Search Results (774)

Remote photoplethysmography (rPPG) extracts physiological signals from facial videos by analyzing subtle skin color variations caused by blood flow. While this technology enables contactless health monitoring, it also raises privacy concerns because facial videos reveal both identity and sensitive biometric information. Existing privacy-preserving techniques, such as blurring or pixelation, degrade visual quality and are unsuitable for practical rPPG applications. This paper presents rePPG, a framework that inserts a desired rPPG signal into facial videos while preserving the original facial appearance. The proposed method disentangles facial appearance and physiological features, enabling replacement of the physiological signal without altering facial identity or visual quality. Skin segmentation restricts modifications to skin regions, and a cycle-consistency mechanism ensures that the injected rPPG signal can be reliably recovered from the generated video. Importantly, the extracted rPPG signals are evaluated against the injected target physiological signals rather than the subject’s original physiological state, ensuring that the evaluation measures signal rewriting accuracy. Experiments on the PURE and UBFC datasets show that rePPG successfully embeds target PPG signals, achieving 1.10 BPM MAE and 95.00% PTE6 on PURE while preserving visual quality (PSNR 24.61 dB, SSIM 0.638). Heart rate metrics are computed using a 5-second temporal window to ensure a consistent evaluation protocol. Full article

Hypertension is a leading global health risk and requires accurate and continuous monitoring for effective management. Although photoplethysmography (PPG) is a promising non-invasive modality for cuffless blood pressure (BP) assessment, many existing approaches (especially raw-signal deep learning) are vulnerable to data leakage, overfitting on small datasets, limited interpretability, and poor performance on minority BP stages. To address these limitations, we propose a robust and physiologically grounded framework for multi-class BP stage classification based on interpretable PPG features. Our approach centers on a comprehensive multi-domain feature engineering pipeline that extracts 124 PPG features, including demographic, morphological, functional decomposition, spectral, nonlinear dynamics, and clinical composite indices. We apply rigorous preprocessing and feature selection prior to model training. We validate the framework on two datasets: PPG-BP dataset (657 segments, 4 classes) for benchmarking and PulseDB (283,773 segments, 3 classes) to assess scalability. We evaluate the proposed framework using a segment-level train/test split, appropriate for assessing intra-subject BP tracking after initial personalization. For the PulseDB dataset, this follows the protocol established by the dataset creators, while for the PPG-BP dataset, it enables direct comparison with prior work given practical dataset constraints. On PPG-BP, LightGBM trained on the selected features achieved macro-F1 = 0.78 and accuracy = 0.74, outperforming comparable deep-learning models. On the PulseDB, a custom Residual MLP achieved accuracy = 0.81 and macro-F1 = 0.79, supporting generalization at scale. These results show that the proposed feature-based approach can outperform complex end-to-end deep-learning models on small datasets while providing improved interpretability. This work establishes a reliable and transparent pathway toward clinically viable continuous BP staging, moving beyond black-box models toward physiologically grounded decision support. Ablation analysis reveals that engineered features provide most of the predictive power (F1 = 0.911), while raw PPG features alone achieve modest performance (F1 = 0.384). For the minority hypertension stage 2 (HT-2) class, a bootstrap 95% confidence interval of [0.762, 1.000] is reported, reflecting uncertainty due to limited sample size. Full article

Remote photoplethysmography (rPPG) enables non-contact vital sign measurements using standard smart device cameras, opening up the potential of scalable health applications on consumer smart devices. However, rPPG signal quality is highly sensitive to camera sensor characteristics and image processing pipelines, which can vary between devices. This variation limits reproducibility and generalisation of rPPG-based algorithms beyond specific hardware platforms. This work presents a reproducible test environment for the validation of the camera sensor response in the context of rPPG signals. A microcontroller-driven illumination system and mechanically constrained setup are used to generate controlled, repeatable optical signals. Two characterisation tests are introduced: a time domain morphology analysis and a frequency domain attenuation analysis. Pulse timing consistency, pulse waveform morphology and normalised frequency responses are compared to assess sensor similarity. This method is applied to selected consumer devices and demonstrates consistent camera response patterns under the controlled test conditions. By explicitly addressing validation of the camera sensor and image processing pipeline, this work supports the development of more robust and transferable rPPG-based vital sign applications across a wider range of consumer devices. Full article

Background: Diabetic foot ulcers (DFUs) are considered a prevalent complication of diabetes mellitus, frequently accompanied with compromised peripheral circulation, slower healing, as well as high risk of infection in addition to risk of amputation. Additional treatments that enhance microvascular perfusion and lessen plantar pressure may accelerate the healing process. This study was carried out to examine the impact of pulsed electromagnetic field (EMF) therapy as well as customized silicone gel insoles in terms of peripheral circulation in addition to vascular indices in patients with DFUs. Methods: A randomized, controlled clinical trial, including sixty-six adults diagnosed with type II diabetes as well as plantar DFUs (Wagner grade I–II) were divided into three groups (n = 22 each): Group A was given low-frequency electromagnetic field therapy (15–50 Hz, 2–5 mT, 30 min, three times per week for 8 weeks), Group B was given a customized silicone gel insoles produced for ulcer offloading, and Group C (control) was given conventional physiotherapy along with wound care. Peripheral microcirculation as well as tissue perfusion were the primary outcomes, and they were measured using Laser Doppler Flowmetry (LDF), Photoplethysmography (PPG), in addition to the Toe–Brachial Index (TBI). The secondary outcome included the Ankle–Brachial Pressure Index (ABPI). A blinded assessor measured the outcomes at the beginning of the study, after the intervention (week 8), and again after the follow-up (week 16). Results: EMF therapy significantly improved LDF (baseline: 45.2 ± 6.5 PU; week 8: 62.5 ± 7.2 PU), PPG (0.42 ± 0.08 mV to 0.68 ± 0.10 mV), TBI (0.64 ± 0.07 to 0.82 ± 0.08), and ABPI (0.88 ± 0.06 to 0.97 ± 0.05) compared with insoles and controls (p < 0.001, partial η² 0.25–0.37). The insole group exhibited moderate enhancements, whereas the control group demonstrated minor changes. Between-group analyses showed substantial differences in favor of EMF therapy across all measured variables (F = 13.5–19.9, p < 0.001). Improvements continued at the 8-week follow-up. Conclusions: Patients with DFUs who receive EMF therapy experience a significant improvement in their peripheral microcirculation, tissue perfusion, as well as vascular indices. This is more effective than just mechanical offloading, and custom insoles offer extra benefits by redistributing pressure. Combining EMF therapy with regular DFU care may speed up healing and lower the risk of problems. Additional research should investigate the efficacy of combined EMF as well as off-loading interventions and their long-term outcomes. Full article

The ankle-brachial index (ABI) is the most non-invasive technique used for diagnosing and assessing peripheral artery disease (PAD), although it is operator-dependent and limited by arterial calcification. Since photoplethysmography (PPG) is a non-invasive, low-cost, and easy-to-use technique that is not limited by arterial compressibility, PPG morphological parameters have been studied for PAD diagnosis, mostly based on mean values. In this work, the relationship between variability indices of PPG morphological parameters and ABI was studied in 52 legs of 32 PAD patients. The morphological PPG parameters, including amplitude, pulse transit time (PTT), and maximum systolic slope, were measured. The mean, standard deviation, and frequency spectral energy for very low, low, and high frequencies were computed as PPG morphological variability indices. The variability indices of PPG morphological parameters have a significant correlation with ABI, indicating that they differ not only between legs with altered and normal ABI but also that they may relate to PAD progression. Fourteen of the 15 variability indices showed significant diagnostic value, with the standard deviation of PTT being the most effective (sensitivity of 96% and specificity of 71%). The differences between normal and non-compressible legs were not significant. The comparison between contralateral legs was also not significant. This suggests that variability indices may provide valuable insights into changes in physiological regulatory mechanisms as PAD progresses, which could aid in the diagnosis, assessment, and prognosis of PAD in future research. Full article

Objective: This study examined whether changes in electroencephalography (EEG)-derived indices, photoplethysmography (PPG)-derived autonomic nervous system indices, heart rate, and rating of perceived exertion (RPE) post-high-intensity exercise differ depending on sleep duration. Methods: Forty physically healthy female university students in their twenties were randomly assigned to the sleep restriction (SR) or normal sleep (NS) group. EEG-derived indices—the theta-to-beta ratio (TBR) and spectral edge frequency at 90% (SEF-90)—and PPG-derived autonomic nervous system indices (HRV index, sympathetic activity, and parasympathetic activity) were measured for one minute at rest before exercise and for one minute immediately after exercise. Heart rate was assessed at rest, immediately after exercise, and at 5, 10, and 15 min post-exercise. The group × time interaction effects were assessed using two-way mixed-design analysis of variance, followed by post hoc analyses. Results: TBR increased significantly post-exercise in the SR group (p = 0.002) with no significant change in the NS group. SEF-90 decreased significantly in the SR group (p < 0.001) with no significant change in the NS group. The HRV index decreased significantly in the SR group (p = 0.004) with no significant change in the NS group. Sympathetic activity increased and parasympathetic activity decreased significantly in the SR group (both p < 0.001). Heart rate was significantly higher in the SR group at rest (p < 0.001), immediately after exercise (p = 0.020), and 5 min post-exercise (p = 0.009). RPE was significantly higher in the SR group (p = 0.003). Conclusions: In healthy young adult women, the central and autonomic nervous systems respond differently to high-intensity exercise depending on sleep duration. Full article

Continuous non-invasive blood pressure monitoring holds significant promise for cardiovascular disease management, yet cuff-based methods remain limited by their intermittent nature. Machine learning approaches leveraging photoplethysmography (PPG) and electrocardiography (ECG) signals present compelling alternatives, though questions persist about which signal type contributes more predictive value. This study compares traditional machine learning models, ensemble methods, and deep learning architectures for estimating systolic blood pressure from physiological waveforms. We extracted 55 features from PPG and ECG recordings of 100 subjects in the MIMIC-III Waveform Database, yielding 3000 segments with invasive arterial blood pressure as ground truth. Data splitting was performed at the subject level (70/15/15 train/validation/test) to prevent data leakage. Evaluation included regression metrics, British Hypertension Society grading, SHAP-based explainability, and ablation studies. Among all models, LightGBM achieved the best performance with mean absolute error of 15.97 mmHg, placing it at BHS Grade D. While SHAP analysis showed ECG features contributing 54.7% of importance versus 45.3% for PPG, our ablation study revealed that PPG-only models achieved comparable performance (MAE 15.97 vs. 16.23 mmHg), with the difference not statistically significant (p = 0.226). These results suggest that PPG-only wearable devices are viable for blood pressure estimation, as adding ECG features provides no statistically significant improvement. However, all configurations achieved only BHS Grade D, indicating that personalized calibration may be necessary for clinical acceptability. Full article

Background: Sleep staging is vital for diagnosing sleep disorders, but the clinical gold standard, polysomnography, is too intrusive for routine home monitoring. While photoplethysmography (PPG) offers a wearable alternative, achieving high diagnostic accuracy remains challenging due to signal noise and individual variability. Methods: We developed DCA-Sleep, a deep learning framework using a Dual Cross-Attention (DCA) mechanism to capture long-range temporal dependencies from raw single-channel PPG. To overcome data scarcity, a cross-modality transfer learning strategy was implemented, pre-training the model on six electrocardiogram (ECG) datasets before extensive validation on a combined cohort of 9738 subjects across nine public datasets (including MESA and CFS). Results: DCA-Sleep demonstrated superior robustness, achieving an average F1-score of 0.731 and a Cohen’s Kappa of 0.652 on the MESA dataset, significantly outperforming state-of-the-art baselines. The model showed high sensitivity in detecting Wake and Deep Sleep stages, which are critical for clinical assessment. Conclusions: This study provides a large-scale validation of a PPG-based staging tool, confirming its reliability as a non-invasive, scalable solution for long-term sleep monitoring and clinical screening. Full article

Respiratory rate (RR) is a critical vital sign for the early detection of hypoxia and respiratory deterioration, yet its continuous monitoring remains challenging in clinical environments. Photoplethysmography (PPG) provides a non-invasive source of physiological information from which respiratory dynamics can be inferred. In this study, numerical physiological features derived from PPG data were used to comparatively evaluate multiple deep learning models for respiratory rate estimation. Fixed-length sliding windows were constructed from the dataset and used to train five neural network architectures: a Deep Feedforward Neural Network (DFNN), unidirectional and bidirectional Recurrent Neural Networks (RNN, Bi-RNN), and unidirectional and bidirectional Long Short-Term Memory networks (LSTM, Bi-LSTM). Model performance was assessed using mean absolute error (MAE), root mean squared error (RMSE), coefficient of determination (R²), and computational runtime. Results indicate that models incorporating temporal dependencies outperform the static feedforward baseline, achieving MAE values as low as 0.521 breaths/min, making them competitive with or lower than previously reported PPG-based approaches. These findings highlight the effectiveness of temporal deep learning models for respiratory rate estimation from PPG-derived numerical features and provide insight into accuracy–efficiency trade-offs relevant to real-time monitoring applications. Full article

Cardiovascular disease has become the leading cause of death worldwide, underscoring the urgent need for widespread cardiac monitoring, while the Electrocardiogram (ECG) remains the diagnostic gold standard, the complexity of its acquisition limits its long-term feasibility. In contrast, Photoplethysmography (PPG), ubiquitous in wearable devices, is increasingly adopted due to its accessibility. However, synthesizing ECG from PPG poses an intrinsically ill-posed inverse problem. Existing purely data-driven paradigms often neglect underlying biophysical mechanisms, resulting in a lack of physical constraints and interpretability, which renders them prone to generating non-physiological hallucinations. To address this, we propose PhysDiff-LBM, a novel physics-aware framework that incorporates Lattice Boltzmann hemodynamic constraints into a conditional diffusion model. Employing a dual-stream architecture, our framework captures high-frequency morphological details via a cross-attention-guided diffusion model with region-wise adaptability. Synergistically, we physically regularize the ECG synthesis by leveraging the mesoscopic streaming and collision operators of LBM. By forcing the synthesized waveform gradients to evolve consistently with hemodynamic momentum, this mechanism constrains the model to strictly adhere to the fluid dynamic conservation laws governing pulse wave propagation. Experimental results demonstrate that our method achieves superior signal fidelity and exhibits significant advantages in downstream clinical applications. Full article

Stress can cause many disorders, including mental and physical ones, if it persists. To take timely and effective early intervention measures, mental stress levels must be carefully monitored. This study investigates the rapidly growing topic of mental stress detection, focusing on the primary goals and mechanisms of existing detection frameworks. The main objectives and mechanisms will be highlighted. This study examines physiological sensors, stressors, algorithms, monitoring methods, and validation tools used to assess and classify mental stress. The study targets physiological sensors. Wearable sensors are becoming more popular because they can continuously monitor physiological responses in human-like environments. This allows them to reveal relevant stress patterns across various work environments. Numerous physiological sensors are used regularly. Galvanic skin response (GSR), electrocardiogram (ECG), photoplethysmography (PPG), electroencephalography (EEG), and pupil diameter camera systems are examples of these sensors. The combination of these sensors provides a wealth of cognitive and autonomic response data for stress detection. This review examines AI-based methods for interpreting complex physiological data. Machine learning and ensemble models are emphasized for improving stress classification accuracy and reducing incorrect classifications. In addition, this article discusses stressors used to induce reliable physiological responses. Validated self-report instruments are being reviewed as benchmarking tools for objective sensor-based measurements. STAI and PSS-10 are examples. These instruments demonstrate a strong correlation between stress and anxiety and physiological health outcomes. In conclusion, this review discusses future research avenues, focusing on advanced artificial intelligence-driven approaches and sophisticated sensors. These developments aim to better define stress levels and physiological factors that have not been thoroughly studied. Full article

Electrodermal activity (EDA) is a powerful anchor for assessing human sympathetic nervous system (SNS) arousal. However, EDA alone is only one facet of physiological response. Researchers have increasingly moved away from single-sensor analysis to multimodal wearable systems, integrating EDA with other signals such as heart rate variability (HRV), photoplethysmography (PPG), skin temperature (SKT), blood oxygen (SpO₂) and more. This critical shift in methodology is not yet reflected in current reviews of the literature. Existing surveys thoroughly cover EDA as a standalone measure, but the combination of sensor technologies has been largely unexamined. In this context, multimodal refers to integrating EDA with complementary biosignals (HRV, PPG, SKT, SpO₂, etc.) commonly captured by modern wearable platforms. This review provides a comprehensive analysis focused on multimodal systems for assessing SNS arousal. A total of 58 studies met the inclusion criteria. We map the landscape, from single signal methods to complex sensor-fusion, and highlight advances in multimodal sensor models, physiological modeling, and context-aware sensing. We also examine recent advances in signal processing and machine learning that enhance multimodal SNS arousal inference, outlining current capabilities and identifying open directions for future work. By providing a framework of this emerging field, this paper serves as a resource for all researchers aiming to build and deploy the next generation of context-aware SNS arousal-sensing technology. Full article

Wearable health monitoring systems (WHMS) are recognized as key enablers of continuous real-time physiological sensing in healthcare, eldercare, sports, and occupational safety. However, current devices face critical limitations due to their dependence on non-renewable batteries, rigid substrates, and non-degradable electronic components, which contribute to environmental waste and limit long-term usability. This study aims to explore the development of sustainable, energy-autonomous WHMS that integrate multimodal energy harvesting, including triboelectric, piezoelectric, photovoltaic, thermoelectric, and radio frequency, with biodegradable and bioresorbable electronics using silk fibroin, cellulose nanofibers, poly(lactic-co-glycolic acid), magnesium, and transient silicon. This unified system architecture would further comprise harvesters, power management circuits, energy buffers, low-power sensing front-ends, and tiny machine learning-enabled data processing. The methodology emphasizes energy-neutral operation through duty-cycling, harvest-aware scheduling, and compressive sensing. Simulation and modeling results indicate harvested power densities between 100 and 220 µW·cm⁻², sufficient to sustain electrocardiography, photoplethysmography, and temperature monitoring under realistic daily use profiles. Material degradation studies demonstrate predictable dissolution kinetics over 8–20 weeks in physiological conditions, aligning with safety and environmental goals. By uniting sustainable materials science with energy-efficient circuit design, this work establishes a blueprint for the next generation of eco-friendly, clinically relevant, and ethically responsible wearable health technologies. Full article

Background. Self-congruency refers to the coherence between emotional experience (internal states) and enacted behavior (outward actions). Reduced self-congruency has been linked to vulnerability in mental health, yet its physiological correlates remain poorly characterized. Heart–brain temporal coupling may provide a candidate physiological marker of this psychological coherence. Methods. Thirty-eight healthy adults underwent resting-state functional magnetic resonance imaging while cardiac activity was simultaneously recorded using photoplethysmography to derive heart rate variability (HRV). Self-congruency was assessed using a graphic rating scale based on the spatial overlap between emotional experience and enacted behavior. Heart–brain temporal coupling between HRV and regional blood-oxygen-level-dependent (BOLD) signals was quantified using cross-covariance analysis across biologically plausible temporal shifts. Results. Heart–brain temporal coupling predominantly reflected brain-to-heart temporal ordering, particularly within regions central to the neurovisceral integration model, including the ventromedial prefrontal and anterior cingulate cortices. In contrast, higher self-congruency was associated with stronger heart-to-brain temporal coupling, notably within the right rostral middle frontal gyrus and supramarginal gyrus, regions implicated in emotion regulation and socio-emotional processing. Conclusions. While global heart–brain temporal coupling is dominated by top-down neural regulation, greater alignment between emotional experience and enacted behavior is associated with enhanced bottom-up cardiac temporal ordering on neural activity. These findings seem to identify a physiological–psychological axis that may inform original prevention-oriented approaches in mental health. Full article

Accurate, non-contact vital-sign monitoring promises a scalable alternative to conventional sensors, yet low signal quality and long recording times have limited real-life adoption. We present a dual-modality system that combines Eulerian video magnified remote photoplethysmography (rPPG) from facial videos with optical flow-based shoulder tracking to estimate heart rate (HR) and respiratory rate (RR) from ultra-short 15 s recordings. With 200 participants, each providing 2 videos, 387 videos passed strict usability criteria, excluding flicker, blur, occlusion, and low illumination. For 15 s recordings, the HR estimates reached 98.5% accuracy within a ±10 beats per minute tolerance (MAE = 3.25, RMSE = 4.88, r = 0.93; p < 0.05) and the RR estimates achieved 98.4% accuracy within a ±5 respirations per minute tolerance (MAE = 0.69, RMSE = 0.87, r = 0.90; p < 0.05), exceeding prior studies that required 30 to 60 s recording lengths. Computational analysis on a standard home computer confirmed feasibility, with near real-time performance achievable on optimized hardware. By integrating complementary modalities and rigorous video quality control, the system overcomes low-SNR challenges, delivering high-fidelity, clinically validated vital signs monitoring. These results establish a robust, scalable, and precise framework for clinical and home care, demonstrating that accurate, contact-free HR and RR monitoring can now be achieved in seconds, making rapid, real-life vital signs assessment practical and accessible. Full article