability and mortality worldwide, and their prevalence is expected to rapidly increase with the aging of the population. These diseases develop silently, with irreversible neuronal damage often occurring decades before any clinical signs of illness are noticed, making early diagnosis and treatment difficult. The presymptomatic period greatly restricts the effectiveness of therapeutic interventions and reduces the possibility of disease-modifying interventions. Traditional diagnostic methods based on clinical assessment, neuroimaging, and invasive biomarkers are not sensitive enough to identify the disease at an early stage and are expensive to the healthcare system. The latest artificial intelligence (AI) technology and machine learning (ML) approaches, together with digital biomarkers obtained from eye tracking, facial expressions, speech analysis, motor dynamics, electrophysiology, wearable devices, and passive sensing, offer promising non-invasive alternatives for early detection of diseases. However, most reported performance metrics are derived from retrospective or pre-validated datasets, and prospective external validation remains limited. This narrative review synthesizes current evidence on AI-driven digital biomarkers for early detection of neurological diseases, examining disease-specific applications, methodological approaches, and challenges in clinical practices. We emphasize that clinical utility is task specific and dependent on disease stage, validation design, clinical endpoints, cost, workflow integration, and availability of disease-modifying therapies. We also note that much of the evidence summarized here derives from retrospective, case-control, or internally validated datasets and that prospective, patient-independent, and external validation with clinically meaningful endpoints remains limited. Reported performance figures should be read as proof-of-concept evidence rather than as evidence of demonstrated clinical readiness. We highlight promising future directions, including federated learning, explainable AI, and precision neurology approaches, while acknowledging that most applications remain investigational and require prospective validation before broad clinical deployment. Full article

Wearable brain-imaging devices have been developed to meet the growing demand in the healthcare industry for long-term monitoring of brain signals in natural conditions, such as monitoring brain diseases and emotions. However, conventional EEG and fNIRS (functional near-infrared spectroscopy) devices are often expensive, bulky and difficult to operate, making it difficult to monitor patients for long periods in natural conditions. To address these issues, this article proposes a low-cost, portable and multimodal wearable brain signal acquisition scheme. It combines EEG (electroencephalography) and fNIRS to reflect brain activity from different perspectives. In order to make it more wearable, a conductive rubber material is used as the electrode for the EEG. In this study, the corresponding experiments were used to verify the performance of the device. The first is the measurement of internal system noise, which satisfies the data acquisition of EEG and fNIRS at different gain levels. The α-rhythm experiment and the SSVEP (steady-state visual evoked potentials) experiment were used to validate the performance of EEG data acquisition. The performance of the fNIRS was verified by measuring changes in cerebral blood oxygen during breath-hold and breathing. In addition, by decomposing the raw fNIRS data with the VMD (variational mode decomposition) algorithm and performing correlation analysis, heart rate information was separated from the data. The performance of the proposed device was validated in the above experiments, confirming the feasibility of the design for multimodal data acquisition and meeting the requirements for portability and wearability. Furthermore, the proposed device was tested with 31 subjects (15 depressive subjects) to detect depression. Experiments proved the effectiveness of the multimodal signals, which outperformed single modal and surpassed EEG by 8.4% and fNIRS by 23.5%. Full article

Wearable technologies are reshaping gait rehabilitation by shifting assessment and therapy from intermittent, clinic-based observation to continuous, data-driven, and adaptive care. This narrative review synthesizes the biomechanical basis of gait instability, the architecture and classification of wearable rehabilitation systems, and the clinical evidence for motion sensors, smart insoles, biofeedback devices, robotic and orthotic wearables, neuromodulatory systems, immersive platforms, and artificial intelligence (AI)-enabled closed-loop interventions. Its main contribution is an integrated framework that links AI, digital biomarkers, device components, adaptive control, and translational implementation, rather than treating wearable rehabilitation as a device-only or disease-specific topic. Current evidence indicates that these technologies can improve gait speed, symmetry, balance, endurance, fall-risk monitoring, and dual-task performance in neurological, musculoskeletal, frailty-related, and aging populations. However, the field is still limited by heterogeneous protocols, small samples, limited longitudinal validation, insufficient device standardization, usability barriers, cybersecurity concerns, uncertain reimbursement, and restricted interoperability with healthcare systems. Future progress will depend on multimodal sensor fusion, explainable and federated AI, digital twins, adaptive wearable robotics, tele-rehabilitation pathways, and large-scale pragmatic trials that validate effectiveness in real-world rehabilitation settings. Full article