Photoplethysmography and its application in clinical physiological measurement

Diffuse transmittance spectroscopy for ultra short-term measurement of pulse rate variability in healthy subjects

Multi-wavelength plethysmography (MWPPG) is a growing technique for noninvasive hemodynamic measurements, particularly spectral based methods. Different wavelengths have been investigated for both transmissive and reflectance PPG configurations. The objective of this work is to investigate the feasibility of Diffuse Transmittance Spectroscopy (DTS) for Pulse Rate Variability (PRV) measurements and to evaluate the performance of diffuse transmittance spectroscopy in quantifying ultrashort pulse rate variability. DTS was used for reconstructing PPG signal followed by PRV analysis. DTS and reference PPG recordings were acquired from 18 healthy subjects in total. PRV features include time-domain, and frequency-domain features are extracted from 50 s duration. The extracted PRV parameters were compared to PRV parameters derived from conventional pulse oximetry-based PPG. Pulse rate variability analysis was applied on DTS and reference PPG tracings. The comparison demonstrated a strong correlation between the diffuse transmittance spectral method and the gold standard PPG sensor. Significant correlation (r > 0.90, p < 0.05) was found between PRV from DTS and reference PRV for mean intervals, standard deviation of intervals (SDNN) and the root-mean square of the difference of successive intervals (RMSSD). A good agreement was found between PRV Parameters in time domain of PPG analysis using Bland-Altman plots with 95 % limits of agreements. However, Bland-Altman analysis showed a considerable divergence in frequency parameters. The study also revealed that PPG based diffuse transmittance measurements were insensitive to ambient noise in comparison with conventional pulse oximeter. The results suggest a potential application of the diffuse transmittance spectroscopy for pulse rate variability analysis.

Generative adversarial networks with fully connected layers to denoise PPG signals

Objective.The detection of arterial pulsating signals at the skin periphery with Photoplethysmography (PPG) are easily distorted by motion artifacts. This work explores the alternatives to the aid of PPG reconstruction with movement sensors (accelerometer and/or gyroscope) which to date have demonstrated the best pulsating signal reconstruction.Approach.A generative adversarial network with fully connected layers is proposed for the reconstruction of distorted PPG signals. Artificial corruption was performed to the clean selected signals from the BIDMC Heart Rate dataset, processed from the larger MIMIC II waveform database to create the training, validation and testing sets.Main results.The heart rate (HR) of this dataset was further extracted to evaluate the performance of the model obtaining a mean absolute error of 1.31 bpm comparing the HR of the target and reconstructed PPG signals with HR between 70 and 115 bpm.Significance.The model architecture is effective at reconstructing noisy PPG signals regardless the length and amplitude of the corruption introduced. The performance over a range of HR (70-115 bpm), indicates a promising approach for real-time PPG signal reconstruction without the aid of acceleration or angular velocity inputs.

Gel-Based Electrolytes for Organic Electrochemical Transistors: Mechanisms, Applications, and Perspectives

Organic electrochemical transistors (OECTs) have emerged as the core component of specialized bioelectronic technologies due to their high signal amplification capability, low operating voltage (<1 V), and biocompatibility. Under a gate bias, OECTs modulate device operation via ionic drift between the electrolyte and the channel. Compared to common electrolytes with a fluid nature (including salt aqueous solutions and ion liquids), gel electrolytes, with an intriguing structure consisting of a physically and/or chemically crosslinked polymer network where the interstitial spaces between polymers are filled with liquid electrolytes or mobile ion species, are promising candidates for quasi-solid electrolytes. Due to relatively high ionic conductivity, the potential for large-scale integration, and the capability to suppress channel swelling, gel electrolytes have been a research highlight in OECTs in recent years. This review summarizes recent progress on OECTs with gel electrolytes that demonstrate good mechanical as well as physical and chemical stabilities. Moreover, various components in forming gel electrolytes, including different mobile liquid phases and polymer components, are introduced. Furthermore, applications of these OECTs in the areas of sensors, neuromorphics, and organic circuits, are discussed. Last, future perspectives of OECTs based on gel electrolytes are discussed along with possible solutions for existing challenges.

WF-PPG: A Wrist-finger Dual-Channel Dataset for Studying the Impact of Contact Pressure on PPG Morphology

Photoplethysmography (PPG) is a simple optical technique widely used in wearable devices for continuous cardiac health monitoring. However, the quality of PPG signals, particularly their morphology, is influenced by the contact pressure between the skin and the sensor. This variability in signal quality complicates complex tasks that rely on high-quality signals, such as blood pressure and heart rate variability estimation, making them less reliable or even impossible. To address this issue, we present a novel dataset (termed WF-PPG) comprising PPG signals from the wrist measured under varying contact pressures, along with high-quality PPG signals from the fingertip captured simultaneously. Data collection was conducted using a custom device setup capable of precisely adjusting the contact pressure for wrist PPG signals while also recording additional metrics such as contact pressure, electrocardiogram (ECG), blood pressure, and oxygen saturation. WF-PPG is designed to facilitate the analysis of effects of contact pressure on PPG morphology and to support the development and evaluation of advanced data-driven techniques aimed at enhancing the reliability of PPG-based health monitoring.

COMPARING STAGES OF DIABETIC RETINOPATHY WITH SYSTEMIC VASCULAR STATUS USING FINGER PHOTOPLETHYSMOGRAPHY

PURPOSE

To evaluate systemic vascular fitness measured by finger photoplethysmography in diabetic retinopathy (DR).

METHODS

This was a cross-sectional observational study on patients with Type II diabetes mellitus from October 2020 to May 2021. Data collected include systolic/diastolic blood pressure, visual acuity, glycated hemoglobin, and central macular thickness. Diabetic retinopathy severity was categorized using the Early Treatment Diabetic Retinopathy Study classification. Photoplethysmography signals were acquired using pulse-oximeter modules (OEM-60; Dolphin Medical, Inc) measured for 90 seconds at 275 Hz sampling rate and 16-bit resolution, which records photoplethysmography fitness index, vascular risk prediction index, and vascular age.

RESULTS

One hundred and forty-one patients were equally distributed into six DR categories. Mean age was 58.8 ± 9.9 years, with female-to-male ratio of 1.27. There were significant differences in mean systolic (125.5 ± 10.0 mmHg, P = 0.007) and diastolic blood pressure (80.0 ± 8.8 mmHg), mean glycated hemoglobin (7.6 ± 1.9%, P = 0.005), median log unit of minimal angle of resolution (0.3, interquartile range: 0.2-0.5, P < 0.001), and central macular thickness ( P = 0.003) across DR severity. Significant differences were also seen in photoplethysmography fitness index ( P = 0.001), vascular risk prediction index ( P < 0.001), and vascular age ( P = 0.001), with poorer values in severe compared with mild/moderate DR. After adjusting for age, blood pressure, and glycated hemoglobin, photoplethysmography fitness reduces by 3.3% (regression coefficient, b = -3.27, P < 0.001), vascular age increases by 2.5 years ( b = 2.54, P = 0.002), and vascular risk prediction index increases by 3.1 ( b = 3.08, P < 0.001) with every DR worsening.

CONCLUSION

More severe DR stages were associated with poorer photoplethysmography vascular markers.

Evaluation of tooth-specific optical properties for the development of a non-invasive pulp diagnostic system using Transmitted-light plethysmography: An in vitro study

OBJECTIVES

Transmitted-light plethysmography (TLP) is an objective and non-invasive pulp diagnosis method that has already been validated for applications for incisors. However, there is a demand for TLP use in the molars, it has not yet been established for this application. This study investigated the optimal light source wavelengths for TLP in premolars, to establish a pulp diagnosis system based on measuring pulpal blood flow.

DESIGN

One extracted incisor and one extracted premolar, which were fully developed and healthy, were prepared. The optical properties of model teeth filled with 0-30 % hematocrit contents in the pulp chamber were analyzed at 525, 590, and 625 nm wavelengths. The incident and transmitted light intensity of model teeth were measured to determine the optical density (O.D.) using a prototype plethysmograph (J.Morita) and a spectrometer. The significant differences in O.D. at each wavelength were analyzed using the Kruskal-Wallis test followed by the Steel-Dwass test as a post-hoc test. Light propagation through the teeth was also observed under a microscope.

RESULTS

A statistically significant differences in O.D. were observed among the three wavelengths at all hematocrit concentrations (p < 0.05). The observation of light absorption and scattering in the whole teeth supported the optical measurement results.

CONCLUSION

The results indicated that the most appropriate wavelengths are 525 nm for incisors and 590 nm for premolars, as it balanced the light transmission through the tooth structure and the sensitivity for detecting changes in blood concentration. Further research is expected to expand the range of applications of TLP in premolars.

Detecting anomalies in smart wearables for hypertension: a deep learning mechanism

Introduction

The growing demand for real-time, affordable, and accessible healthcare has underscored the need for advanced technologies that can provide timely health monitoring. One such area is predicting arterial blood pressure (BP) using non-invasive methods, which is crucial for managing cardiovascular diseases. This research aims to address the limitations of current healthcare systems, particularly in remote areas, by leveraging deep learning techniques in Smart Health Monitoring (SHM).

Methods

This paper introduces a novel neural network architecture, ResNet-LSTM, to predict BP from physiological signals such as electrocardiogram (ECG) and photoplethysmogram (PPG). The combination of ResNet's feature extraction capabilities and LSTM's sequential data processing offers improved prediction accuracy. Comprehensive error analysis was conducted, and the model was validated using Leave-One-Out (LOO) cross-validation and an additional dataset.

Results

The ResNet-LSTM model showed superior performance, particularly with PPG data, achieving a mean absolute error (MAE) of 6.2 mmHg and a root mean square error (RMSE) of 8.9 mmHg for BP prediction. Despite the higher computational cost (~4,375 FLOPs), the improved accuracy and generalization across datasets demonstrate the model's robustness and suitability for continuous BP monitoring.

Discussion

The results confirm the potential of integrating ResNet-LSTM into SHM for accurate and non-invasive BP prediction. This approach also highlights the need for accurate anomaly detection in continuous monitoring systems, especially for wearable devices. Future work will focus on enhancing cloud-based infrastructures for real-time analysis and refining anomaly detection models to improve patient outcomes.

Spiking-PhysFormer: Camera-based remote photoplethysmography with parallel spike-driven transformer

Artificial neural networks (ANNs) can help camera-based remote photoplethysmography (rPPG) in measuring cardiac activity and physiological signals from facial videos, such as pulse wave, heart rate and respiration rate with better accuracy. However, most existing ANN-based methods require substantial computing resources, which poses challenges for effective deployment on mobile devices. Spiking neural networks (SNNs), on the other hand, hold immense potential for energy-efficient deep learning owing to their binary and event-driven architecture. To the best of our knowledge, we are the first to introduce SNNs into the realm of rPPG, proposing a hybrid neural network (HNN) model, the Spiking-PhysFormer, aimed at reducing power consumption. Specifically, the proposed Spiking-PhyFormer consists of an ANN-based patch embedding block, SNN-based transformer blocks, and an ANN-based predictor head. First, to simplify the transformer block while preserving its capacity to aggregate local and global spatio-temporal features, we design a parallel spike transformer block to replace sequential sub-blocks. Additionally, we propose a simplified spiking self-attention mechanism that omits the value parameter without compromising the model's performance. Experiments conducted on four datasets-PURE, UBFC-rPPG, UBFC-Phys, and MMPD demonstrate that the proposed model achieves a 10.1% reduction in power consumption compared to PhysFormer. Additionally, the power consumption of the transformer block is reduced by a factor of 12.2, while maintaining decent performance as PhysFormer and other ANN-based models.

Analysis of the Effect of Skin Pigmentation and Oxygen Saturation on Monte Carlo-Simulated Reflectance Photoplethysmography Signals

The effect of skin pigmentation on photoplethysmography and, specifically, pulse oximetry has recently received a significant amount of attention amongst researchers, especially since the COVID-19 pandemic. With most computational studies observing overestimation of arterial oxygen saturation (SpO2) in individuals with darker skin, this study seeks to further investigate the root causes of these discrepancies. This study analysed intensity changes from Monte Carlo-simulated reflectance PPG signals across light, moderate, and dark skin types at oxygen saturations of 70% and 100% in MATLAB R2024a. With simulated intensity reflecting PPG amplitude, the results showed that systolic intensity decreased by 3-4% as pigmentation increased at 660 nm. It was also shown that the impact at 940 nm is minimal (<0.2%), indicating that the increased absorption of red light by melanin has a greater effect on the ratio of ratios calculations. These results suggest that in-built adjustments may be required for data collected from red-light sources in pulse oximeters that do not currently have the necessary post-processing algorithms to account for this difference between diverse skin populations.

Comparative Evaluation of Consumer Wearable Devices for Atrial Fibrillation Detection: Validation Study

Background

Consumer-oriented wearable devices (CWDs) such as smartphones and smartwatches have gained prominence for their ability to detect atrial fibrillation (AF) through proprietary algorithms using electrocardiography or photoplethysmography (PPG)-based digital recordings. Despite numerous individual validation studies, a direct comparison of interdevice performance is lacking.

Objective

This study aimed to evaluate and compare the ability of CWDs to distinguish between sinus rhythm and AF.

Methods

Patients exhibiting sinus rhythm or AF were enrolled through a cardiology outpatient clinic. The participants were instructed to perform heart rhythm measurements using a handheld 6-lead electrocardiogram (ECG) device (KardiaMobile 6L), a smartwatch-derived single-lead ECG (Apple Watch), and two PPG-based smartphone apps (FibriCheck and Preventicus) in a random sequence, with simultaneous 12-lead reference ECG as the gold standard.

Results

A total of 122 participants were included in the study: median age 69 (IQR 61-77) years, 63.9% (n=78) men, 25% (n=30) with AF, 9.8% (n=12) without prior smartphone experience, and 73% (n=89) without experience in using a smartwatch. The sensitivity to detect AF was 100% for all devices. The specificity to detect sinus rhythm was 96.4% (95% CI 89.5%-98.8%) for KardiaMobile 6L, 97.8% (95% CI 91.6%-99.5%) for Apple Watch, 98.9% (95% CI 92.5%-99.8%) for FibriCheck, and 97.8% (95% CI 91.5%-99.4%) for Preventicus (P=.50). Insufficient quality measurements were observed in 10.7% (95% CI 6.3%-17.5%) of cases for both KardiaMobile 6L and Apple Watch, 7.4% (95% CI 3.9%-13.6%) for FibriCheck, and 14.8% (95% CI 9.5%-22.2%) for Preventicus (P=.21). Participants preferred Apple Watch over the other devices to monitor their heart rhythm.

Conclusions

In this study population, the discrimination between sinus rhythm and AF using CWDs based on ECG or PPG was highly accurate, with no significant variations in performance across the examined devices.

Evaluation of Non-Invasive Hemoglobin Monitoring in Perioperative Patients: A Retrospective Study of the Rad-67TM (Masimo)

Background: Hemoglobin (Hb) is a crucial parameter in perioperative care due to its essential role for oxygen transport and tissue oxygenation. Accurate Hb monitoring allows for timely interventions to address perioperative anemia and, thus, prevent morbidity and mortality. Traditional Hb measurements rely on invasive blood sampling, which significantly contributes to iatrogenic anemia and poses discomfort and increased infection risks. The advent of non-invasive devices like Masimo's Rad-67™, which measures Hb using pulse CO-oximetry (SpHb), offers a promising alternative. This study evaluates the accuracy of SpHb compared to clinical standard blood gas analysis (BGA) in perioperative patients. Methods: This retrospective study analyzed 335 paired Hb measurements with an interval <15 min between SpHb and BGA in the operating theater and post-anesthesia care unit of a university hospital. Patients experiencing hemodynamic instability, acute bleeding, or critical care were excluded. Statistical analysis included Bland-Altman plots and Pearson correlation coefficients (PCCs) to assess the agreement between SpHb and BGA. Potential confounders, e.g., patient age, skin temperature, sex, perfusion index (PI), and atrial fibrillation, were also analyzed. Results: The bias of the SpHb compared to BGA according to Bland-Altman was 0.00 g/dL, with limits of agreement ranging from -2.70 to 2.45 g/dL. A strong correlation was observed (r = 0.79). Overall, 57.6% of the paired measurements showed a deviation between the two methods of ≤±1 g/dL; however, this applied to only 33.3% of the anemic patients. Modified Clark's Error Grid analysis showed 85.4% of values fell within clinically acceptable limits. Sex was found to have a statistically significant, but not clinically relevant, effect on accuracy (p = 0.02). Conclusions: The Rad-67TM demonstrates reasonable accuracy for non-invasive SpHb, but exhibits significant discrepancies in anemic patients with overestimating low values. While it offers potential for reducing iatrogenic blood loss, SpHb so far should not replace BGA in critical clinical decision-making.

Reliability and Accuracy of the Fitbit Charge 4 Photoplethysmography Heart Rate Sensor in Ecological Conditions: Validation Study

Background

Wrist-worn photoplethysmography (PPG) sensors allow for continuous heart rate (HR) measurement without the inconveniences of wearing a chest belt. Although green light PPG technology reduces HR measurement motion artifacts, only a limited number of studies have investigated the reliability and accuracy of wearables in non-laboratory-controlled conditions with actual specific and various physical activity movements.

Objective

The purpose of this study was to (1) assess the reliability and accuracy of the PPG-based HR sensor of the Fitbit Charge 4 (FC4) in ecological conditions and (2) quantify the potential variability caused by the nature of activities.

Methods

We collected HR data from participants who performed badminton, tennis, orienteering running, running, cycling, and soccer while simultaneously wearing the FC4 and the Polar H10 chest belt (criterion sensor). Skin tone was assessed with the Fitzpatrick Skin Scale. Once data from the FC4 and criterion data were synchronized, accuracy and reliability analyses were performed, using intraclass correlation coefficients (ICCs), Lin concordance correlation coefficients (CCCs), mean absolute percentage errors (MAPEs), and Bland-Altman tests. A linear univariate model was also used to evaluate the effect of skin tone on bias. All analyses were stratified by activity and pooled activity types (racket sports and running sports).

Results

A total of 77.5 hours of HR recordings from 26 participants (age: mean 21.1, SD 5.8 years) were analyzed. The highest reliability was found for running sports, with ICCs and CCCs of 0.90 and 0.99 for running and 0.80 and 0.93 for orienteering running, respectively, whereas the ICCs and CCCs were 0.37 and 0.78, 0.42 and 0.88, 0.65 and 0.97, and 0.49 and 0.81 for badminton, tennis, cycling, and soccer, respectively. We found the highest accuracy for running (bias: 0.1 beats per minute [bpm]; MAPE 1.2%, SD 4.6%) and the lowest for badminton (bias: -16.5 bpm; MAPE 16.2%, SD 14.4%) and soccer (bias: -16.5 bpm; MAPE 17.5%, SD 20.8%). Limit of agreement (LOA) width and artifact rate followed the same trend. No effect of skin tone was observed on bias.

Conclusions

LOA width, bias, and MAPE results found for racket sports and soccer suggest a high sensitivity to motion artifacts for activities that involve "sharp" and random arm movements. In this study, we did not measure arm motion, which limits our results. However, whereas individuals might benefit from using the FC4 for casual training in aerobic sports, we cannot recommend the use of the FC4 for specific purposes requiring high reliability and accuracy, such as research purposes.

Non-Intrusive Monitoring of Vital Signs in the Lower Limbs Using Optical Sensors

Invisible health monitoring is currently a topic of global interest within the scientific community. Sensorization of everyday objects can provide valuable health information without requiring any changes in people's routines. In this work, a feasibility study of photoplethysmography (PPG) acquisition in the lower limbs for continuous and real-time monitoring of the vital signs, including heart rate (HR) and respiratory rate (RR), is presented. The proposed system uses two MAX30102 sensors to obtain PPG signals from the back of the thigh. As proof of concept, tests were conducted in 17 volunteers (age group between 22 and 40 years old, twelve females and five males), and the results were compared to those of reference sensors. A Pearson correlation coefficient of r = 0.92 and r = 0.77 and a mean difference of 1.2 bpm and 0.9 rpm for HR and RR, respectively, were obtained between the developed system and reference. System accuracies of 95.9% for HR and 91.3% for RR were achieved, showing the system viability for vital sign monitoring of the lower limbs.

Non-invasive blood glucose monitoring using PPG signals with various deep learning models and implementation using TinyML

Accurate and continuous blood glucose monitoring is essential for effective diabetes management, yet traditional finger pricking methods are often inconvenient and painful. To address this issue, photoplethysmography (PPG) presents a promising non-invasive alternative for estimating blood glucose levels. In this study, we propose an innovative 1-second signal segmentation method and evaluate the performance of three advanced deep learning models using a novel dataset to estimate blood glucose levels from PPG signals. We also extend our testing to additional datasets to assess the robustness of our models against unseen distributions, thereby providing a comprehensive evaluation of the models' generalizability and specificity and accuracy. Initially, we analyzed 10-second PPG segments; however, our newly developed 1-second signal segmentation technique proved to significantly enhance accuracy and computational efficiency. The selected model, after being optimized and deployed on an embedded device, achieved immediate blood glucose estimation with a processing time of just 6.4 seconds, demonstrating the method's practical applicability. The method demonstrated strong generalizability across different populations. Training data was collected during surgery and anesthesia, and the method also performed successfully in normal states using a separate test dataset. The results showed an average root mean squared error (RMSE) of 19.7 mg/dL, with 76.6% accuracy within the A zone and 23.4% accuracy within the B zone of the Clarke Error Grid Analysis (CEGA), indicating a 100% clinical acceptance. These findings demonstrate that blood glucose estimation using 1-second PPG signal segments not only outperforms the traditional 10-second segments, but also provides a more convenient and accurate alternative to conventional monitoring methods. The study's results highlight the potential of this approach for non-invasive, accurate, and convenient diabetes management, ultimately offering improved health management.

Extracellular matrix in vascular homeostasis and disease

The extracellular matrix is an essential component and constitutes a dynamic microenvironment of the vessel wall with an indispensable role in vascular homeostasis and disease. From early development through to ageing, the vascular extracellular matrix undergoes various biochemical and biomechanical alterations in response to diverse environmental cues and exerts precise regulatory control over vessel remodelling. Advances in novel technologies that enable the comprehensive evaluation of extracellular matrix components and cell-matrix interactions have led to the emergence of therapeutic strategies that specifically target this fine-tuned network. In this Review, we explore various aspects of extracellular matrix biology in vascular development, disorders and ageing, emphasizing the effect of the extracellular matrix on disease initiation and progression. Additionally, we provide an overview of the potential therapeutic implications of targeting the extracellular matrix microenvironment in vascular diseases.

Pupil size correlates with heart rate, skin conductance, pulse wave amplitude, and respiration responses during emotional conflict and valence processing

Pupil size is a non-invasive index for autonomic arousal mediated by the locus coeruleus-norepinephrine (LC-NE) system. While pupil size and its derivative (velocity) are increasingly used as indicators of arousal, limited research has investigated the relationships between pupil size and other well-known autonomic responses. Here, we simultaneously recorded pupillometry, heart rate, skin conductance, pulse wave amplitude, and respiration signals during an emotional face-word Stroop task, in which task-evoked (phasic) pupil dilation correlates with LC-NE responsivity. We hypothesized that emotional conflict and valence would affect pupil and other autonomic responses, and trial-by-trial correlations between pupil and other autonomic responses would be observed during both tonic and phasic epochs. Larger pupil dilations, higher pupil size derivative, and lower heart rates were observed in the incongruent condition compared to the congruent condition. Additionally, following incongruent trials, the congruency effect was reduced, and arousal levels indexed by previous-trial pupil dilation were correlated with subsequent reaction times. Furthermore, linear mixed models revealed that larger pupil dilations correlated with higher heart rates, higher skin conductance responses, higher respiration amplitudes, and lower pulse wave amplitudes on a trial-by-trial basis. Similar effects were seen between positive and negative valence conditions. Moreover, tonic pupil size before stimulus presentation significantly correlated with all other tonic autonomic responses, whereas tonic pupil size derivative correlated with heart rates and skin conductance responses. These results demonstrate a trial-by-trial relationship between pupil dynamics and other autonomic responses, highlighting pupil size as an effective real-time index for autonomic arousal during emotional conflict and valence processing.

Blood Pressure Estimation Using Explainable Deep-Learning Models Based on Photoplethysmography

BACKGROUND

Due to their invasiveness, arterial lines are not typically used in routine monitoring, despite their superior responsiveness in hemodynamic monitoring and detecting intraoperative hypotension. To address this issue, noninvasive, continuous arterial pressure monitoring is necessary. We developed a deep-learning model that reconstructs continuous mean arterial pressure (MAP) using the photoplethysmograhy (PPG) signal and compared it to the arterial line gold standard.

METHODS

We analyzed high-frequency PPG signals from 117 patients in neuroradiology and digestive surgery with a median of 2201 (interquartile range [IQR], 788-4775) measurements per patient. We compared models with different combinations of convolutional and recurrent layers using as inputs for our neural network high-frequency PPG and derived features including dicrotic notch relative amplitude, perfusion index, and heart rate. Mean absolute error (MAE) was used as performance metrics. Explainability of the deep-learning model was reconstructed with Grad-CAM, a visualization technique using saliency maps to highlight the parts of an input that are significant for a deep-learning model decision-making process.

RESULTS

An MAP baseline model, which consisted only of standard cuff measures, reached an MAE of 6.1 (± 14.5) mm Hg. In contrast, the deep-learning model achieved an MAE of 3.5 (± 4.4) mm Hg on the external test set (a 42.6% improvement). This model also achieved the narrowest confidence intervals and met international standards used within the community (grade A). The saliency map revealed that the deep-learning model primarily extracts information near the dicrotic notch region.

CONCLUSIONS

Our deep-learning model noninvasively estimates arterial pressure with high accuracy. This model may show potential as a decision-support tool in operating-room settings, particularly in scenarios where invasive blood pressure monitoring is unavailable.

Developing technologies to assess vascular ageing: a roadmap from VascAgeNet

Vascular ageing (vascular ageing) is the deterioration of arterial structure and function which occurs naturally with age, and which can be accelerated with disease. Measurements of vascular ageing are emerging as markers of cardiovascular risk, with potential applications in disease diagnosis and prognosis, and for guiding treatments. However, vascular ageing is not yet routinely assessed in clinical practice. A key step towards this is the development of technologies to assess vascular ageing. In this Roadmap, experts discuss several aspects of this process, including: measurement technologies; the development pipeline; clinical applications; and future research directions. The Roadmap summarises the state of the art, outlines the major challenges to overcome, and identifies potential future research directions to address these challenges.

Exploring Near- and Far-Field Effects in Photoplethysmography Signals Across Different Source-Detector Distances

Photoplethysmography is a widely used optical technique to extract physiological information non-invasively. Despite its large use and adoption, multiple factors influence the signal shape and quality, including the instrumentation used. This work analyzes the variability of the DC component of the PPG signal at three source-detector distances (6 mm, 9 mm, and 12 mm) using green, red, and infrared light and four photodiodes per distance. The coefficient of variation (CV) is proposed as a new signal quality index (SQI) to evaluate signal variabilities. This study first characterizes the PPG system, which is then used to acquire PPG signals in the chest of 14 healthy participants. Results show a great DC variability at 6 mm, homogenizing at 9 and 12 mm. This suggests that PPG systems are also sensitive to the near- and far-field effects commonly reported and studied in optics, which can impact the accuracy of physiological parameters dependent on the DC component, such as oxygen saturation (SpO2).

Arousal threshold reveals novel neural markers of sleep depth independently from the conventional sleep stages

Reports of sleep-specific brain activity patterns have been constrained by assessing brain function as it related to the conventional polysomnographic sleep stages. This limits the variety of sleep states and underlying activity patterns that one can discover. The current study used all-night functional MRI sleep data and defined sleep behaviorally with auditory arousal threshold (AAT) to characterize sleep depth better by searching for novel neural markers of sleep depth that are neuroanatomically localized and temporally unrelated to the conventional stages. Functional correlation values calculated in a four-min time window immediately before the determination of AAT were entered into a linear mixed effects model, allowing multiple arousals across the night per subject into the analysis, and compared to models with sleep stage to determine the unique relationships with AAT. These unique relationships were for thalamocerebellar correlations, the relationship between the right language network and the right "default-mode network dorsal medial prefrontal cortex subsystem," and the relationship between thalamus and ventral attention network. These novel neural markers of sleep depth would have remained undiscovered if the data were merely analyzed with the conventional sleep stages.

Identification of pregnancy in women based on fingertip pulse using a multi-feature fusion neural network model

This study proposes a rapid method for determining pregnancy status based on fingertip pulse signals. A finger pulse sensor collects data, which is processed into unified multimodal signals. The Bamboo-Net model, combining ResNet, LSTM, and 1D-CNN, extracts key features from time, frequency, and time-frequency domains. Tested on 346 training and 138 testing samples, the model achieves 91% accuracy with 6 s input, outperforming mainstream methods. Recognition rates for mid and late pregnancy are higher than for early pregnancy, highlighting its potential for practical applications.

Impact of macrohemodynamic manipulations during cardiopulmonary bypass on finger microcirculation assessed by photoplethysmography signal components

Objective.Continuous monitoring of the hemodynamic coherence between macro and microcirculation is difficult at the bedside. We tested the role of photoplethysmography (PPG) to real-time assessment of microcirculation during extreme manipulation of macrohemodynamics induced by the cardiopulmonary bypass (CPB).Approach.We analyzed the alternating (AC) and direct (DC) components of the finger PPG in 12 patients undergoing cardiac surgery with CPB at five moments: (1) before-CPB; (2) CPB-start, at the transition from pulsatile to non-pulsatile blood flow; (3) CPB-aortic clamping, at a sudden decrease in pump blood flow and volemia.; (4) CPB-weaning, during step-wise 20% decreases in pump blood flow and opposite proportional increases in native pulsatile blood flow; and (5) after-CPB.Main results.Nine Caucasian men and three women were included for analysis. Macrohemodynamic changes during CPB had an immediate impact on the PPG at all studied moments. Before-CPB the AC signal amplitude showed a median and IQR values of 0.0023(0.0013). The AC signal completely disappeared at CPB-start and at CPB-aortic clamping. During CPB weaning its amplitude progressively increased but remained lower than before CPB, at 80% [0.0008 (0.0005);p< 0.001], 60% [0.0010(0.0006);p< 0.001], and 40% [0.0013(0.0009);p= 0.011] of CPB flow. The AC amplitude returned close to Before-CPB values at 20% of CPB flow [0.0015(0.0008);p= 0.081], when CPB was completely stopped [0.0019 (0.0009);p= 0.348], and at after-CPB [0.0021(0.0009);p= 0.687]. The DC signal Before-CPB [0.95(0.02)] did not differ statistically from CPB-start, CPB-weaning and After-CPB. However, at CPB-aortic clamping, at no flow and a sudden drop in volemia, the DC signal decreased from [0.96(0.01)] to [0.94(0.02);p= 0.002].Significance.The macrohemodynamic alterations brought on by CPB were consistent with changes in the finger's microcirculation. PPG described local pulsatile blood flow (AC) as well as non-pulsatile blood flow and volemia (DC) in the finger. These findings provide plausibility to the use of PPG in ongoing hemodynamic coherence monitoring.

Validation of a Wearable Sensor Prototype for Measuring Heart Rate to Prescribe Physical Activity: Cross-Sectional Exploratory Study

BACKGROUND

Wearable sensors are rapidly evolving, particularly in health care, due to their ability to facilitate continuous or on-demand physiological monitoring.

OBJECTIVE

This study aimed to design and validate a wearable sensor prototype incorporating photoplethysmography (PPG) and long-range wide area network technology for heart rate (HR) measurement during a functional test.

METHODS

We conducted a transversal exploratory study involving 20 healthy participants aged between 20 and 30 years without contraindications for physical exercise. Initially, our laboratory developed a pulse wearable sensor prototype for HR monitoring. Following this, the participants were instructed to perform the Incremental Shuttle Walk Test while wearing the Polar H10 HR chest strap sensor (the reference for HR measurement) and the wearable sensor. This test allowed for real-time comparison of HR responses between the 2 devices. Agreement between these measurements was determined using the intraclass correlation coefficient (ICC3.1) and Lin concordance correlation coefficient. The mean absolute percentage error was calculated to evaluate reliability or validity. Cohen d was used to calculate the agreement's effect size.

RESULTS

The mean differences between the Polar H10 and the wearable sensor during the test were -2.6 (95% CI -3.5 to -1.8) for rest HR, -4.1 (95% CI -5.3 to -3) for maximum HR, -2.4 (95% CI -3.5 to -1.4) for mean test HR, and -2.5 (95% CI -3.6 to -1.5) for mean recovery HR. The mean absolute percentage errors were -3% for rest HR, -2.2% for maximum HR, -1.8% for mean test HR, and -1.6% for recovery HR. Excellent agreement was observed between the Polar H10 and the wearable sensor for rest HR (ICC3.1=0.96), mean test HR (ICC3.1=0.92), and mean recovery HR (ICC3.1=0.96). The agreement for maximum HR (ICC3.1=0.78) was considered good. By the Lin concordance correlation coefficient, the agreement was found to be substantial for rest HR (rc=0.96) and recovery HR (rc=0.96), moderate for mean test HR (rc=0.92), and poor for maximum HR (rc=0.78). The power of agreement between the Polar H10 and the wearable sensor prototype was large for baseline HR (Cohen d=0.97), maximum HR (Cohen d=1.18), and mean recovery HR (Cohen d=0.8) and medium for mean test HR (Cohen d= 0.76).

CONCLUSIONS

The pulse-wearable sensor prototype tested in this study proves to be a valid tool for monitoring HR at rest, during functional tests, and during recovery compared with the Polar H10 reference device used in the laboratory setting.

Robust modelling of arterial blood pressure reconstruction from photoplethysmography

Blood pressure is a crucial indicator of cardiovascular disease, and arterial blood pressure (ABP) waveforms contain information that reflects the cardiovascular status. We propose a novel deep-learning method that converts photoplethysmogram (PPG) signals into ABP waveforms. We used [Formula: see text]-Net as a feature extractor and designed a Bi-block to capture individualised time information in encoder feature extraction. We further enhanced the prediction accuracy of the ABP waveforms by applying a combined loss function to each layer of deep supervision. We also propose a total error index (TEI) to measure overall performance. Furthermore, we extended our method from the UCI dataset to the VitalDB dataset, achieving mean absolute error ± standard deviation (MAE ± STD) values of 2.48 ± 1.95, 1.42 ± 1.42, and 1.48 ± 1.36 mmHg for systolic blood pressure (SBP), diastolic blood pressure (DBP), and mean arterial pressure (MAP) in UCI dataset, and 2.16 ± 1.53, 1.12 ± 0.59, and 1.35 ± 0.84 mmHg in VitalDB dataset, respectively. The mean ± STD values of the TEI index are 0.29 ± 0.10 in UCI dataset and 0.29 ± 0.15 in VitalDB dataset. These results demonstrate the superiority of the proposed method over existing methods and its robustness to different sampling frequencies and devices.

A novel approach for contactless heart rate monitoring from pet facial videos

Introduction

Monitoring the heart rate (HR) of pets is challenging when contact with a conscious pet is inconvenient, difficult, injurious, distressing, or dangerous for veterinarians or pet owners. However, few established, simple, and non-invasive techniques for HR measurement in pets exist.

Methods

To address this gap, we propose a novel, contactless approach for HR monitoring in pet dogs and cats, utilizing facial videos and imaging photoplethysmography (iPPG). This method involves recording a video of the pet's face and extracting the iPPG signal from the video data, offering a simple, non-invasive, and stress-free alternative to conventional HR monitoring techniques. We validated the accuracy of the proposed method by comparing it to electrocardiogram (ECG) recordings in a controlled laboratory setting.

Results

Experimental results indicated that the average absolute errors between the reference ECG monitor and iPPG estimates were 2.94 beats per minute (BPM) for dogs and 3.33 BPM for cats under natural light, and 2.94 BPM for dogs and 2.33 BPM for cats under artificial light. These findings confirm the reliability and accuracy of our iPPG-based method for HR measurement in pets.

Discussion

This approach can be applied to resting animals for real-time monitoring of their health and welfare status, which is of significant interest to both veterinarians and families seeking to improve care for their pets.

Autonomic nervous system and endocrine system response to upper or lower cervical spine mobilization in males with persistent post-concussion symptoms: a proof-of-concept trial

INTRODUCTION

The peripheral stress response, consisting of the autonomic nervous system (ANS) and hypothalamic pituitary adrenal-axis (HPA-axis), functions to maintain homeostasis in response to stressors. Cervical spine manual therapy has been shown to differentially modulate the stress response in healthy populations. No study has investigated whether cervical spine mobilizations can differentially modulate the stress response in individuals with persistent post-concussion symptoms (PPCS), a population characterized by a dysfunctional stress response.

METHODS

A randomized, controlled, parallel design trial was performed to investigate whether upper or lower cervical spine mobilization can differentially modulate components of the stress response in individuals with PPCS. The outcomes were salivary cortisol (sCOR) concentration (primary) and the HRV metric, rMSSD, measured with a smartphone application (secondary). Nineteen males diagnosed with PPCS, aged 19-35, were included. Participants were randomly assigned into either intervention group, upper (n = 10) or lower (n = 9) cervical spine mobilization. Each outcome was collected at different time points, pre- and post-intervention. Statistical analyses were performed using the Friedman's Two-Way ANOVA, Mann-Whitney U test, and Wilcoxon Signed Rank Test.

RESULTS

There was a statistically significant within-group reduction in sCOR concentration 30 minutes following lower cervical spine mobilizations and statistically significant within-group increase in rMSSD 30 minutes following upper cervical spine mobilizations.

CONCLUSION

The results of this trial provide preliminary evidence for cervical spine mobilizations to differentially modulate components of the stress response at specific time points. Understanding the mechanisms of the effect of cervical spine mobilizations on the stress response provides a novel rationale for selecting cervical spine mobilizations to rehabilitate individuals with PPCS.

Heart rate variability wrist-wearable biomarkers identify adverse posttraumatic neuropsychiatric sequelae after traumatic stress exposure

Adverse posttraumatic neuropsychiatric sequelae (APNS) are common after traumatic events. We examined whether wrist-wearable devices could provide heart rate variability (HRV) biomarkers for recovery after traumatic stress exposure in a large socioeconomically disadvantaged cohort. Participants were enrolled in the emergency department within 72 hours after a traumatic event as part of the AURORA (Advancing Understanding of RecOvery afteR traumA) multicenter prospective observational cohort study and followed over 6 months. HRV biomarkers were derived and validated for associations with specific APNS symptoms at a point in time and changes in symptom severity over time. Sixty-four HRV characteristics were derived and validated as cross-sectional biomarkers of APNS symptoms, including pain (26), re-experiencing (8), somatic (7), avoidance (7), concentration difficulty (6), hyperarousal (5), nightmares (1), anxiety (1), and sleep disturbance (3). Changes in 22 HRV characteristics were derived and validated as biomarkers identifying changes in APNS symptoms, including reexperiencing (11), somatic (3), avoidance (2), concentration difficulty (1), hyperarousal (1), and sleep disturbance (4). Changes in HRV variables over time predicted symptom improvement (PPV 0.68-0.87) and symptom worsening (NPV 0.71-0.90). HRV biomarkers collected from wrist-wearable devices may have utility as screening tools for APNS symptoms that occur after traumatic stress exposure in high-risk populations.

Transforming in-clinic post-operative and intermediate care with cosinuss°

Continuous, mobile patient monitoring plays a critical role in healthcare, particularly for post-surgery, intermediate care in clinics. The implementation of vital signs monitoring technology enables healthcare professionals to triage patients effectively by maintaining real-time awareness of their health status and allowing for prompt intervention when necessary. This technology supports early mobilization and facilitates the detection of potential complications such as post-surgical sepsis. cosinuss° technology has been evaluated in various studies, in terms of its accuracy in capturing vital parameters and its usability, emphasizing its potential to enhance intermediate patient care and outcomes. This report outlines the design and implementation of cosinuss° Health patient monitoring solution for use in intermediate, postoperative clinic settings. It presents the results and insights from three recent, in-clinic applications, discussing both technical and practical aspects, clinical processes, and the reported satisfaction from both patients and medical caregivers. The findings highlight the promising potential of cosinuss° Health on improving patient monitoring and overall clinical outcomes.

Contactless and short-range vital signs detection with doppler radar millimetre-wave (76-81 GHz) sensing firmware

Vital signs such as heart rate (HR) and respiration rate (RR) are essential physiological parameters that are routinely used to monitor human health and bodily functions. They can be continuously monitored through contact or contactless measurements performed in the home or a hospital. In this study, a contactless Doppler radar W-band sensing system was used for short-range, contactless vital sign estimation. Frequency-modulated continuous wave (FMCW) measurements were performed to reduce the influence of a patient's micromotion. Sensing software was developed that can process the received chirps to filter and extract heartbeat and breathing rhythm signals. The proposed contactless sensing system eliminates the need for the contact electrodes, electric patches, photoelectric sensors, and conductive wires used in typical physiological sensing methods. The system operates at 76-81 GHz in FMCW mode and can detect objects on the basis of changes in frequency and phase. The obtained signals are used to precisely monitor a patient's HR and RR with minimal noise interference. In a laboratory setting, the heartbeats and breathing rhythm signals of healthy young participants were measured, and their HR and RR were estimated through frequency- and time-domain analyses. The experimental results confirmed the feasibility of the proposed W-band mm-wave radar for contactless and short-range continuous detection of human vital signs.

Machine Learning-Based Cardiac Output Estimation Using Photoplethysmography in Off-Pump Coronary Artery Bypass Surgery

Background/Objectives: Hemodynamic monitoring is crucial for managing critically ill patients and those undergoing major surgeries. Cardiac output (CO) is an essential marker for diagnosing hemodynamic deterioration and guiding interventions. The gold standard thermodilution method for measuring CO is invasive, prompting a search for non-invasive alternatives. This pilot study aimed to develop a non-invasive algorithm for classifying the cardiac index (CI) into low and non-low categories using finger photoplethysmography (PPG) and a machine learning model. Methods: PPG and continuous thermodilution CO data were collected from patients undergoing off-pump coronary artery bypass graft surgery. The dataset underwent preprocessing, and features were extracted and selected using the Relief algorithm. A CatBoost machine learning model was trained and evaluated using a validation and testing phase approach. Results: The developed model achieved an accuracy of 89.42% in the validation phase and 87.57% in the testing phase. Performance was balanced across low and non-low CO categories, demonstrating robust classification capabilities. Conclusions: This study demonstrates the potential of machine learning and non-invasive PPG for accurate CO classification. The proposed method could enhance patient safety and comfort in critical care and surgical settings by providing a non-invasive alternative to traditional invasive CO monitoring techniques. Further research is needed to validate these findings in larger, diverse patient populations and clinical scenarios.

A Review on Assisted Living Using Wearable Devices

Forecasts about the aging trend of the world population agree on identifying increased life expectancy as a serious risk factor for the financial sustainability of social healthcare systems if not properly supported by innovative care management policies. Such policies should include the integration within traditional healthcare services of assistive technologies as tools for prolonging healthy and independent living at home, but also for introducing innovations in clinical practice such as long-term and remote health monitoring. For their part, solutions for active and assisted living have now reached a high degree of technological maturity, thanks to the considerable amount of research work carried out in recent years to develop highly reliable and energy-efficient wearable sensors capable of enabling the development of systems to monitor activity and physiological parameters over time, and in a minimally invasive manner. This work reviews the role of wearable sensors in the design and development of assisted living solutions, focusing on human activity recognition by joint use of onboard electromyography sensors and inertial measurement units and on the acquisition of parameters related to overall physical and psychological conditions, such as heart activity and skin conductance.

Development of a novel light-sensitive PPG model using PPG scalograms and PPG-NET learning for non-invasive hypertension monitoring

Background and objective

Photoplethysmography (PPG) signals provide a non-invasive method for monitoring cardiovascular health, including blood pressure levels, which are critical for the early detection and management of hypertension. This study leverages wavelet transformation and special purpose deep learning model, enhanced by signal processing and normalization, to classify blood pressure stages from PPG signals. The primary objective is to advance non-invasive hypertension monitoring, improving the accuracy and efficiency of these assessments.

Methods

The study employed continuous wavelet transform (CWT) to prepare PPG signals for analysis using a special purpose PPG-NET designed by applying advanced deep-learning models. PPG-NET was verified by applying several pre-trained models, including Inception, MobileNetV2, InceptionResNetV2, and others to the PPG data. Rigorously five-fold cross-validated models were conducted to obtain the models' performance to ensure robustness and repeatability of results.

Results

The PPG-NET model demonstrated superior performance, achieving a perfect accuracy of 100 % in classifying the four stages of hypertension-normal, prehypertension, stage 1, and stage 2. The evaluation metrics reported include precision, sensitivity, and specificity, with the PPG-NET model achieving 100 % across all metrics. Other models showed varying levels of accuracy, with InceptionV3 also reaching 91.5 %, while some, like VGG-19, underperformed significantly.

Conclusions

Integrating CWT and PPG-NET offers a promising avenue for enhancing non-invasive blood pressure monitoring. The PPG-NET model, in particular, showed potential for clinical application due to its high accuracy and reliability. This study showed the effectiveness of combining advanced computational techniques with traditional PPG analysis, potentially leading to more personalized and accessible hypertension management strategies.

Evaluation of photoplethysmography-based monitoring of pulse rate, interbeat-intervals, and oxygen saturation during high-intensity interval training

BACKGROUND

Heart disease patients necessitate precise monitoring to ensure the safety and efficacy of their physical activities when managing conditions such as hypertension or heart failure. This study, therefore, aimed to evaluate the accuracy of photoplethysmography (PPG)-based monitoring of pulse rate (PR), interbeat-intervals (IB-I) and oxygen saturation (SpO2) during high-intensity interval training (HIIT).

METHODS

Between January and March 2024, healthy volunteers were subjected to a cycling HIIT workout with bike resistance increments to evaluate performance within different heart rate ranges. To determine the accuracy of PPG-based measurements for PR, IB-I, and SpO2 using the CardioWatch 287-2 (Corsano Health, the Netherlands), measurements throughout these ranges were compared to paired reference values from the Covidien Nellcor pulse oximeter (PM10N) and Vivalink's wearable ECG patch monitor. Subgroups were defined for Fitzpatrick skin type and gender.

RESULTS

In total, 35 healthy individuals participated, resulting in 7183 paired measurements for PR, 22,713 for IB-I, and 41,817 for SpO2. The PR algorithm showed an average root mean square (Arms) of 2.51 beats per minute (bpm), bias at 0.05 bpm, and limits of agreement (LoA) from -4.87 to 4.97 bpm. The IB-I algorithm achieved an Arms of 23.00 ms, a bias of 1.00 ms, and LoA from -43.82 to 46.21 ms. Finally, the SpO2 algorithm showed an Arms of 1.28%, a bias of 0.13%, and LoA from -2.37% to 2.62%. The results were consistent across different demographic subgroups.

CONCLUSIONS

This study demonstrates that the PPG-based CardioWatch 287-2 can accurately monitor PR, IB-I, and SpO2 during HIIT. However, further research is recommended to evaluate the algorithm's performance in heart disease patients during demanding exercise.

Machine Learning Applied to Reference Signal-Less Detection of Motion Artifacts in Photoplethysmographic Signals: A Review

Machine learning algorithms have brought remarkable advancements in detecting motion artifacts (MAs) from the photoplethysmogram (PPG) with no measured or synthetic reference data. However, no study has provided a synthesis of these methods, let alone an in-depth discussion to aid in deciding which one is more suitable for a specific purpose. This narrative review examines the application of machine learning techniques for the reference signal-less detection of MAs in PPG signals. We did not consider articles introducing signal filtering or decomposition algorithms without previous identification of corrupted segments. Studies on MA-detecting approaches utilizing multiple channels and additional sensors such as accelerometers were also excluded. Despite its promising results, the literature on this topic shows several limitations and inconsistencies, particularly those regarding the model development and testing process and the measures used by authors to support the method's suitability for real-time applications. Moreover, there is a need for broader exploration and validation across different body parts and a standardized set of experiments specifically designed to test and validate MA detection approaches. It is essential to provide enough elements to enable researchers and developers to objectively assess the reliability and applicability of these methods and, therefore, obtain the most out of them.

The behavioral and physiological correlates of affective mood switching in premenstrual dysphoric disorder

Premenstrual dysphoric disorder (PMDD), a more severe manifestation of premenstrual syndrome (PMS), is characterized by emotional, behavioral, and physical symptoms that begin in the mid-to-late luteal phase of the menstrual cycle, when estradiol and progesterone levels precipitously decline, and remit after the onset of menses. Remotely monitoring physiologic variables associated with PMDD depression symptoms, such as heart rate variability (HRV), sleep, and physical activity, holds promise for developing an affective state prediction model. Switching into and out of depressive states is associated with an increased risk of suicide, and therefore, monitoring periods of affective switching may help mitigate risk. Management of other chronic health conditions, including cardiovascular disease and diabetes, has benefited from remote digital monitoring paradigms that enable patients and physicians to monitor symptoms in real-time and make behavioral and medication adjustments. PMDD is a chronic condition that may benefit from real-time, remote monitoring. However, clinical practice has not advanced to monitoring affective states in real-time. Identifying remote monitoring paradigms that can detect within-person affective state change may help facilitate later research on timely and efficacious interventions for individuals with PMDD. This narrative review synthesizes the current literature on behavioral and physiological correlates of PMDD suitable for remote monitoring during the menstrual cycle. The reliable measurement of heart rate variability (HRV), sleep, and physical activity, with existing wearable technology, suggests the potential of a remote monitoring paradigm in PMDD and other depressive disorders.

Assessment of Physiological Signals from Photoplethysmography Sensors Compared to an Electrocardiogram Sensor: A Validation Study in Daily Life

Wearables with photoplethysmography (PPG) sensors are being increasingly used in clinical research as a non-invasive, inexpensive method for remote monitoring of physiological health. Ensuring the accuracy and reliability of PPG-derived measurements is critical, as inaccuracies can impact research findings and clinical decisions. This paper systematically compares heart rate (HR) and heart rate variability (HRV) measures from PPG against an electrocardiogram (ECG) monitor in free-living settings. Two devices with PPG and one device with an ECG sensor were worn by 25 healthy volunteers for 10 days. PPG-derived HR and HRV showed reasonable accuracy and reliability, particularly during sleep, with mean absolute error < 1 beat for HR and 6-15 ms for HRV. The relative error of HRV estimated from PPG varied with activity type and was higher than during the resting state by 14-51%. The accuracy of HR/HRV was impacted by the proportion of usable data, body posture, and epoch length. The multi-scale peak and trough detection algorithm demonstrated superior performance in detecting beats from PPG signals, with an F1 score of 89% during sleep. The study demonstrates the trade-offs of utilizing PPG measurements for remote monitoring in daily life and identifies optimal use conditions by recommending enhancements.

Evaluating AI Methods for Pulse Oximetry: Performance, Clinical Accuracy, and Comprehensive Bias Analysis

Blood oxygen saturation (SpO2) is vital for patient monitoring, particularly in clinical settings. Traditional SpO2 estimation methods have limitations, which can be addressed by analyzing photoplethysmography (PPG) signals with artificial intelligence (AI) techniques. This systematic review, following PRISMA guidelines, analyzed 183 unique references from WOS, PubMed, and Scopus, with 26 studies meeting the inclusion criteria. The review examined AI models, key features, oximeters used, datasets, tested saturation intervals, and performance metrics while also assessing bias through the QUADAS-2 criteria. Linear regression models and deep neural networks (DNNs) emerged as the leading AI methodologies, utilizing features such as statistical metrics, signal-to-noise ratios, and intricate waveform morphology to enhance accuracy. Gaussian Process models, in particular, exhibited superior performance, achieving Mean Absolute Error (MAE) values as low as 0.57% and Root Mean Square Error (RMSE) as low as 0.69%. The bias analysis highlighted the need for better patient selection, reliable reference standards, and comprehensive SpO2 intervals to improve model generalizability. A persistent challenge is the reliance on non-invasive methods over the more accurate arterial blood gas analysis and the limited datasets representing diverse physiological conditions. Future research must focus on improving reference standards, test protocols, and addressing ethical considerations in clinical trials. Integrating AI with traditional physiological models can further enhance SpO2 estimation accuracy and robustness, offering significant advancements in patient care.

MDAR: A Multiscale Features-Based Network for Remotely Measuring Human Heart Rate Utilizing Dual-Branch Architecture and Alternating Frame Shifts in Facial Videos

Remote photoplethysmography (rPPG) refers to a non-contact technique that measures heart rate through analyzing the subtle signal changes of facial blood flow captured by video sensors. It is widely used in contactless medical monitoring, remote health management, and activity monitoring, providing a more convenient and non-invasive way to monitor heart health. However, factors such as ambient light variations, facial movements, and differences in light absorption and reflection pose challenges to deep learning-based methods. To solve these difficulties, we put forward a measurement network of heart rate based on multiscale features. In this study, we designed and implemented a dual-branch signal processing framework that combines static and dynamic features, proposing a novel and efficient method for feature fusion, enhancing the robustness and reliability of the signal. Furthermore, we proposed an alternate time-shift module to enhance the model's temporal depth. To integrate the features extracted at different scales, we utilized a multiscale feature fusion method, enabling the model to accurately capture subtle changes in blood flow. We conducted cross-validation on three public datasets: UBFC-rPPG, PURE, and MMPD. The results demonstrate that MDAR not only ensures fast inference speed but also significantly improves performance. The two main indicators, MAE and MAPE, achieved improvements of at least 30.6% and 30.2%, respectively, surpassing state-of-the-art methods. These conclusions highlight the potential advantages of MDAR for practical applications.

Photoplethysmography Features Correlated with Blood Pressure Changes

Blood pressure measurement is a key indicator of vascular health and a routine part of medical examinations. Given the ability of photoplethysmography (PPG) signals to provide insights into the microvascular bed and their compatibility with wearable devices, significant research has focused on using PPG signals for blood pressure estimation. This study aimed to identify specific clinical PPG features that vary with different blood pressure levels. Through a literature review of 297 publications, we selected 16 relevant studies and identified key time-dependent PPG features associated with blood pressure prediction. Our analysis highlighted the second derivative of PPG signals, particularly the b/a and d/a ratios, as the most frequently reported and significant predictors of systolic blood pressure. Additionally, features from the velocity and acceleration photoplethysmograms were also notable. In total, 29 features were analyzed, revealing novel temporal domain features that show promise for further research and application in blood pressure estimation.

Survey on portable sensing technologies for the radial artery characterization

The radial artery, one of the terminal branches of the forearm, is utilized for vascular access and in various non-invasive measurement method, providing crucial medical insights. Various sensor technologies have been developed, each suited to specific characterization requirements. The work presented in this paper is based on a systematic literature review of the main publications relating to this topic. Analysis of the forearm vascular system complex array of anatomical structures shows that the radial artery can be characterized by its size, position, elasticity, tissue evaluation, blood flow and blood composition. The survey of medical procedures for patient monitoring, diagnosis and pre-operative validation shows the use of measures for pulse wave, blood pressure, heart rate, skin temperature, tissue response,…By exploring sensor technologies used for artery characterization, we produce a synthesis of measurement principles, measured phenomena and measurement accuracy for capacitive, piezoresistive, bioimpedance, thermography, fiber optic based, piezoelectric and photoacoustic sensors. A comparative study is conducted for sensor technologies by considering the metrics of the information to be collected and the associated accuracy as well as the portability, the complexity of the processing, the cost and the mode of contact with the arm. Finally, a comprehensive framework is proposed to facilitate informed decisions in the development of medical devices tailored to specific characterization needs.

Associations of Personal Hourly Exposures to Air Temperature and Pollution with Resting Heart Rate in Chronic Obstructive Pulmonary Disease

Previous studies linked higher daily ambient air temperature and pollution with increased cardiorespiratory morbidity, but immediate effects of personal, hourly exposures on resting heart rate remained unclear. We followed 30 older former smokers with chronic obstructive pulmonary disease (COPD) in Massachusetts for four nonconsecutive 30-day periods over 12 months, collecting 54,487 hourly observations of personal air temperature, fine particulate matter (PM2.5), nitrogen dioxide (NO2), ozone (O3), and resting heart rate. We explored the single lag effects (0-71 h) and cumulative effects (0-5 h, the significant lag windows) of air temperature and pollution on resting heart rate using generalized additive mixed models with distributed lag nonlinear models. Single lag effects of higher air temperature and pollutants on higher resting heart rate were most pronounced at lag 0 to 5 h. Cumulative effects of higher air temperature, PM2.5, O3, and NO2 (each interquartile range increment) on higher resting heart rate at lag 0-5 h, show differences of (beats per minute [bpm], 95% CI) 1.46 (1.31-1.62), 0.35 (0.32-0.39), 2.32 (2.19-2.45), and 1.79 (1.66-1.92), respectively. In conclusion, higher personal hourly air temperature, PM2.5, O3, and NO2 exposures at lag 0-5 h are associated with higher resting heart rate in COPD patients.

Leveraging Classifier Performance Using Heuristic Optimization for Detecting Cardiovascular Disease from PPG Signals

BACKGROUND/OBJECTIVES

Photoplethysmography (PPG) signals, which measure blood volume changes through light absorption, are increasingly used for non-invasive cardiovascular disease (CVD) detection. Analyzing PPG signals can help identify irregular heart patterns and other indicators of CVD.

METHODS

This research involves a total of 41 subjects sourced from the CapnoBase database, consisting of 21 normal subjects and 20 CVD cases. In the initial stage, heuristic optimization algorithms, such as ABC-PSO, the Cuckoo Search algorithm (CSA), and the Dragonfly algorithm (DFA), were applied to reduce the dimension of the PPG data. Next, these Dimensionally Reduced (DR) PPG data are then fed into various classifiers such as Linear Regression (LR), Linear Regression with Bayesian Linear Discriminant Classifier (LR-BLDC), K-Nearest Neighbors (KNN), PCA-Firefly, Linear Discriminant Analysis (LDA), Kernel LDA (KLDA), Probabilistic LDA (ProbLDA), SVM-Linear, SVM-Polynomial, and SVM-RBF, to identify CVD. Classifier performance is evaluated using Accuracy, Kappa, MCC, F1 Score, Good Detection Rate (GDR), Error rate, and Jaccard Index (JI).

RESULTS

The SVM-RBF classifier for ABC PSO dimensionality reduced values outperforms other classifiers, achieving the highest accuracy of 95.12% along with the minimum error rate of 4.88%. In addition to that, it provides an MCC and kappa value of 0.90, a GDR and F1 score of 95%, and a Jaccard Index of 90.48%.

CONCLUSIONS

This study demonstrated that heuristic-based optimization and machine learning classification of PPG signals are highly effective for the non-invasive detection of cardiovascular disease.

Clinical evaluation of a smart wristband for monitoring oxygen saturation, pulse rate, and respiratory rate

Recently, photoplethysmography-based vital parameter measurements have increased in popularity. However, clinical evaluation of these measurements is lacking. The objective of this study was to rigorously evaluate the clinical accuracy and reliability of a novel photoplethysmography-based wristband for measuring key vital parameters-oxygen saturation (SpO2), respiratory rate (RR), and pulse rate (PR)-during heart catheterisations. Vital parameters obtained during heart catheterisations by means of a photoplethysmography-based wristband (CardioWatch 287-2, Corsano Health) were compared to reference measurements performed by a Nellcor fingerclip (SpO2, PR) as well as a 5-lead ECG (RR) (QMAPP Haemodynamic Monitoring module, Fysicon B.V.) by means of correlation coefficients and root means squared error (RMSE). Effects of skin colour and arm hair density were additionally evaluated. In total, 945 samples from a total of 100 patients were included in the analysis. The correlation coefficients and RSME obtained for the difference between reference and photoplethysmography-based wristband measurements were r = 0.815 and 1.6% for SpO2, r = 0.976 and 0.9 brpm for RR, and r = 0.995 and 1.3 bpm for PR. Similar results were obtained across all skin colour and arm hair density subcategories. This study shows that photoplethysmography-based SpO2, RR, and PR measurements can be accurate during heart catheterisations. Future investigations are required to evaluate the wristband's performance under dynamic circumstances as well as over an extended time period. Trial registration: www.clinicaltrials.gov, NCT05566886.

Exploration of the Conditions for Occurrence of Photoplethysmographic Signal Inversion above the Dorsalis Pedis Artery

Inversion of the photoplethysmographic (PPG) signal is a rarely reported case. This signal anomaly can have implications for PPG-based cardiovascular assessments. The conditions for PPG signal inversion in the vicinity of the dorsalis pedis (DPA) artery of the foot were investigated. Wireless multi-wavelength PPG sensing with skin-probe contact pressure and local skin temperature were studied at different sensor positions, and the occurrence of inversion (OOI) was investigated. Twelve healthy adult volunteers were studied over four LED wavelengths at three levels of contact pressure for 11 probe positions. A novel algorithm quantified the proportion of inverted samples with respect to the abovementioned variables. Our algorithm classifying inverted vs. non-inverted pulses achieved 98.3% accuracy. Ten of the participants had at least one inverted signal identified. The impact of interindividual variation on inversion prevalence was large, but different LEDs, relative position to the DPA and sensor contact pressure also affected OOI. Skin surface and room temperatures showed no impact on OOI. Lateral measurements showed 39.6% more inversion at maximum compared to minimum contact pressure. Mechanical capillary bed variations and arterial reflections during venous engorgement are considered viable explanations for our observations. These findings motivate an expanded study of the occurrence of PPG signal inversion.

Oxygen saturation measurement in cyanotic heart disease with the Apple watch

BACKGROUND

Accurate measurement of transcutaneous oxygen saturation is important for the assessment of cyanosis in CHD. Aim of this study was the evaluation of a supplementary transcutaneous oxygen saturation measurement with an Apple watch® in children with cyanotic heart disease.

MATERIAL AND METHODS

During a six-minute walk test, measurement of transcutaneous oxygen saturation was performed simultaneously with an Oximeter (Nellcor, Medtronic, USA) and an Apple watch® Series 7 (Apple inc, USA) in 36 children with cyanotic heart disease.

RESULTS

Median age was 9.2 (IQR 5.7-13.8) years. Transcutaneous oxygen saturation measurement with the Apple watch® was possible in 35/36 and 34/36 subjects before and after six-minute walk test. Children, in whom Apple watch® measurement was not possible, had a transcutaneous oxygen saturation < 85% on oximeter. Before six-minute walk test, median transcutaneous oxygen saturation was 93 (IQR 91-97) % measured by oximeter and 95 (IQR 93-96) % by the Apple watch®. After a median walking distance of 437 (IQR 360-487) m, transcutaneous oxygen saturation dropped to 92 (IQR 88-95, p < 0.001) % by oximeter and to 94 (IQR 90-96, p = 0.013) % measured with the Apple watch®.

CONCLUSION

In children with mild cyanosis measurement of transcutaneous oxygen saturation with an Apple watch® showed only valid results if transcutaneous oxygen saturation was > 85%, with higher values being measured with the smart watch. In children with moderate or severe cyanosis transcutaneous oxygen saturation, measurement with the Apple watch® was not reliable and cannot be recommended to monitor oxygen saturation at home.

Comparative Analysis of Heart Rate Variability and Arterial Stiffness in Elite Male Athletes after COVID-19

This study investigated the long-term cardiovascular effects of coronavirus disease (COVID-19) in elite male athletes by comparing the heart rate variability (HRV), arterial stiffness, and other cardiovascular parameters between those with and without prior COVID-19 infection. Methods: This cross-sectional study evaluated 120 elite male athletes (60 post COVID-19, 60 controls) using anthropometric measurements, body composition analysis, pulmonary function tests, HRV analysis, arterial stiffness assessments, hemodynamic monitoring, and microcirculatory function tests. Results: Athletes post COVID-19 showed significantly higher lean mass (p = 0.007), forced vital capacity (p = 0.001), and forced expiratory volume in 1 s (p = 0.007) than controls. HRV parameters did not significantly differ between the groups. Post-COVID-19 athletes exhibited peripheral vascular resistance (p = 0.048) and reflection index (p = 0.038). No significant differences were observed in the blood pressure, cardiac output, oxygen saturation, or microcirculatory oxygen absorption. Conclusions: Elite male athletes showed notable cardiovascular resilience after COVID-19, with only minor differences in vascular function. The maintained cardiac autonomic function and improved lung parameters in post-COVID-19 athletes suggests an adaptive response. These findings support the cardiovascular health of elite athletes following COVID-19 but emphasize the importance of continued monitoring.

Cardiovascular and vasomotor pulsations in the brain and periphery during awake and NREM sleep in a multimodal fMRI study

Introduction

The cerebrospinal fluid dynamics in the human brain are driven by physiological pulsations, including cardiovascular pulses and very low-frequency (< 0.1 Hz) vasomotor waves. Ultrafast functional magnetic resonance imaging (fMRI) facilitates the simultaneous measurement of these signals from venous and arterial compartments independently with both classical venous blood oxygenation level dependent (BOLD) and faster arterial spin-phase contrast.

Methods

In this study, we compared the interaction of these two pulsations in awake and sleep using fMRI and peripheral fingertip photoplethysmography in both arterial and venous signals in 10 healthy subjects (5 female).

Results

Sleep increased the power of brain cardiovascular pulsations, decreased peripheral pulsation, and desynchronized them. However, vasomotor waves increase power and synchronicity in both brain and peripheral signals during sleep. Peculiarly, lag between brain and peripheral vasomotor signals reversed in sleep within the default mode network. Finally, sleep synchronized cerebral arterial vasomotor waves with venous BOLD waves within distinct parasagittal brain tissue.

Discussion

These changes in power and pulsation synchrony may reflect systemic sleep-related changes in vascular control between the periphery and brain vasculature, while the increased synchrony of arterial and venous compartments may reflect increased convection of regional neurofluids in parasagittal areas in sleep.

Relationship Between Finger Photoplethysmographic Pulses and Skin Blood Perfusion

Introduction Photoplethysmography (PPG) measures are important in monitoring peripheral oxygen saturation (SpO2). Another parameter is a derived quantity referred to as the peripheral perfusion index (PPI). It is calculated as the ratio of the peak-to-peak pulse amplitude of a PPG signal (PAPPG) to the non-pulsating part of the total PPG signal. The PPI has been used as a marker of blood perfusion states in a variety of clinical settings but has not been systematically and directly compared to measures of local blood perfusion. This study's purpose was to investigate this issue to provide initial data on the relationship between finger skin blood perfusion, measured by laser Doppler blood perfusion flux (LDF) and PAPPG. Methods Ten subjects (five male), recruited from medical students with an average age of 26 years, participated. While supine for 30 minutes, skin blood perfusion was recorded using laser Doppler flux (LDF) on the ring finger pulp of the non-dominant hand, and the photoplethysmography pulse (PPG) was recorded from the index finger of the same hand. The recorded data was searched sequentially manually to locate the first 30-pulse sequence in which the PPG amplitude of at least six PPG pulses was less than or equal to 60% of the maximum pulse amplitude in the sequence. The primary PPG parameter of interest was PAPPG. For the LDF signal, the pulse amplitude is designated as PALDF, the total LDF for each pulse is designated as LDFTOT, and the LDF pulsatile component is designated as PF. To investigate the relationship between LDF parameters and PAPPG a linear regression analysis of each 30-pulse sequence was done with PAPPG as the independent variable and each of the three LDF parameters individually (PALDF, LDFTOT, and PF) as dependent variables.  Results There was a statistically significant direct relationship between PAPPG and all three measures of blood perfusion (p<0.05). Correlation coefficients (R) varied among subjects but within-subject variations versus PAPPG were similar, having mean values that ranged from 0.665 to 0.694. The results also provided evidence in support of a direct relationship between the LDF pulsatility index, defined as the ratio of PF to its mean value., and PAPPG (R=0.779). Conclusions When finger PPG pulse amplitudes are measured in individual subjects there is a moderate-to-strong correlation between the PPG pulse amplitude changes and skin blood perfusion changes. This fact impacts the confidence in using the widely available PPG parameter, peripheral perfusion index, as an indicator of changes in tissue perfusion. However, differences in the PPG pulse amplitude among subjects were less reliable indicators of differences in blood perfusion among subjects. The findings also indicate that a related parameter, the LDF pulsatility index, is also highly correlated with the PPG pulse amplitude and may serve as a useful parameter for future clinical investigations.

Robust Feature Selection for BP Estimation in Multiple Populations: Towards Cuffless Ambulatory BP Monitoring

Current blood pressure (BP) estimation methods have not achieved an accurate and adaptable approach for ambulatory diagnosis and monitoring applications of populations at risk of cardiovascular disease, generally due to a limited sample size. This paper introduces an algorithm for BP estimation solely reliant on photoplethysmography (PPG) signals and demographic features. It automatically obtains signal features and employs the Markov Blanket (MB) feature selection to discern informative and transmissible features, achieving a robust space adaptable to the population shift. This approach was validated with the Aurora-BP database, compromising ambulatory wearable cuffless BP measurements for over 500 individuals. After evaluating several machine-learning regression methods, Gradient Boosting emerged as the most effective. According to the MB feature selection, temporal, frequency, and demographic features ranked highest in importance, while statistical ones were deemed non-significant. A comparative assessment of a generic model (trained on unclassified BP data) and specialized models (tailored to each distinct BP population), demonstrated a consistent superiority of our proposed MB feature space with a mean absolute error of [Formula: see text] for systolic BP and [Formula: see text] for diastolic BP on the whole dataset. Moreover, we present a first comparison of in-clinic vs. ambulatory models, with performance significantly lower for the latter with a drop of [Formula: see text] in systolic ( ) and [Formula: see text] for diastolic ( ) estimation errors. This work contributes to the resilient understanding of BP estimation algorithms from PPG signals, providing causal features in the signal and quantifying the disparities between ambulatory and in-clinic measurements.

Leveraging Artificial Intelligence to Optimize the Care of Peripheral Artery Disease Patients

Peripheral artery disease is a major atherosclerotic disease that is associated with poor outcomes such as limb loss, cardiovascular morbidity, and death. Artificial intelligence (AI) has seen increasing integration in medicine, and its various applications can optimize the care of peripheral artery disease (PAD) patients in diagnosis, predicting patient outcomes, and imaging interpretation. In this review, we introduce various AI applications such as natural language processing, supervised machine learning, and deep learning, and we analyze the current literature in which these algorithms have been applied to PAD.