Toward Accurate Extraction of Respiratory Frequency From the Photoplethysmogram: Effect of Measurement Site

Age-Related Changes in Blood Volume Pulse Wave at Fingers and Ears

OBJECTIVE

The decline in vascular elasticity with aging can be manifested in the shape of pulse wave. The study investigated the pulse wave features that are sensitive to age and the pattern of these features change with increasing age were examined.

METHODS

Five features were proposed and extracted from the photoplethysmography (PPG)-based pulse wave or its first derivative wave. The correlation between these PPG features and ages was studied in 100 healthy subjects with a wide range of ages (20-71 years). Piecewise regression coefficients were calculated to examine the rates of change of the PPG features with age at different age stages.

RESULTS

The proposed PPG features obtained from the finger showed a strong and significant correlation with age (with r = 0.76 - 0.77, p < 0.01), indicating higher sensitivity to age changes compared to the PPG features reported in previous studies (with r = 0.66 - 0.75). The correlation remained significant even after correcting for other clinical variables. The rate of change of the PPG feature values was found to be significantly faster in subjects aged ≥40 years compared to those aged < 40 years in the healthy population. This rate of change was similar to the age-related progression of arterial stiffness evaluated by pulse wave velocity (PWV), which is considered a gold standard for evaluating vascular stiffness.

CONCLUSIONS

The proposed PPG features showed a high correlation with chronological age in healthy subjects and exhibited a similar age-related change trend as PWV.

SIGNIFICANCE

With the convenience of PPG measures, the proposed age-related features have the potential to be used as biomarkers for vascular aging and estimating the risk of cardiovascular disease.

Prospective observational study of 2 wearable strain sensors for measuring the respiratory rate

The respiratory rate is an important factor for assessing patient status and detecting changes in the severity of illness. Real-time determination of the respiratory rate will enable early responses to changes in the patient condition. Several methods of wearable devices have enabled remote respiratory rate monitoring. However, gaps persist in large-scale validation, patient-specific calibration, standardization and their usefulness in clinical practice has not been fully elucidated. The aim of this study was to evaluate the accuracy of 2 wearable stretch sensors, C-STRECH® which is used in clinical practice and a novel stretchable capacitor in measuring the respiratory rate. The respiratory rate of 20 healthy subjects was measured by a spirometer with the stretch sensor applied to 1 of 5 locations (umbilicus, lateral abdomen, epigastrium, lateral chest, or chest) of their body at rest while they were in a sitting or supine position before or after exercise. The sensors detected the largest amplitudes at the epigastrium and umbilicus compared to other sites of measurement for the sitting and supine positions, respectively. At rest, the respiratory rate of the sensors had an error of 0.06 to 2.39 breaths/minute, whereas after exercise, an error of 1.57 to 3.72 breaths/minute was observed compared to the spirometer. The sensors were able to detect the respiratory rate of healthy volunteers in the sitting and supine positions, but there was a need for improvement in detection after exercise.

A Novel Respiratory Rate Estimation Algorithm from Photoplethysmogram Using Deep Learning Model

Respiratory rate (RR) is a critical vital sign that can provide valuable insights into various medical conditions, including pneumonia. Unfortunately, manual RR counting is often unreliable and discontinuous. Current RR estimation algorithms either lack the necessary accuracy or demand extensive window sizes. In response to these challenges, this study introduces a novel method for continuously estimating RR from photoplethysmogram (PPG) with a reduced window size and lower processing requirements. To evaluate and compare classical and deep learning algorithms, this study leverages the BIDMC and CapnoBase datasets, employing the Respiratory Rate Estimation (RRest) toolbox. The optimal classical techniques combination on the BIDMC datasets achieves a mean absolute error (MAE) of 1.9 breaths/min. Additionally, the developed neural network model utilises convolutional and long short-term memory layers to estimate RR effectively. The best-performing model, with a 50% train-test split and a window size of 7 s, achieves an MAE of 2 breaths/min. Furthermore, compared to other deep learning algorithms with window sizes of 16, 32, and 64 s, this study's model demonstrates superior performance with a smaller window size. The study suggests that further research into more precise signal processing techniques may enhance RR estimation from PPG signals.

Diffuse transmittance visible spectroscopy using smartphone flashlight for photoplethysmography and vital signs measurements

Photoplethysmography (PPG), with its wide range of applications, has become one of the most promising modalities for healthcare monitoring technology. In this work, we present a new PPG measurement technique based on diffuse transmittance spectroscopy (DTS) with the help of a smartphone built-in flashlight as an alternative broadband light source. The blood Volume Pulse (BVP) signal was extracted from recorded transmittance spectra at 620 nm. The results were compared with the ground truth and conventional contact finger PPG sensors. A very high correlation was found between the diffuse transmittance signal and the reference PPG signals (r = 0.997, p < 0.0001). The accuracy and root mean square error (RMSE) were 99.23% and 0.8 bpm, respectively. In addition, a Bland-Altman analysis showed a good agreement between both techniques, with a very small bias between mean paired differences of heart rate observations. A simple forward model for diffuse transmittance spectra for different levels of blood oxygen saturation is developed and supported by experimental measurements. It was also found that blood oxygen saturation (SpO2) can be estimated with the aid of DTS based smartphone flash by tracking the wavelength corresponding to the oxygenation level in the visible range between orange and red regions of the visible spectrum particularly in the range between 610 and 635 nm for 26 healthy subjects. 624 nm on average seems to be the wavelength that corresponds with the normal blood oxygenation level. These findings show the potential of DTS PPG to reliably extract cardiac frequency and estimate SpO2 with adequate accuracy. The results also demonstrate the capability of smartphone flash as a miniature visible light source for recording multispectral PPG signals and quantifying vital signs in the transmission mode at the fingertip with acceptable signal quality over a wide range of wavelengths from 550 nm to 650 nm.

Face2PPG: An Unsupervised Pipeline for Blood Volume Pulse Extraction From Faces

Photoplethysmography (PPG) signals have become a key technology in many fields, such as medicine, well-being, or sports. Our work proposes a set of pipelines to extract remote PPG signals (rPPG) from the face robustly, reliably, and configurably. We identify and evaluate the possible choices in the critical steps of unsupervised rPPG methodologies. We assess a state-of-the-art processing pipeline in six different datasets, incorporating important corrections in the methodology that ensure reproducible and fair comparisons. In addition, we extend the pipeline by proposing three novel ideas; 1) a new method to stabilize the detected face based on a rigid mesh normalization; 2) a new method to dynamically select the different regions in the face that provide the best raw signals, and 3) a new RGB to rPPG transformation method, called Orthogonal Matrix Image Transformation (OMIT) based on QR decomposition, that increases robustness against compression artifacts. We show that all three changes introduce noticeable improvements in retrieving rPPG signals from faces, obtaining state-of-the-art results compared with unsupervised, non-learning-based methodologies and, in some databases, very close to supervised, learning-based methods. We perform a comparative study to quantify the contribution of each proposed idea. In addition, we depict a series of observations that could help in future implementations.

Experimental Verification of the Possibility of Reducing Photoplethysmography Measurement Time for Stress Index Calculation

Stress is a direct or indirect cause of reduced work efficiency in daily life. It can damage physical and mental health, leading to cardiovascular disease and depression. With increased interest and awareness of the risks of stress in modern society, there is a growing demand for quick assessment and monitoring of stress levels. Traditional ultra-short-term stress measurement classifies stress situations using heart rate variability (HRV) or pulse rate variability (PRV) information extracted from electrocardiogram (ECG) or photoplethysmography (PPG) signals. However, it requires more than one minute, making it difficult to monitor stress status in real-time and accurately predict stress levels. In this paper, stress indices were predicted using PRV indices acquired at different lengths of time (60 s, 50 s, 40 s, 30 s, 20 s, 10 s, and 5 s) for the purpose of real-time stress monitoring. Stress was predicted with Extra Tree Regressor, Random Forest Regressor, and Gradient Boost Regressor models using a valid PRV index for each data acquisition time. The predicted stress index was evaluated using an R2 score between the predicted stress index and the actual stress index calculated from one minute of the PPG signal. The average R2 score of the three models by the data acquisition time was 0.2194 at 5 s, 0.7600 at 10 s, 0.8846 at 20 s, 0.9263 at 30 s, 0.9501 at 40 s, 0.9733 at 50 s, and 0.9909 at 60 s. Thus, when stress was predicted using PPG data acquired for 10 s or more, the R2 score was confirmed to be over 0.7.

An ultralow power wearable vital sign sensor using an electromagnetically reactive near field

Despite coronavirus disease 2019, cardiovascular disease, the leading cause of global death, requires timely detection and treatment for a high survival rate, underscoring the 24 h monitoring of vital signs. Therefore, telehealth using wearable devices with vital sign sensors is not only a fundamental response against the pandemic but a solution to provide prompt healthcare for the patients in remote sites. Former technologies which measured a couple of vital signs had features that disturbed practical applications to wearable devices, such as heavy power consumption. Here, we suggest an ultralow power (100 μW) sensor that collects all cardiopulmonary vital signs, including blood pressure, heart rate, and the respiration signal. The small and lightweight (2 g) sensor designed to be easily embedded in the flexible wristband generates an electromagnetically reactive near field to monitor the contraction and relaxation of the radial artery. The proposed ultralow power sensor measuring noninvasively continuous and accurate cardiopulmonary vital signs at once will be one of the most promising sensors for wearable devices to bring telehealth to our lives.

Influence of Photoplethysmogram Signal Quality on Pulse Arrival Time during Polysomnography

Intervals of low-quality photoplethysmogram (PPG) signals might lead to significant inaccuracies in estimation of pulse arrival time (PAT) during polysomnography (PSG) studies. While PSG is considered to be a "gold standard" test for diagnosing obstructive sleep apnea (OSA), it also enables tracking apnea-related nocturnal blood pressure fluctuations correlated with PAT. Since the electrocardiogram (ECG) is recorded synchronously with the PPG during PSG, it makes sense to use the ECG signal for PPG signal-quality assessment. (1) Objective: to develop a PPG signal-quality assessment algorithm for robust PAT estimation, and investigate the influence of signal quality on PAT during various sleep stages and events such as OSA. (2) Approach: the proposed algorithm uses R and T waves from the ECG to determine approximate locations of PPG pulse onsets. The MESA database of 2055 PSG recordings was used for this study. (3) Results: the proportions of high-quality PPG were significantly lower in apnea-related oxygen desaturation (matched-pairs rc = 0.88 and rc = 0.97, compared to OSA and hypopnea, respectively, when p < 0.001) and arousal (rc = 0.93 and rc = 0.98, when p < 0.001) than in apnea events. The significantly large effect size of interquartile ranges of PAT distributions was between low- and high-quality PPG (p < 0.001, rc = 0.98), and regular and irregular pulse waves (p < 0.001, rc = 0.74), whereas a lower quality of the PPG signal was found to be associated with a higher interquartile range of PAT across all subjects. Suggested PPG signal quality-based PAT evaluation reduced deviations (e.g., rc = 0.97, rc = 0.97, rc = 0.99 in hypopnea, oxygen desaturation, and arousal stages, respectively, when p < 0.001) and allowed obtaining statistically larger differences between different sleep stages and events. (4) Significance: the implemented algorithm has the potential to increase the robustness of PAT estimation in PSG studies related to nocturnal blood pressure monitoring.

Machine Learning-Based Respiration Rate and Blood Oxygen Saturation Estimation Using Photoplethysmogram Signals

The continuous monitoring of respiratory rate (RR) and oxygen saturation (SpO2) is crucial for patients with cardiac, pulmonary, and surgical conditions. RR and SpO2 are used to assess the effectiveness of lung medications and ventilator support. In recent studies, the use of a photoplethysmogram (PPG) has been recommended for evaluating RR and SpO2. This research presents a novel method of estimating RR and SpO2 using machine learning models that incorporate PPG signal features. A number of established methods are used to extract meaningful features from PPG. A feature selection approach was used to reduce the computational complexity and the possibility of overfitting. There were 19 models trained for both RR and SpO2 separately, from which the most appropriate regression model was selected. The Gaussian process regression model outperformed all the other models for both RR and SpO2 estimation. The mean absolute error (MAE) for RR was 0.89, while the root-mean-squared error (RMSE) was 1.41. For SpO2, the model had an RMSE of 0.98 and an MAE of 0.57. The proposed system is a state-of-the-art approach for estimating RR and SpO2 reliably from PPG. If RR and SpO2 can be consistently and effectively derived from the PPG signal, patients can monitor their RR and SpO2 at a cheaper cost and with less hassle.

A Flexible Near-Field Biosensor for Multisite Arterial Blood Flow Detection

Modern wearable devices show promising results in terms of detecting vital bodily signs from the wrist. However, there remains a considerable need for a device that can conform to the human body's variable geometry to accurately detect those vital signs and to understand health better. Flexible radio frequency (RF) resonators are well poised to address this need by providing conformable bio-interfaces suitable for different anatomical locations. In this work, we develop a compact wearable RF biosensor that detects multisite hemodynamic events due to pulsatile blood flow through noninvasive tissue-electromagnetic (EM) field interaction. The sensor consists of a skin patch spiral resonator and a wearable transceiver. During resonance, the resonator establishes a strong capacitive coupling with layered dielectric tissues due to impedance matching. Therefore, any variation in the dielectric properties within the near-field of the coupled system will result in field perturbation. This perturbation also results in RF carrier modulation, transduced via a demodulator in the transceiver unit. The main elements of the transceiver consist of a direct digital synthesizer for RF carrier generation and a demodulator unit comprised of a resistive bridge coupled with an envelope detector, a filter, and an amplifier. In this work, we build and study the sensor at the radial artery, thorax, carotid artery, and supraorbital locations of a healthy human subject, which hold clinical significance in evaluating cardiovascular health. The carrier frequency is tuned at the resonance of the spiral resonator, which is 34.5 ± 1.5 MHz. The resulting transient waveforms from the demodulator indicate the presence of hemodynamic events, i.e., systolic upstroke, systolic peak, dicrotic notch, and diastolic downstroke. The preliminary results also confirm the sensor's ability to detect multisite blood flow events noninvasively on a single wearable platform.

An XGBoost-based model for assessment of aortic stiffness from wrist photoplethysmogram

BACKGROUND AND OBJECTIVE

Carotid-femoral pulse wave velocity (cf-PWV) is the gold standard for non-invasive assessment of aortic stiffness. Photoplethysmography used in wearable devices provides an indirect measurement method for cf-PWV. This study aimed to construct a cf-PWV prediction method based on the XGBoost algorithm and wrist photoplethysmogram (wPPG) for the early screening of arteriosclerosis in primary healthcare.

METHODS

Data from 210 subjects were used for modeling, and 100 subjects were used as an external validation set. The wPPG pulse waves were filtered by discrete wavelet transform, and various features were extracted from each waveform, including two original indexes. The extraction rate (ER) and Pearson P were calculated to evaluate the applicability of each feature for model training. The magnitude of cf-PWV was predicted by an XGBoost-based model using the selected features and basic physiological parameters (age, sex, height, weight and BMI). The level of aortic stiffness was classified by a 3-classification strategy according to the standard cf-PWV (measured by the Complior device). Bland-Altman plot, Pearson correlation analysis, and accuracy tested performance from two aspects: predicting the magnitude of cf-PWV and classifying the level of aortic stiffness.

RESULTS

In the external validation set (n = 100, age range 22-79), 97 subjects obtained features (ER = 97%). The predicted cf-PWV was significantly correlated with the standard cf-PWV (r = 0.927, P < 0.001). The accuracy (AC) of the 3-classification was 85.6%. The interrater agreement for assessing aortic stiffness was at least substantial (quadratically weighted Kappa = 0.833).

CONCLUSIONS

The multi-parameter fusion cf-PWV prediction method based on the XGBoost algorithm and wPPG pulse wave analysis proves the feasibility of atherosclerosis screening in wearable devices.

Lightweight End-to-End Deep Learning Solution for Estimating the Respiration Rate from Photoplethysmogram Signal

Respiratory ailments are a very serious health issue and can be life-threatening, especially for patients with COVID. Respiration rate (RR) is a very important vital health indicator for patients. Any abnormality in this metric indicates a deterioration in health. Hence, continuous monitoring of RR can act as an early indicator. Despite that, RR monitoring equipment is generally provided only to intensive care unit (ICU) patients. Recent studies have established the feasibility of using photoplethysmogram (PPG) signals to estimate RR. This paper proposes a deep-learning-based end-to-end solution for estimating RR directly from the PPG signal. The system was evaluated on two popular public datasets: VORTAL and BIDMC. A lightweight model, ConvMixer, outperformed all of the other deep neural networks. The model provided a root mean squared error (RMSE), mean absolute error (MAE), and correlation coefficient (R) of 1.75 breaths per minute (bpm), 1.27 bpm, and 0.92, respectively, for VORTAL, while these metrics were 1.20 bpm, 0.77 bpm, and 0.92, respectively, for BIDMC. The authors also showed how fine-tuning a small subset could increase the performance of the model in the case of an out-of-distribution dataset. In the fine-tuning experiments, the models produced an average R of 0.81. Hence, this lightweight model can be deployed to mobile devices for real-time monitoring of patients.

Quality Assessment and Morphological Analysis of Photoplethysmography in Daily Life

The photoplethysmographic (PPG) signal has been applied in various research fields, with promising results for its future clinical application. However, there are several sources of variability that, if not adequately controlled, can hamper its application in pervasive monitoring contexts. This study assessed and characterized the impact of several sources of variability, such as physical activity, age, sex, and health state on PPG signal quality and PPG waveform parameters (Rise Time, Pulse Amplitude, Pulse Time, Reflection Index, Delta T, and DiastolicAmplitude). We analyzed 31 24 h recordings by as many participants (19 healthy subjects and 12 oncological patients) with a wristband wearable device, selecting a set of PPG pulses labeled with three different quality levels. We implemented a Multinomial Logistic Regression (MLR) model to evaluate the impact of the aforementioned factors on PPG signal quality. We then extracted six parameters only on higher-quality PPG pulses and evaluated the influence of physical activity, age, sex, and health state on these parameters with Generalized Linear Mixed Effects Models (GLMM). We found that physical activity has a detrimental effect on PPG signal quality quality (94% of pulses with good quality when the subject is at rest vs. 9% during intense activity), and that health state affects the percentage of available PPG pulses of the best quality (at rest, 44% for healthy subjects vs. 13% for oncological patients). Most of the extracted parameters are influenced by physical activity and health state, while age significantly impacts two parameters related to arterial stiffness. These results can help expand the awareness that accurate, reliable information extracted from PPG signals can be reached by tackling and modeling different sources of inaccuracy.

Design of a Realtime Photoplethysmogram Signal Quality Checker for Wearables and Edge Computing

Photoplethysmogram (PPG) signal is extensively used for deducing health parameters of patients in order to infer about physiological conditions of heart, blood pressure, respiratory patterns, and so on. Such analysis and estimations can be done accurately only on high quality PPG signals with very minimal artifacts. PPG signals collected from fitness grade and smart phone scenarios are prone to muscle artifacts and hence there is a need to assess the signal quality before using the signal. Although there are approaches available in the realm of machine learning and deep learning, they are computationally expensive and may not be suitable for a wearable or edge computing scenario. In this paper, we propose the design of a quality checker to check the quality of the signal that can be directly implemented on edge devices like smartwatch. The algorithm is tested on PPG data collected from wearable, ICU and medical grade devices. In the wearable scenario where the noise levels are very high, our algorithm has performed significantly better with a F_score of over 0.92. Further we show that by applying the proposed quality checker, the accuracy of the computed heart rate from a smart phone PPG-application significantly improves.

The Hemodynamic Parameters Values Prediction on the Non-Invasive Hydrocuff Technology Basis with a Neural Network Applying

The task to develop a mechanism for predicting the hemodynamic parameters values based on non-invasive hydrocuff technology of a pulse wave signal fixation is described in this study. The advantages and disadvantages of existing methods of recording the ripple curve are noted in the published materials. This study proposes a new hydrocuff method for hemodynamic parameters and blood pressure values measuring. A block diagram of the device being developed is presented. Algorithms for processing the pulse wave contour are presented. A neural network applying necessity for the multiparametric feature space formation is substantiated. The pulse wave contours obtained using hydrocuff technology of oscillation formation for various age groups are presented. According to preliminary estimates, by the moment of the dicrotic surge formation, it is possible to judge the ratio of the heart and blood vessels work, which makes it possible to form an expanded feature space of significant parameters based on neural network classifiers. This study presents the characteristics accounted for creating a database for training a neural network.

Breathing Rate Estimation from Head-Worn Photoplethysmography Sensor Data Using Machine Learning

Breathing rate is considered one of the fundamental vital signs and a highly informative indicator of physiological state. Given that the monitoring of heart activity is less complex than the monitoring of breathing, a variety of algorithms have been developed to estimate breathing activity from heart activity. However, estimating breathing rate from heart activity outside of laboratory conditions is still a challenge. The challenge is even greater when new wearable devices with novel sensor placements are being used. In this paper, we present a novel algorithm for breathing rate estimation from photoplethysmography (PPG) data acquired from a head-worn virtual reality mask equipped with a PPG sensor placed on the forehead of a subject. The algorithm is based on advanced signal processing and machine learning techniques and includes a novel quality assessment and motion artifacts removal procedure. The proposed algorithm is evaluated and compared to existing approaches from the related work using two separate datasets that contains data from a total of 37 subjects overall. Numerous experiments show that the proposed algorithm outperforms the compared algorithms, achieving a mean absolute error of 1.38 breaths per minute and a Pearson's correlation coefficient of 0.86. These results indicate that reliable estimation of breathing rate is possible based on PPG data acquired from a head-worn device.

Cuffless Blood Pressure Measurement Using Linear and Nonlinear Optimized Feature Selection

The cuffless blood pressure (BP) measurement allows for frequent measurement without discomfort to the patient compared to the cuff inflation measurement. With the availability of a large dataset containing physiological waveforms, now it is possible to use them through different learning algorithms to produce a relationship with changes in BP. In this paper, a novel cuffless noninvasive blood pressure measurement technique has been proposed using optimized features from electrocardiogram and photoplethysmography based on multivariate symmetric uncertainty (MSU). The technique is an improvement over other contemporary methods due to the inclusion of feature optimization depending on both linear and nonlinear relationships with the change of blood pressure. MSU has been used as a selection criterion with algorithms such as the fast correlation and ReliefF algorithms followed by the penalty-based regression technique to make sure the features have maximum relevance as well as minimum redundancy. The result from the technique was compared with the performance of similar techniques using the MIMIC-II dataset. After training and testing, the root mean square error (RMSE) comes as 5.28 mmHg for systolic BP and 5.98 mmHg for diastolic BP. In addition, in terms of mean absolute error, the result improved to 4.27 mmHg for SBP and 5.01 for DBP compared to recent cuffless BP measurement techniques which have used substantially large datasets and feature optimization. According to the British Hypertension Society Standard (BHS), our proposed technique achieved at least grade B in all cumulative criteria for cuffless BP measurement.

Pulse Oximetry: The Working Principle, Signal Formation, and Applications

Pulse oximeters are routinely used in various medical-grade and consumer-grade applications. They can be used to estimate, for example, blood oxygen saturation, autonomic nervous system activity and cardiac function, blood pressure, sleep quality, and recovery through the recording of photoplethysmography signal. Medical-grade devices often record red and infra-red light-based photoplethysmography signals while smartwatches and other consumer-grade devices usually rely on a green light. At its simplest, a pulse oximeter can consist of one or two photodiodes and a photodetector attached, for example, a fingertip or earlobe. These sensors are used to record light absorption in a medium as a function of time. This time-varying absorption information is used to form a photoplethysmography signal. In this chapter, we discuss the working principles of pulse oximeters and the formation of the photoplethysmography signal. We will further discuss the advantages and disadvantages of pulse oximeters, which kind of applications exist in the medical field, and how pulse oximeters are utilized in daily health monitoring.

Performance of Automated Point-of-Care Respiratory Rate Counting versus Manual Counting in Children under Five Admitted with Severe Febrile Illness to Kisantu Hospital, DR Congo

To improve the early recognition of danger signs in children with severe febrile illness in low resource settings, WHO promotes automated respiratory rate (RR) counting, but its performance is unknown in this population. Therefore, we prospectively evaluated the field performance of automated point-of-care plethysmography-based RR counting in hospitalized children with severe febrile illness (<5 years) in DR Congo. A trained research nurse simultaneously counted the RR manually (comparative method) and automatically with the Masimo Rad G pulse oximeter. Valid paired RR measurements were obtained in 202 (83.1%) children, among whom 43.1% (87/202) had fast breathing according to WHO criteria based on manual counting. Automated counting frequently underestimated the RR (median difference of -1 breath/minute; p2.5-p97.5 limits of agreement: -34-6), particularly at higher RR. This resulted in a failure to detect fast breathing in 24.1% (21/87) of fast breathing children (positive percent agreement: 75.9%), which was not explained by clinical characteristics (p > 0.05). Children without fast breathing were mostly correctly classified (negative percent agreement: 98.3%). In conclusion, in the present setting the automated RR counter performed insufficiently to facilitate the early recognition of danger signs in children with severe febrile illness, given wide limits of agreement and a too low positive percent agreement.

Pulse Rate Variability Analysis Using Remote Photoplethysmography Signals

Pulse rate variability (PRV) refers to the change in the interval between pulses in the blood volume pulse (BVP) signal acquired using photoplethysmography (PPG). PRV is an indicator of the health status of an individual’s autonomic nervous system. A representative method for measuring BVP is contact PPG (CPPG). CPPG may cause discomfort to a user, because the sensor is attached to the finger for measurements. In contrast, noncontact remote PPG (RPPG) extracts BVP signals from face data using a camera without the need for a sensor. However, because the existing RPPG is a technology that extracts a single pulse rate rather than a continuous BVP signal, it is difficult to extract additional health status indicators. Therefore, in this study, PRV analysis is performed using lab-based RPPG technology that can yield continuous BVP signals. In addition, we intended to confirm that the analysis of PRV via RPPG can be performed with the same quality as analysis via CPPG. The experimental results confirmed that the temporal and frequency parameters of PRV extracted from RPPG and CPPG were similar. In terms of correlation, the PRVs of RPPG and CPPG yielded correlation coefficients between 0.98 and 1.0.

Breathing rate estimation based on multiple linear regression

The breathing rate is a key clinical parameter that can now be estimated using photoplethysmographic methods. Here, we present an indirect method of breathing rate estimation that does not require bulky and uncomfortable sensors. Breathing modulates a pulsed wave; we extracted the maximum and minimum values, and first-order derivatives thereof, to measure breathing amplitude, frequency, and baseline drift. Demodulation was used to obtain multiple breathing waveforms, from which peak values are extracted to obtain breathing rates. Multiple linear regression was used to combine the breathing rates of different feature points. We used a breathing dataset for 53 subjects, and divided the data into training and test sets when calculating the regression coefficients. We also assessed the generalizability of our linear model. We found that breathing rate estimation was more accurate when using a multivariate signal method with multiple versus a single feature point. The mean absolute error, mean error, and standard deviation of the error were 1.28, -0.07, and 1.60 breaths per minute, respectively.

Filtering-induced time shifts in photoplethysmography pulse features measured at different body sites: the importance of filter definition and standardization

Objective.The waveform of a photoplethysmography (PPG) signal depends on the measurement site and individual physiological conditions. Filtering can distort the morphology of the original PPG signal waveform and change the timing of pulse feature points on PPG signals. We aim to quantitatively investigate the effect of PPG signal morphology (related to measurement site) and type of pulse feature on the filtering-induced time shift (TS).Approach.60 s PPG signals were measured from six body sites (finger, wrist under (volar), wrist upper (dorsal), earlobe, and forehead) of 36 healthy adults. Using infinite impulse response digital filters which are common in PPG signal processing, PPG signals were prefiltered (band-pass, pass and stop bands: >0.5 Hz and <0.2 Hz for high-pass filter, <20 Hz and >30 Hz for low-pass filter) and then filtered (low-pass, pass and stop bands: <3 Hz and >5 Hz). Four pulse feature points were defined and extracted (peak, valley, maximal first derivative, and maximal second derivative). For each subject, overall TS and intra-subject TS variability in feature points were calculated as the mean and standard deviation of TS between prefiltered and filtered PPG signals in 50 cardiac cycles. Statistical testing was performed to investigate the effect of measurement site and type of pulse feature on overall TS and intra-subject TS variability.Main results.Measurement site, type of pulse feature, and their interaction had significant impacts on the overall TS and intra-subject TS variability (p < 0.001 for all). Valley and maximal second derivative showed higher overall TS than peak and maximal first derivative. Finger had higher overall TS and lower intra-subject TS variability than other measurement sites.Significance. Measurement site and type of pulse feature can significantly influence the timing of feature points on filtered PPG signals. Filtering parameters should be quoted to support the reproducibility of PPG-related studies.

Efficient embedded sleep wake classification for open-source actigraphy

This study presents a thorough analysis of sleep/wake detection algorithms for efficient on-device sleep tracking using wearable accelerometric devices. It develops a novel end-to-end algorithm using convolutional neural network applied to raw accelerometric signals recorded by an open-source wrist-worn actigraph. The aim of the study is to develop an automatic classifier that: (1) is highly generalizable to heterogenous subjects, (2) would not require manual features' extraction, (3) is computationally lightweight, embeddable on a sleep tracking device, and (4) is suitable for a wide assortment of actigraphs. Hereby, authors analyze sleep parameters, such as total sleep time, waking after sleep onset and sleep efficiency, by comparing the outcomes of the proposed algorithm to the gold standard polysomnographic concurrent recordings. The relatively substantial agreement (Cohen's kappa coefficient, median, equal to 0.78 ± 0.07) and the low-computational cost (2727 floating-point operations) make this solution suitable for an on-board sleep-detection approach.

Derivation of Respiratory Metrics in Health and Asthma

The ability to continuously monitor breathing metrics may have indications for general health as well as respiratory conditions such as asthma. However, few studies have focused on breathing due to a lack of available wearable technologies. To examine the performance of two machine learning algorithms in extracting breathing metrics from a finger-based pulse oximeter, which is amenable to long-term monitoring. Methods: Pulse oximetry data were collected from 11 healthy and 11 with asthma subjects who breathed at a range of controlled respiratory rates. U-shaped network (U-Net) and Long Short-Term Memory (LSTM) algorithms were applied to the data, and results compared against breathing metrics derived from respiratory inductance plethysmography measured simultaneously as a reference. Results: The LSTM vs. U-Net model provided breathing metrics which were strongly correlated with those from the reference signal (all p < 0.001, except for inspiratory: expiratory ratio). The following absolute mean bias (95% confidence interval) values were observed (in seconds): inspiration time 0.01(−2.31, 2.34) vs. −0.02(−2.19, 2.16), expiration time −0.19(−2.35, 1.98) vs. −0.24(−2.36, 1.89), and inter-breath intervals −0.19(−2.73, 2.35) vs. −0.25(2.76, 2.26). The inspiratory:expiratory ratios were −0.14(−1.43, 1.16) vs. −0.14(−1.42, 1.13). Respiratory rate (breaths per minute) values were 0.22(−2.51, 2.96) vs. 0.29(−2.54, 3.11). While percentage bias was low, the 95% limits of agreement was high (~35% for respiratory rate). Conclusion: Both machine learning models show strong correlation and good comparability with reference, with low bias though wide variability for deriving breathing metrics in asthma and health cohorts. Future efforts should focus on improvement of performance of these models, e.g., by increasing the size of the training dataset at the lower breathing rates.

Reconstruction of the respiratory signal through ECG and wrist accelerometer data

Respiratory rate and changes in respiratory activity provide important markers of health and fitness. Assessing the breathing signal without direct respiratory sensors can be very helpful in large cohort studies and for screening purposes. In this paper, we demonstrate that long-term nocturnal acceleration measurements from the wrist yield significantly better respiration proxies than four standard approaches of ECG (electrocardiogram) derived respiration. We validate our approach by comparison with flow-derived respiration as standard reference signal, studying the full-night data of 223 subjects in a clinical sleep laboratory. Specifically, we find that phase synchronization indices between respiration proxies and the flow signal are large for five suggested acceleration-derived proxies with [Formula: see text] for males and [Formula: see text] for females (means ± standard deviations), while ECG-derived proxies yield only [Formula: see text] for males and [Formula: see text] for females. Similarly, respiratory rates can be determined more precisely by wrist-worn acceleration devices compared with a derivation from the ECG. As limitation we must mention that acceleration-derived respiration proxies are only available during episodes of non-physical activity (especially during sleep).

Wearable monitoring of sleep-disordered breathing: estimation of the apnea-hypopnea index using wrist-worn reflective photoplethysmography

A large part of the worldwide population suffers from obstructive sleep apnea (OSA), a disorder impairing the restorative function of sleep and constituting a risk factor for several cardiovascular pathologies. The standard diagnostic metric to define OSA is the apnea-hypopnea index (AHI), typically obtained by manually annotating polysomnographic recordings. However, this clinical procedure cannot be employed for screening and for long-term monitoring of OSA due to its obtrusiveness and cost. Here, we propose an automatic unobtrusive AHI estimation method fully based on wrist-worn reflective photoplethysmography (rPPG), employing a deep learning model exploiting cardiorespiratory and sleep information extracted from the rPPG signal trained with 250 recordings. We tested our method with an independent set of 188 heterogeneously disordered clinical recordings and we found it estimates the AHI with a good agreement to the gold standard polysomnography reference (correlation = 0.61, estimation error = 3±10 events/h). The estimated AHI was shown to reliably assess OSA severity (weighted Cohen's kappa = 0.51) and screen for OSA (ROC-AUC = 0.84/0.86/0.85 for mild/moderate/severe OSA). These findings suggest that wrist-worn rPPG measurements that can be implemented in wearables such as smartwatches, have the potential to complement standard OSA diagnostic techniques by allowing unobtrusive sleep and respiratory monitoring.

Influences of Sensor Placement Site and Subject Posture on Measurement of Respiratory Frequency Using Triaxial Accelerometers

Introduction

Respiration frequency (RF) could be derived from the respiratory signals recorded by accelerometers which detect chest wall movements. The optimum direction of acceleration for accurate RF measurement is still uncertain. We aim to investigate the effect of measure site, posture, and direction of acceleration on the accuracy of accelerometer-based RF estimation.

Methods

In supine and seated postures respectively, respiratory signals were measured from 34 healthy subjects in 70 s by triaxial accelerometers located at four sites on the body wall (over the clavicle, laterally on the chest wall, over the pectoral part of the anterior chest wall, on the abdomen in the midline at the umbilicus), with the reference respiratory signal simultaneously recorded by a strain gauge chest belt. RFs were extracted from the accelerometer and reference respiratory signals using wavelet transformation. To investigate the effect of measure site, posture, and direction of acceleration on the accuracy of accelerometer-based RF estimation, repeated measures multivariate analysis of variance, linear regression, Bland-Altman analysis, and Scheirer-Ray-Hare test were performed between reference and accelerometer-based RFs.

Results

There was no significant difference in accelerometer-based RF estimation between seated and supine postures, among four accelerometer sites, or between seated or supine postures (p > 0.05 for all). The error of accelerometer-based RF estimation was less than 0.03 Hz (two breaths per minute) at any site or posture, but was significantly smaller in supine posture than in seated posture (p < 0.05), with narrower limits of agreement in Bland-Altman analysis and higher accuracy in linear regression (R² > 0.61 vs. R² < 0.51).

Conclusion

Respiration frequency can be accurately measured from the acceleration of any direction using triaxial accelerometers placed at the clavicular, pectoral and lateral sites on the chest as well the mid abdominal site. More accurate RF estimation could be achieved in supine posture compared with seated posture.

Respiratory activity extracted from wrist-worn reflective photoplethysmography in a sleep-disordered population

OBJECTIVE

Respiratory activity is an essential parameter to monitor healthy and disordered sleep, and unobtrusive measurement methods have important clinical applications in diagnostics of sleep-related breathing disorders. We propose a respiratory activity surrogate extracted from wrist-worn reflective photoplethysmography validated on a heterogeneous dataset of 389 sleep recordings.

APPROACH

The surrogate was extracted by interpolating the amplitude of the PPG pulses after evaluation of pulse morphological quality. Subsequent multistep post-processing was applied to remove parts of the surrogate with low quality and high motion levels. In addition to standard respiration rate performance, we evaluated the similarity between surrogate respiratory activity and reference inductance plethysmography of the thorax, using Spearman's correlations and spectral coherence, and assessed the influence of PPG signal quality, motion levels, sleep stages and obstructive sleep apnea.

MAIN RESULTS

Prior to post-processing, the surrogate already had a strong similarity with the reference (correlation = 0.54, coherence = 0.81), and reached respiration rate estimation performance in line with the literature (estimation error = 0.76± 2.11 breaths/min). Detrimental effects of low PPG quality, high motion levels and sleep-dependent physiological phenomena were significantly mitigated by the proposed post-processing steps (correlation = 0.62, coherence = 0.88, estimation error = 0.53± 1.85 breaths/min).

SIGNIFICANCE

Wrist-worn PPG can be used to extract respiratory activity, thus allowing respiration monitoring in real-world sleep medicine applications using (consumer) wearable devices.