Search Results (38)

Non-contact blood pressure (BP) estimation from remote photoplethysmography (rPPG) can yield unstable window-level predictions. This study combines a pulse-feature long short-term memory (LSTM) estimator with temporal variance-based prediction filtering. Fifty-two features from the rPPG waveform and its first and second derivatives were arranged into sliding-window sequences for systolic BP (SBP) and diastolic BP (DBP) estimation. The filter selects locally stable predictions from temporally ordered prediction sequences without using ground-truth BP values. Performance was first assessed in 10 repeated subject-dependent randomized-block experiments. Filtering reduced the SBP mean absolute error (MAE) from $7.04\pm 1.52$ to $5.34\pm 1.62$ mmHg and the DBP MAE from $4.63\pm 1.32$ to $3.07\pm 0.97$ mmHg while retaining $76.39\pm 7.59\%$ of predictions. A subject-specific mean predictor was also competitive under the subject-dependent setting and achieved lower DBP MAE at full coverage than the filtered LSTM. Chronological rolling-origin and leave-one-subject-out (LOSO) evaluations further showed that the improvement persisted for later intervals from the same subjects but not for unseen subjects. Because the filter operates only on model outputs, it requires neither additional trainable parameters nor model retraining. These findings show a low-overhead accuracy–coverage trade-off for within-subject rPPG-based BP estimation, while subject-independent generalization remains limited. Full article

Background/Objectives: Chiropractors serve as first-contact practitioners in South Africa and frequently encounter patients with systemic conditions that may mimic musculoskeletal complaints. Non-musculoskeletal (non-MSK) examinations are essential for identifying red flags, ruling out serious pathologies, and facilitating timely referrals. Despite their importance for patient safety and integration into primary healthcare, limited research exists on the frequency with which South African chiropractors perform these assessments. This study aimed to describe the frequency and indications for non-MSK examinations performed by South African chiropractors and to explore variations across examination types, demographic factors, years of experience, and training institutions in secondary analyses. Methods: A cross-sectional online survey was distributed to 898 registered chiropractors, yielding 186 responses (20.7%). The questionnaire assessed the frequency of non-MSK examinations using a five-point Likert scale. Data were analysed using descriptive statistics (frequencies, percentages, medians, interquartile ranges). Exploratory subgroup comparisons were conducted using nonparametric tests, but these findings should be interpreted with caution due to small and uneven sample sizes in some subgroups. Ethical approval was obtained (REC-3366-2025). Results: Most respondents were female (57.5%) and practising in Gauteng (49.5%). Blood pressure (84.4%) and heart rate (81.2%) were the most frequently performed examinations, while respiratory rate (12.4%), oxygen saturation (9.7%), and temperature (11.8%) were the least frequently performed vital signs. Breast (3.8%), abdominal (10.2%), and genitourinary (1.1%) examinations were rarely conducted. Exploratory subgroup observations suggested provincial variation: chiropractors in KwaZulu-Natal performed non-MSK examinations more frequently than those in Gauteng and the Western Cape (mean differences ranging from 0.21 to 1.19 on a five-point scale), whereas no meaningful differences were found across years in practice. Conclusions: South African chiropractors perform a selective range of non-MSK examinations, supporting their role as first-contact practitioners. However, many systemic examinations are conducted infrequently, with observed provincial variation. These descriptive findings highlight the need for greater consistency and standardisation in non-MSK screening to enhance patient safety and interdisciplinary care. Future adequately powered studies are needed to confirm the exploratory subgroup observations. Full article

Hypertension is a major global health issue, and continuous, convenient blood pressure monitoring is of great significance for early screening and intervention. To address the insufficient exploitation of multi-scale temporal features and the high model complexity in existing radar-based non-contact blood pressure prediction methods, we propose a lightweight temporal multi-scale feature fusion network (LULMNet), for blood pressure prediction and waveform reconstruction. LULMNet adopts a two-stage training strategy. In the first stage, a lightweight one-dimensional U-Net (1D U-Net) is employed for blood pressure waveform reconstruction and intermediate-to-deep temporal feature extraction. In the second stage, systolic and diastolic blood pressure are estimated via multi-scale fusion of intermediate and deep features from the encoder of the 1D U-Net, followed by LSTM-based temporal modeling and regression through a global average pooling (GAP)and a two-layer fully connected prediction head. Experimental results show that the proposed model achieves an error of 3.21 ± 4.94 mmHg for systolic blood pressure (SBP) and 2.25 ± 3.39 mmHg for diastolic blood pressure (DBP), satisfying the Grade A standard of the British Hypertension Society (BHS). In addition, the normalized mean absolute error (NMAE) for waveform reconstruction is as low as 0.044. These results indicate that the proposed method maintains low model complexity while ensuring prediction accuracy, with only 3.0 M parameters and 0.37 G floating-point operations (FLOPs), demonstrating strong potential for non-contact continuous blood pressure monitoring. Full article

Fieldwork carries a high risk of irregular, non-compressible traumatic wounds, which often initiate a vicious cycle of “traumatic bleeding-insect bite-secondary infection”. Conventional dressings cannot combine rapid hemostasis with physical protection against venomous insects, creating an urgent demand for multifunctional field trauma dressings. To solve this problem, this study developed a shape-adaptive bilayer hydrogel that concurrently provides rapid hemostasis, promotes wound repair, and acts as a robust physical barrier. The hydrogel adopts a layered design: the bottom layer (PPTY) achieves autogelation within 3 s upon blood contact, while the top armor protective layer (AP) withstands pressures up to 942 kPa. By incorporating chitosan and sodium citrate into the AP precursor solution, the hydrogel achieved in situ formation within 50 s and developed a stable self-renewing armor layer. The tightly bonded bilayer showed complementary functions. In rat models of femoral artery puncture and tail vein bleeding, PPTY-AP hydrogel significantly reduced blood loss and shortened hemostasis time. Moreover, the hydrogel demonstrated excellent tissue adhesion and moisture retention capacity, promoting full-thickness skin wound healing. This multifunctional, rapidly deployable hydrogel presents a promising solution for field trauma management and offers a new design paradigm for advanced wound dressings. Full article

Continuous blood pressure (BP) monitoring is essential for the prevention and management of cardiovascular diseases. Traditional cuff-based methods cause discomfort during repeated measurements, and wearable sensors require direct skin contact, limiting their applicability. Radar-based contactless BP measurement has emerged as a promising alternative. However, radar pulse wave (RPW) signals are susceptible to motion artifacts, respiratory interference, and environmental clutter, posing persistent challenges to estimation accuracy and robustness. In this paper, we propose MARU-MTL, a Mamba-enhanced multi-task learning framework for continuous BP estimation using a single millimeter-wave radar sensor. To address signal quality degradation, a Variational Autoencoder-based Signal Quality Index (VAE-SQI) mechanism is proposed to automatically screen RPW segments without manual annotation. To capture long-range temporal dependencies across cardiac cycles, we integrate a Bidirectional Mamba module into the bottleneck of a U-Net backbone, enabling linear-time sequence modeling with respect to the segment length. We also introduce a multi-task learning strategy that couples BP regression with arterial blood pressure waveform reconstruction to strengthen physiological consistency. Extensive experiments on two datasets comprising 55 subjects demonstrate that MARU-MTL achieves mean absolute errors of 3.87 mmHg and 2.93 mmHg for systolic and diastolic BP, respectively, meeting commonly used AAMI error thresholds and achieving metrics comparable to BHS Grade A. Full article

Intelligent driving cabins operated by artificial intelligence technology are evolving into the third living space. They aim to integrate perception, analysis, decision making, and intervention. By using multimodal biosignal acquisition technologies (flexible sensors and non-contact sensing), it is possible to monitor the physiological indicators of heart rate and blood pressure in real time. Leveraging the benefits of domain controllers in the vehicle and edge computing helps the AI platform reduce data latency and enhance real-time processing capabilities, as well as integrate the cabin’s internal and external data through machine learning. Its aim is to build tailored health baselines and high-precision risk prediction models (e.g., CNN, LSTM). This system can initiate multi-level interventions such as adjustments to the environment, health recommendations, and ADAS-assisted emergency parking with telemedicine help. Current issues consist of sensor precision, AI model interpretation, security of data privacy, and whom to attribute legal liability to. Future development will mainly focus on cognitive digital twin construction, L4/L5 autonomous driving integration, new biomedical sensor applications, and smart city medical ecosystems. Full article

Microchannels can create disturbed flow patterns by altering pressure gradients, shear forces, and flow symmetry, which are essential in the design of microfluidic devices and, hence, blood-contacting devices. The effect of asymmetric stenosis on pressure, wall shear stress, and velocity in rectangular and circular microchannels with same operating conditions was analyzed in this study using three-dimensional (3D) steady laminar computational fluid dynamics (CFD) simulations. Asymmetric flow patterns induced by asymmetric stenosis are of particular importance and remain underexplored, especially in the context of multiple constrictions. This is, to our knowledge, is the first systematic CFD comparison of multiple asymmetric stenoses in circular microchannels directly contrasted with rectangular and single-stenosis cases under identical settings. Several parameters, such as wall shear stress (WSS), pressure, and velocity distributions, were analyzed in various stenotic and non-stenotic geometries. These microchannel models, while not reflecting real blood vessels themselves nor exhibiting wall compliance, pulsatility, or non-Newtonian rheology, replicate important mechanical characteristics of stenosis-mediated flow disturbance. Single and multiple asymmetric stenoses create flow patterns that are similar to those of vascular pathologies. For this reason, these channels should be considered as simplified device-scale models of vascular phenomena as opposed to realistic, in vitro vascular models. The results showed that asymmetric stenosis creates asymmetric velocity peaks and elevated WSS, which are more evident in the case of circular configurations with double asymmetric stenosis. The findings will help design microfluidic devices that mimic unstable flow characteristics that occur in stenotic conditions, and assist in testing clinical devices. In this study, two fabrication-ready microchannel designs under fixed operating conditions (identical inlet velocity and fluid properties) that reflect common microfluidic use were compared. Consequently, all pressure, velocity, and WSS outcomes are interpreted as device-scale responses under fixed velocity, rather than a fundamental isolation of cross-section shape, which would require matched hydraulic diameters or flow rates. This study is explicitly device-oriented, representing a fixed operating point rather than a strict geometric isolation. Accordingly, the results are also expressed with dimensionless loss coefficients (Ktot and Klocal) to enable scale-independent, device-level comparison. Full article

Background and objectives: Numerous studies and meta-analyses have established the efficacy of telemonitoring for blood pressure and other components of metabolic syndrome in improving disease management. Nevertheless, the adoption of telemonitoring technologies is often hindered by personal, technological, and systemic barriers. In Slovakia, where patient–physician contact rates are high, there is limited research on patients’ perspectives regarding telemedicine adoption for cardiovascular risk management. The objective of this study was to examine patients’ perspectives on and perceived obstacles to the use of telemonitoring for arterial hypertension and dyslipidemia in Slovakia. Methods: This cross-sectional, questionnaire-based survey targeted a cohort of 18,053 patients. The survey instrument was designed to gather data on several key areas: patient demographic characteristics, blood pressure measurement habits, the utilization of smart technologies, perceived benefits and barriers to telemonitoring, and patients’ knowledge of their lipid profiles and cardiovascular risk factors. Statistical analysis included chi-square tests, ANOVA, and effect size calculations with 95% confidence intervals (CI). Results: A total of 1787 patient responses (9.9%) were collected. Among the respondents, 67.4% (n = 1204) had arterial hypertension, while 7.9% (n = 95) were on non-pharmacological therapy. Only 21.2% (n = 255) of hypertensive patients measured their blood pressure daily, with a significantly higher proportion of men than women (28.6% vs. 12.7%, p = 0.011, Cohen’s d = 0.42). The most frequent users of blood pressure monitoring were in the 31–45 age group (p = 0.001, η² = 0.08). A total of 19.4% (n = 347) of respondents used wearable devices, and 6.3% (n = 113) used blood pressure monitors connected to an application. Smart technology use was significantly more common in the 31–45 age group (p = 0.01, Cramer’s V = 0.15). Moderate interest in telemedicine was expressed by 69.8% (n = 1247) of respondents, though only 27.4% (n = 490) showed strong interest. The majority of patients (73.8%, n = 1319) did not know their LDL-C levels, and 45.7% (n = 817) of those who did had elevated levels. Conclusions: The findings suggest that while interest in telemedicine methods for the management of arterial hypertension and dyslipidemia exists among Slovak patients, it is more moderate than initially assumed. Importantly, expressed willingness to participate in a study should not be directly equated with readiness to adopt new technologies in daily practice. Successful integration of telemonitoring into the Slovak healthcare system will therefore require not only patient engagement but also active support from healthcare providers to overcome practical and motivational barriers. These findings highlight the need for targeted implementation strategies that address the specific barriers identified in the Central and Eastern European healthcare context. Full article

Background: Arterial hypertension (HTN) is the leading modifiable cardiovascular risk factor for overall mortality worldwide. In Austria, 1.6 million individuals above the age of 15, representing 20% of the total population and 70% of adults aged 65 and older, suffer from HTN. Despite numerous antihypertensive treatment options on the European market, only 38.8% of patients on optimal medical treatment (OMT) reach their treatment goal. Primary prevention remains a challenge, particularly for HTN and the consequential risk of cardiovascular diseases (CVDs). Thus, there is an urgent need for Disease Management Programs (DMPs). We sought to study a possible trial to diagnose hypertension in a non-medical setting at a very early stage of the disease and raise awareness for hypertension in affected people to avoid future complications of unrecognized and untreated HTN. For a non-medical setting, hairdressers fulfil many criteria for an optimal blood pressure (BP) measurement. Methods: This is a pilot study. A total of 193 individuals were included at a Viennese hairdresser. Metric data were described either using mean ± SD given normal distribution or median otherwise. Categorical data were described using absolute frequencies and percentages. For comparison, either independent t-tests or Mann–Whitney U tests or chi² tests were assessed. The staff received expert training on how to measure blood pressure in a guideline-compliant way. All members signed the written and informed consent and received a questionnaire about their demographic data and cardiovascular risk factors. Results: Of the 193 participants in this study, 56.5% (109/193) were female and 43.5% (84/193) were male. The mean age was 54 ± 15.1 years. In the automatically measured office blood pressure (AOBP) measurement, the mean systolic BP was 137.1 ± 17.8 and the mean diastolic BP was 91.6 ± 11.2. Of all participants, 65.8% (127/193) were hypertensive, whereof 74.8% (95/127) had no treatment at all. Among 127 individuals evaluated, 63% (80/127) were unaware of their elevated blood pressure levels, while 28% (44/127) had a prior diagnosis of HTN. The control rate of the individuals with previously diagnosed HTN was very low, with only 18.5% [10.4; 30.9] reaching normotensive values in the current measurement. There was no difference in BP values of patients with previously diagnosed HTN and patients who were unaware of their disease. Antihypertensive treatment was being received by 20.2% (39/193), while 62.2% had not taken their prescribed blood pressure medication on the day of recruitment. Conclusions: This is the first Austrian study to show that screening for HTN in an unconventional non-medical setting is effective to diagnose HTN and raise awareness. Based on the even-higher-than-expected prevalence of HTN, we plan to conduct a cohort study in Vienna, inviting all hairdressers in socially deprived districts to act as gate openers for hypertensive subjects to raise awareness and to contact a regional GP for provision of medical care. An implementation of such a cost-effective and feasible disease management program in Austria might therefore reduce the burden of preventable cardiovascular events associated with HTN. Full article

Advancements in camera technology over the past two decades have made image-based monitoring increasingly accessible for healthcare applications. Imaging photoplethysmography (iPPG) and remote photoplethysmography (rPPG) are non-invasive methods for measuring vital signs, such as heart rate, respiratory rate, oxygen saturation, and blood pressure, without physical contact. rPPG utilizes basic cameras to detect physiological changes, while rPPG enables remote monitoring by capturing subtle skin colour variations linked to blood flow. Various rPPG techniques, including colour-based, motion-based, multispectral, and depth-based approaches, enhance accuracy and resilience. These technologies are beneficial not only for healthcare but also for fitness tracking, stress management, and security systems, offering a promising future for contactless physiological monitoring. In this article, there is an overview of these methods and their uniqueness for use in remote photoplethysmography. Full article

Emerging radar sensing technology is revolutionizing cardiovascular monitoring by eliminating direct skin contact. This approach captures vital signs through electromagnetic wave reflections, enabling contactless blood pressure (BP) tracking while maintaining user comfort and privacy. We present a hierarchical neural framework that synergizes spatial and temporal feature learning for radar-driven, contactless BP monitoring. By employing advanced preprocessing techniques, the system captures subtle chest wall vibrations and their second-order derivatives, feeding dual-channel inputs into a hierarchical neural network. Specifically, Stage 1 deploys convolutional depth-adjustable lightweight residual blocks to extract spatial features from micro-motion characteristics, while Stage 2 employs a transformer architecture to establish correlations between these spatial features and BP periodic dynamic variations. Drawing on the intrinsic link between systolic (SBP) and diastolic (DBP) blood pressures, early estimates from Stage 2 are used to expand the feature set for the second-stage network, boosting its predictive power. Validation achieved clinically acceptable errors (SBP: −1.09 ± 5.15 mmHg, DBP: −0.26 ± 4.35 mmHg). Notably, this high degree of accuracy, combined with the ability to estimate BP at 2 s intervals, closely approximates real-time, beat-to-beat monitoring, representing a pivotal breakthrough in non-contact BP monitoring. Full article

Hypertension (HPT) is a chronic disease characterized by the consistent elevation of arterial blood pressure, which is considered to be a significant risk factor for conditions such as stroke, coronary artery disease, and heart failure. The detection and continuous monitoring of HPT can be a demanding process. As a non-contact measuring method, the ballistocardiography (BCG) signal characterizes the repetitive body motion resulting from the forceful ejection of blood into the major blood vessels during each heartbeat. Therefore, it can be applied for HPT detection. HPT detection with BCG signals remains a challenging task. In this study, we propose an end-to-end deep convolutional model BH-Net for HPT detection through BCG signals. We also propose a data augmentation scheme by selecting the J-peak neighborhoods from the BCG time sequences for hypertension detection. Rigorously evaluated via a public data-set, we report an average accuracy of 97.93% and an average F1-score of 97.62%, outperforming the comparative state-of-the-art methods. We also report that the performance of the traditional machine learning methods and the comparative deep learning models was improved with the proposed data augmentation scheme. Full article

Between 2018 and 2024, the global market has experienced significant advancements in sensor technologies for monitoring patients’ health conditions, which have demonstrated a pivotal role in diagnostics, treatment monitoring, and healthcare optimization. Progress in microelectronics, device miniaturization, and wireless communication technologies has facilitated the development of sophisticated sensors, including wearable devices such as smartwatches and fitness trackers, enabling the real-time monitoring of key health parameters. These devices are widely employed across clinical settings, nursing care, and daily life to collect critical data on vital signs, including heart rate, blood pressure, oxygen saturation, and respiratory rate. A systematic review of the developments within this period highlights the transformative potential of AI and IoT-based technologies in healthcare personalization, particularly in disease symptom prediction and public health management. Furthermore, innovative techniques such as respiratory inductive plethysmography (RIP) and millimeter-wave radar systems (mmTAA) have emerged as precise, non-contact solutions for respiratory monitoring, with applications spanning diagnostics, therapeutic interventions, and enhanced safety in daily life. Full article

In response to the rising prevalence of hypertension due to lifestyle changes, this study introduces a novel approach for non-contact blood pressure (BP) monitoring. Recognizing the “silent killer” nature of hypertension, this research focuses on developing accessible, non-invasive BP measurement methods. This study compares two distinct non-contact BP measurement approaches: one combining the Nelder–Mead simplex method with particle swarm optimization (NM-PSO) and the other using machine learning regression analysis. In the NM-PSO method, a standard webcam captures continuous images of the palm, extracting physiological data through light wave reflection and employing independent component analysis (ICA) to remove noise artifacts. The NM-PSO achieves a verified root mean square error (RMSE) of 2.71 mmHg for systolic blood pressure (SBP) and 3.42 mmHg for diastolic blood pressure (DBP). Alternatively, the regression method derives BP values through machine learning-based regression formulas, resulting in an RMSE of 2.88 mmHg for SBP and 2.60 mmHg for DBP. Both methods enable fast, accurate, and convenient BP measurement within 10 s, suitable for home use. This study demonstrates a cost-effective solution for non-contact BP monitoring and highlights each method’s advantages. The NM-PSO approach emphasizes optimization in noise handling, while the regression method leverages formulaic efficiency in BP estimation. These results offer a biomimetic approach that could replace traditional contact-based BP measurement devices, contributing to enhanced accessibility in hypertension management. Full article

Optical Coherence Tomography (OCT)-based angiography (OCTA) is a high-resolution, high-speed, and non-invasive imaging method that can provide vascular mapping of subcutaneous tissue up to approximately 2 mm. In dermatology applications of OCTA, handheld probes are always designed with a piece of transparent but solid contact window placed at the end of the probe to directly contact the skin for achieving better focusing between the light source and the tissue, reducing noise caused by minor movements. The pressure between the contact window and the skin is usually uncontrollable, and high external pressure affects the quality of microvascular imaging by compressing the vessels and obstructing the underlying blood flow. Therefore, it is necessary to determine a pressure range to ensure that the vessels can be fully imaged in high-quality images. In this paper, two pressure sensors were added to the existing handheld OCT probe, and the imaging probe was fixed to a metal stand and adjusted vertically to change the pressure between the probe and the tested skin site, a gradient of roughly 4 kPa (with 1–2 kPa error) increase was applied in each experiment, and the impact of pressure to the vessel was calculated. The experiment involved a total of five subjects, three areas of which were scanned (palm, back of the hand, and forearm). The vessel density was calculated to evaluate the impact of external pressure on angiography. In addition, PSNR was calculated to ensure that the quality of different tests was at a similar level. The angiography showed the highest density (about 10%) when the pressure between the contact window on the probe and the test area was between 3 and 5 kPa. As the pressure increased, the vascular density decreased, and the rate of decrease varied in different test areas. After fitting all the data points according to the different sites, the slope of the fitted line, i.e., the rate of decrease in density per unit value of pressure, was found to be 4.05% at the palm site, 6.93% at the back of the hand, and 4.55% at the forearm site. This experiment demonstrates that the pressure between the skin and contact window is a significant parameter that cannot be ignored. It is recommended that in future OCTA data collection processes and probe designs, the impact of pressure on the experiment be considered. Full article