PPG Pulse Research Articles

Assessing hemodynamics from the photoplethysmogram to gain insights into vascular age: a review from VascAgeNet.

The photoplethysmogram (PPG) signal is widely measured by clinical and consumer devices, and it is emerging as a potential tool for assessing vascular age. The shape and timing of the PPG pulse wave are both influenced by normal vascular aging, changes in arterial stiffness and blood pressure, and atherosclerosis. This review summarizes research into assessing vascular age from the PPG. Three categories of approaches are described: 1) those which use a single PPG signal (based on pulse wave analysis), 2) those which use multiple PPG signals (such as pulse transit time measurement), and 3) those which use PPG and other signals (such as pulse arrival time measurement). Evidence is then presented on the performance, repeatability and reproducibility, and clinical utility of PPG-derived parameters of vascular age. Finally, the review outlines key directions for future research to realize the full potential of photoplethysmography for assessing vascular age.

Age-Related Changes in the Characteristics of the Elderly Females Using the Signal Features of an Earlobe Photoplethysmogram.

Non-invasive measurement of physiological parameters and indicators, specifically among the elderly, is of utmost importance for personal health monitoring. In this study, we focused on photoplethysmography (PPG), and developed a regression model that calculates variables from the second (SDPPG) and third (TDPPG) derivatives of the PPG pulse that can observe the inflection point of the pulse wave measured by a wearable PPG device. The PPG pulse at the earlobe was measured for 3 min in 84 elderly Korean women (age: 71.19 ± 6.97 years old). Based on the PPG-based cardiovascular function, we derived additional variables from TDPPG, in addition to the aging variable to predict the age. The Aging Index (AI) from SDPPG and Sum of TDPPG variables were calculated in the second and third differential forms of PPG. The variables that significantly correlated with age were c/a, Tac, AI of SDPPG, sum of TDPPG, and correlation coefficient ‘r’ of the model. In multiple linear regression analysis, the r value of the model was 0.308, and that using deep learning on the model was 0.839. Moreover, the possibility of improving the accuracy of the model using supervised deep learning techniques, rather than the addition of datasets, was confirmed.

Reflection-type photoplethysmography pulse sensor based on an integrated optoelectronic chip with a ring structure.

Reflection-type photoplethysmography (PPG) pulse sensors are widely used in consumer markets to measure cardiovascular signals. Different from off-chip package solutions in which the light-emitting diode (LED) and photodetector (PD) are in separate chips, a GaN integrated optoelectronic chip with a novel ring structure is proposed to realize a PPG pulse sensor. The integrated optoelectronic chip consists of two multiple-quantum well (MQW) diodes. For higher sensitivities, the central and peripheral MQW diodes are suitable as the LED and PD, respectively. The results indicate that the integrated optoelectronic chip based on a blue LED epitaxial wafer is more suitable for the integrated PPG sensor based on device performance. Moreover, the amplitude of the PPG pulse signal collected from fingertips is higher than that from a wrist. The feasibility of the reflection-type PPG pulse sensor based on a GaN integrated optoelectronic chip is fully verified with the advantages of smaller sizes and lower costs.

Physiological noise modeling in fMRI based on the pulsatile component of photoplethysmograph

The blood oxygenation level-dependent (BOLD) contrast mechanism allows the noninvasive monitoring of changes in deoxyhemoglobin content. As such, it is commonly used in functional magnetic resonance imaging (fMRI) to study brain activity since levels of deoxyhemoglobin are indirectly related to local neuronal activity through neurovascular coupling mechanisms. However, the BOLD signal is severely affected by physiological processes as well as motion. Due to this, several noise correction techniques have been developed to correct for the associated confounds. The present study focuses on cardiac pulsatility fMRI confounds, aiming to refine model-based techniques that utilize the photoplethysmograph (PPG) signal. Specifically, we propose a new technique based on convolution filtering, termed cardiac pulsatility model (CPM) and compare its performance with the cardiac-related RETROICOR (Card-RETROICOR), which is a technique commonly used to model fMRI fluctuations due to cardiac pulsatility. Further, we investigate whether variations in the amplitude of the PPG pulses (PPG-Amp) covary with variations in amplitude of pulse-related fMRI fluctuations, as well as with the systemic low frequency oscillations (SLFOs) component of the fMRI global signal (GS – defined as the mean signal across all gray matter voxels). Capitalizing on 3T fMRI data from the Human Connectome Project, CPM was found to explain a significantly larger fraction of the fMRI signal variance compared to Card-RETROICOR, particularly for subjects with larger heart rate variability during the scan. The amplitude of the fMRI pulse-related fluctuations did not covary with PPG-Amp; however, PPG-Amp explained significant variance in the GS that was not attributed to variations in heart rate or breathing patterns. Our results suggest that the proposed approach can model high-frequency fluctuations due to pulsation as well as low-frequency physiological fluctuations more accurately compared to model-based techniques commonly employed in fMRI studies.

Coherence between Decomposed Components of Wrist and Finger PPG Signals by Imputing Missing Features and Resolving Ambiguous Features.

: Feature extraction from photoplethysmography (PPG) signals is an essential step to analyze vascular and hemodynamic information. Different morphologies of PPG waveforms from different measurement sites appear. Various phenomena of missing or ambiguous features exist, which limit subsequent signal processing. : The reasons that cause missing or ambiguous features of finger and wrist PPG pulses are analyzed based on the concept of component waves from pulse decomposition. Then, a systematic approach for missing-feature imputation and ambiguous-feature resolution is proposed. : From the experimental results, with the imputation and ambiguity resolution technique, features from 35,036 (98.7%) of 35,502 finger PPG cycles and 36307 (99.1%) of 36,652 wrist PPG cycles can be successfully identified. The extracted features became more stable and the standard deviations of their distributions were reduced. Furthermore, significant correlations up to 0.92 were shown between the finger and wrist PPG waveforms regarding the positions and widths of the third to fifth component waves. : The proposed missing-feature imputation and ambiguous-feature resolution solve the problems encountered during PPG feature extraction and expand the feature availability for further processing. More intrinsic properties of finger and wrist PPG are revealed. The coherence between the finger and wrist PPG waveforms enhances the applicability of the wrist PPG.

Blood Pressure Estimation Using Custom Photoplethysmography Sensors Located on Radial Artery at Wrist

Introduction Cardiovascular diseases (CVD), diabetes, and chronic kidney disease are among the most society concerns with a high correlation to blood pressure (BP) factor. As a result, developing a wearable device with a BP monitoring function is highly demanded health caring and monitoring. In order to measure BP, traditional methods are based on a sphygmomanometer as a gold standard, but it is not suitable for wearable applications. A solution, therefore, employed some sensors placed along artery paths of a human body and estimated BP from time transfer delay or Pulse Transit Time (PTT) of blood volume through these paths [1]. In practice, it is comfortable if all sensors are located centrally in a specific region and the wrist hand is considered the most convenient. For detecting the pulse wave of blood flow, photoplethysmography (PPG) is the king reigning the wearable device market for healthcare because of its small form factor, none-electrode-contact requirement, and multi-wavelength applications in extracting health indexes such as heart rate, SPO2, Glucose, Hydration levels, etc. Hence, a custom PPG sensor aiming to estimate BP in this paper is designed to optimize signal strength collecting and then applied to measure PTT, Reflective PTT (R-PTT) on the radial artery at three wrist’s location as Fig. 1. Method First, a three-sensor array with four LEDs at different wavelengths (525nm, 630nm, 850nm, and 940nm) is designed. The distances between LEDs and a single photodetector (PD) are considered to find the optimized places to detect blood pulse and the intensity of light by controlling the electric current on LEDs. The PD is a broadband sensitivity sensor permitting it absorbs all reflecting lights from LEDs on blood flow.Next, because light penetrates the skin depends on wavelength and intensity, we inherited the research work by Paul C.-P. Chao et al. [2] to select the optimal distances for placing LEDs. Next, a wearable device utilizing an ultra-low-energy analog-front-end, high-resolution 24bit-ADC, and small form factor is designed for collecting PPG data. After that, three well-known locations on a radial artery in Traditional Chinese Medicine at wrist, namely Cun, Guan, and Chi are considered to measure PTT for inter-sites and reflective PTT (R-PTT) for each site and compare each other’s to evaluate how different in each method, which one is better for estimating BP. The position of these points and the depth of the radial artery had been widely studied in [3]. Finally, BP estimation based on R-PTT with a validation using a 24-hour ambulatory BP meter namely Oscar 2TM from SunTech Medical® permits us to extract heart rate, systolic BP and diastolic BP. Five healthy subjects with an average age of 30 ± 6, height 170 ± 8 cm are recruited for seven days (9am-9pm) experiments. Results and Conclusions From our experiment, we discover the in-phase and invert-phase effect which affect the ratio AC/DC for each wavelength. In invert-phase status, the longer wavelength gives the better AC/DC ratio while this rule will change in in-phase condition. In other words, depending on the locations and status of the PPG pulse, the AC/DC ratio of these signals have a different outcome. Next, for measuring PTT between each location pair Cun-Guan, Chi-Guan and Cun-Chi are ambiguous by phase effect and resolution of data sampling while R-PTT takes advantage because of using just a single site. The correlation values of the R-PTT to SBP and DBP are r = 0.8 and 0.65 respectively.

Cuffless Blood Pressure Measurement Using a Smartphone-Case Based ECG Monitor with Photoplethysmography in Hypertensive Patients.

The availability of simple, accurate, and affordable cuffless blood pressure (BP) devices has the potential to greatly increase the compliance with measurement recommendations and the utilization of BP measurements for BP telemonitoring. The aim of this study is to evaluate the correlation between findings from routine BP measurements using a conventional sphygmomanometer with the results from a portable ECG monitor combined with photoplethysmography (PPG) for pulse wave registration in patients with arterial hypertension. Methods: The study included 500 patients aged 32–88 years (mean 64 ± 7.9 years). Mean values from three routine BP measurements by a sphygmomanometer with cuff were selected for comparison; within one minute after the last measurement, an electrocardiogram (ECG) was recorded for 3 min in the standard lead I using a smartphone-case based single-channel ECG monitor (CardioQVARK®-limited responsibility company “L-CARD”, Moscow, Russia) simultaneously with a PPG pulse wave recording. Using a combination of the heart signal with the PPG, levels of systolic and diastolic BP were determined based on machine learning using a previously developed and validated algorithm and were compared with sphygmomanometer results. Results: According to the Bland–Altman analysis, SD for systolic BP was 3.63, and bias was 0.32 for systolic BP. SD was 2.95 and bias was 0.61 for diastolic BP. The correlation between the results from the sphygmomanometer and the cuffless method was 0.89 (p = 0.001) for systolic and 0.87 (p = 0.002) for diastolic BP. Conclusion: Blood pressure measurements on a smartphone-case without a cuff are encouraging. However, further research is needed to improve the accuracy and reliability of clinical use in the majority of patients.

CHANGES IN GAUSSIAN MODELING PARAMETERS OF PPG PULSE DURING HEALTHY PREGNANCY

We used Gaussian modeling to depict the changes in finger photoplethysmographic (PPG) pulse during pregnancy in healthy women. We enrolled 70 healthy pregnant women and recorded their PPG pulses in 11–13 gestational weeks, 20–22 gestational weeks, and 37–39 gestational weeks. Three independent positive Gaussian functions were utilized to decompose the pulses, and each Gaussian function extracted three key parameters: the peak amplitude ([Formula: see text]), the peak position ([Formula: see text]), and the half-width ([Formula: see text]). The method of ANOVA and post-hoc multiple comparisons of mathematical statistics were utilized to study the differences of these parameters between the three trimesters. We found that in the first trimester [Formula: see text] increased significantly ([Formula: see text]: [Formula: see text] versus [Formula: see text], [Formula: see text]). [Formula: see text] and [Formula: see text] increased in the first trimester ([Formula: see text]: [Formula: see text] versus [Formula: see text], [Formula: see text]; [Formula: see text]: [Formula: see text] versus [Formula: see text], [Formula: see text]), then decreased significantly ([Formula: see text]: [Formula: see text] versus [Formula: see text], [Formula: see text]: [Formula: see text] versus [Formula: see text], [Formula: see text]). [Formula: see text] is associated with cardiac output, and [Formula: see text] and [Formula: see text] are associated with peripheral vascular resistance. The results of this study were consistent with the conclusion that healthy pregnant women exhibited high flow state of the cardiovascular system and their peripheral vascular resistance decreased first and then gradually recovered during pregnancy. This study indicated that PPG pulse could also reflect the changes in the maternal cardiovascular system during pregnancy.

A device employing a neural network for blood pressure estimation from the oscillatory pressure pulse wave and PPG signal

Purpose Wrist-cuff oscillometric blood pressure monitors are very popular in the portable medical device market. However, its accuracy has always been controversial. In addition to the oscillatory pressure pulse wave, the finger photoplethysmography (PPG) can provide information on blood pressure changes. A blood pressure measurement system integrating the information of pressure pulse wave and the finger PPG may improve measurement accuracy. Additionally, a neural network can synthesize the information of different types of signals and approximate the complex nonlinear relationship between inputs and outputs. The purpose of this study is to verify the hypothesis that a wrist-cuff device using a neural network for blood pressure estimation from both the oscillatory pressure pulse wave and PPG signal may improve the accuracy. Design/methodology/approach A PPG sensor was integrated into a wrist blood pressure monitor, so the finger PPG and the oscillatory pressure wave could be detected at the same time during the measurement. After the peak detection, curves were fitted to the data of pressure pulse amplitude and PPG pulse amplitude versus time. A genetic algorithm-back propagation neural network was constructed. Parameters of the curves were inputted into the neural network, the outputs of which were the measurement values of blood pressure. Blood pressure measurements of 145 subjects were obtained using a mercury sphygmomanometer, the developed device with the neural network algorithm and an Omron HEM-6111 blood pressure monitor for comparison. Findings For the systolic blood pressure (SBP), the difference between the proposed device and the mercury sphygmomanometer is 0.0062 ± 2.55 mmHg (mean ± SD) and the difference between the Omron device and the mercury sphygmomanometer is 1.13 ± 9.48 mmHg. The difference in diastolic blood pressure between the mercury sphygmomanometer and the proposed device was 0.28 ± 2.99 mmHg. The difference in diastolic blood pressure between the mercury sphygmomanometer and Omron HEM-6111 was −3.37 ± 7.53 mmHg. Originality/value Although the difference in the SBP error between the proposed device and Omron HEM-6111 was not remarkable, there was a significant difference between the proposed device and Omron HEM-6111 in the diastolic blood pressure error. The developed device showed an improved performance. This study was an attempt to enhance the accuracy of wrist-cuff oscillometric blood pressure monitors by using the finger PPG and the neural network. The hardware framework constructed in this study can improve the conventional wrist oscillometric sphygmomanometer and may be used for continuous measurement of blood pressure.

Advancing PPG Signal Quality and Know-How Through Knowledge Translation-From Experts to Student and Researcher.

Objective: Despite the vast number of photoplethysmography (PPG) research publications and growing demands for such sensing in Digital and Wearable Health platforms, there appears little published on signal quality expectations for morphological pulse analysis. Aim: to determine a consensus regarding the minimum number of undistorted i.e., diagnostic quality pulses required, as well as a threshold proportion of noisy beats for recording rejection.Approach: Questionnaire distributed to international fellow researchers in skin contact PPG measurements on signal quality expectations and associated factors concerning recording length, expected artifact-free pulses (“diagnostic quality”) in a trace, proportion of trace having artifact to justify excluding/repeating measurements, minimum beats required, and number of respiratory cycles.Main Results: 18 (of 26) PPG researchers responded. Modal range estimates considered a 2-min recording time as target for morphological analysis. Respondents expected a recording to have 86–95% of diagnostic quality pulses, at least 11–20 sequential pulses of diagnostic quality and advocated a 26–50% noise threshold for recording rejection. There were broader responses found for the required number of undistorted beats (although a modal range of 51–60 beats for both finger and toe sites was indicated).Significance: For morphological PPG pulse wave analysis recording acceptability was indicated if <50% of beats have artifact and preferably that a minimum of 50 non-distorted PPG pulses are present (with at least 11–20 sequential) to be of diagnostic quality. Estimates from this knowledge transfer exercise should help inform students and researchers as a guide in standards development for PPG study design.

Quantitative detection of sleep apnea with wearable watch device.

The spread of wearable watch devices with photoplethysmography (PPG) sensors has made it possible to use continuous pulse wave data during daily life. We examined if PPG pulse wave data can be used to detect sleep apnea, a common but underdiagnosed health problem associated with impaired quality of life and increased cardiovascular risk. In 41 patients undergoing diagnostic polysomnography (PSG) for sleep apnea, PPG was recorded simultaneously with a wearable watch device. The pulse interval data were analyzed by an automated algorithm called auto-correlated wave detection with adaptive threshold (ACAT) which was developed for electrocardiogram (ECG) to detect the cyclic variation of heart rate (CVHR), a characteristic heart rate pattern accompanying sleep apnea episodes. The median (IQR) apnea-hypopnea index (AHI) was 17.2 (4.4-28.4) and 22 (54%) subjects had AHI ≥15. The hourly frequency of CVHR (Fcv) detected by the ACAT algorithm closely correlated with AHI (r = 0.81), while none of the time-domain, frequency-domain, or non-linear indices of pulse interval variability showed significant correlation. The Fcv was greater in subjects with AHI ≥15 (19.6 ± 12.3 /h) than in those with AHI <15 (6.4 ± 4.6 /h), and was able to discriminate them with 82% sensitivity, 89% specificity, and 85% accuracy. The classification performance was comparable to that obtained when the ACAT algorithm was applied to ECG R-R intervals during the PSG. The analysis of wearable watch PPG by the ACAT algorithm could be used for the quantitative screening of sleep apnea.

PPGSynth: An Innovative Toolbox for Synthesizing Regular and Irregular Photoplethysmography Waveforms.

Photoplethysmography (PPG) is increasingly used in digital health, exceptionally in smartwatches. The PPG signal contains valuable information about heart activity, and there is lots of research interest in its means and analysis for cardiovascular diseases. Unfortunately, to our knowledge, there is no arrhythmic PPG dataset publicly available—this paper attempt to provide a toolbox that can generate synthesized arrhythmic PPG signals. The model of a single PPG pulse in this toolbox utilizes two combined Gaussian functions. This toolbox supports synthesizing PPG waveform with regular heartbeats and three irregular heartbeats: compensation, interpolation, and reset. The user can generate a large amount of PPG data with a certain irregularity, with different sampling frequency, time length, and a range of noise types (Gaussian noise and multi-frequency noise) can be added to the synthesized PPG which can all be modified from the interface, and different types of arrhythmic PPGs (as calculated by the model) generated. The generation for large PPG datasets that simulate PPG collected from real humans could be used for testing the robustness of developed algorithms that are targeting arrhythmic PPG signals. Our PPG synthesis tool is publicly available.

Traditional Chinese Medicine Pulse Diagnosis on a Smartphone Using Skin Impedance at Acupoints: A Feasibility Study.

In traditional Chinese medicine (TCM), pulse diagnosis is one of the most important methods for diagnosis. A pulse can be felt by applying firm fingertip pressure to the skin where the arteries travel. The pulse diagnosis has become an important tool not only for TCM practitioners but also for several areas of Western medicine. Many pulse measuring devices have been proposed to obtain objective pulse conditions. In the past, pulse diagnosis instruments were single-point sensing methods, which missed a lot of information. Later, multi-point sensing instruments were developed that resolved this issue but were much higher in cost and lacked mobility. In this article, based on the concept of sensor fusion, we describe a portable low-cost system for TCM pulse-type estimation using a smartphone connected to two sensors, including one photoplethysmography (PPG) sensor and one galvanic skin response (GSR) sensor. As a proof of concept, we collected five-minute PPG pulse information and skin impedance on 24 acupoints from 80 subjects. Based on these collected data, we implemented a fully connected neural network (FCN), which was able to provide high prediction accuracy (>90%) for patients with a TCM wiry pulse.

Analysis of Change Rate of SBP and DBP Estimation Fusion Algorithm According to PTT Measurement change PPG Pulse Wave Analysis

Analysis of Change Rate of SBP and DBP Estimation Fusion Algorithm According to PTT Measurement change PPG Pulse Wave Analysis

Classification of Photoplethysmographic Signal Quality with Deep Convolution Neural Networks for Accurate Measurement of Cardiac Stroke Volume

As photoplethysmographic (PPG) signals are comprised of numerous pieces of important physiological information, they have been widely employed to measure many physiological parameters. However, only a high-quality PPG signal can provide a reliable physiological assessment. Unfortunately, PPG signals are easily corrupted by motion artifacts and baseline drift during recording. Although several rule-based algorithms have been developed for evaluating the quality of PPG signals, few artificial intelligence-based algorithms have been presented. Thus, this study aims to classify the quality of PPG signals by using two two-dimensional deep convolution neural networks (DCNN) when the PPG pulse is used to measure cardiac stroke volume (SV) by impedance cardiography. An image derived from a PPG pulse and its differential pulse is used as the input to the two DCNN models. To quantify the quality of individual PPG pulses, the error percentage of the beat-to-beat SV measured by our device and medis® CS 2000 synchronously is used to determine whether the pulse quality is high, middle, or low. Fourteen subjects were recruited, and a total of 3135 PPG pulses (1342 high quality, 73 middle quality, and 1720 low quality) were obtained. We used a traditional DCNN, VGG-19, and a residual DCNN, ResNet-50, to determine the quality levels of the PPG pulses. Their results were all better than the previous rule-based methods. The accuracies of VGG-19 and ResNet-50 were 0.895 and 0.925, respectively. Thus, the proposed DCNN may be applied for the classification of PPG quality and be helpful for improving the SV measurement in impedance cardiography.

Optimal filter characterization for photoplethysmography-based pulse rate and pulse power spectrum estimation.

Photoplethysmography (PPG) is a non-invasive, low-cost optical technique used to assess the cardiovascular system. In recent years, PPG-based heart rate measurement has gained significant attention due to its popularity in wearable devices, as well as its practicality relative to electrocardiography (ECG). Studies comparing the dynamics of ECG- and PPG-based heart rate measures have found small differences between these two modalities; differences related to the physiological processes behind each technique. In this work, we analyzed the spectral coherence and the signal-to-noise ratio between isolated PPG pulses and the raw PPG signal in order to: (i) determine the optimal filter to enhance pulse detection from raw PPG for improved heart rate estimation, and (ii) characterize the spectral content of the PPG pulse. The proposed methods were evaluated on 27000 pulses from a PPG database acquired from 42 participants (adults and children). The results showed that the optimal bandpass filter to enhance PPG from the adult group was 0.6-3.3 Hz, while for the children group it was 1.0-2.7 Hz. The spectral analysis on the pulse signal showed that similar bandwidths were found for the adult (0.8-2.4 Hz) and children (0.9-2.7 Hz) groups. We hope that the results presented herein serve as a baseline for pulse detection algorithms and assist with the development of more sophisticated PPG processing algorithms.

Stochastic Modeling for Photoplethysmography Compression.

Photoplethysmography (PPG) has been widely involved in health monitoring for clinical medicine and wearable devices. To make full use of PPG signals for diagnosis and health care, raw PPG waveforms have to be stored and transmitted in a storage and power-efficient way, which is data compression. In this study, we proposed a new approach for PPG compression using stochastic modeling. This new method models a single cardiac period of PPG waveform using two sets of Gaussian functions to fit the forward and backward waves of the PPG pulse, representing the signal with a few numbers of parameters that share high similarity inter cardiac periods. An adaptive quantization based on higher-order statistics of inter-cardiac- period parameters was then adopted to quantize continuous parameters into transmissive-friendly integers of different bits. Although further ASCII encoding was not applied in this research, comparison results on a wearable PPG dataset with 30 subjects show that the proposed approach can achieve a much higher compression ratio (up to 41 under 200 Samples/s for 18-bit data) than conventional delta modulation-based methods under clinical-acceptable recover quality, with percentage root-mean-square difference (PRD) lower than 9%. This algorithm may also have comparative results with state-of-the-art methods after introducing lossless encoding, which is hardly absent from the latter. This study indicates the high potential of using stochastic modeling in PPG compression, especially for reflective PPG collected by wearable devices where the amplitudes of signals can be significantly affected by respiration.Clinical Relevance-This research establishes a new approach of photoplethysmography compression, which contributes to remote and telehealth monitoring in wearable devices.

Machine Learning Approaches For Improved Continuous, Non-occlusive Arterial Pressure Monitoring Using Photoplethysmography.

Arterial pressure (AP) is a crucial biomarker for cardiovascular disease prevention and management. Photoplethysmography (PPG) could provide a novel, paradigm-shifting approach for continuous, non-obtrusive AP monitoring, comfortably integrated in wearable and mobile devices; yet, it still faces challenges in accuracy and robustness. In this work, we sought to integrate machine learning (ML) techniques into a previously established, clinically-validated classical approach (oBPM®) to develop new accurate AP estimation tools based on PPG, and at the same time improve our understanding of the underlying physiological parameters. In this novel approach, oBPM® was used to pre-process PPG signals and robustly extract physiological features, and ML models were trained on these features to estimate systolic AP (SAP). A feature relevance analysis showed that reference (calibration) information, followed by various morphological parameters of the PPG pulse wave, comprised the most important features for SAP estimation. A performance analysis then revealed that LASSO-regularized linear regression, Gaussian process regression and support vector regression are effective for SAP estimation, particularly when operating on reduced feature sets previously obtained with e.g. LASSO. These approaches yielded substantial reductions in error standard deviation of 9-15% relative to conventional oBPM®. Altogether, these results indicate that ML approaches are well-suited, and promising tools to help overcoming the challenges of ubiquitous AP monitoring.

Age-related changes in pulse risetime measured by multi-site photoplethysmography

Objective: It is accepted that changes in the peripheral pulse waveform characteristics occur with ageing. Pulse risetime is one important feature which has clinical value. However, it is unclear how it varies across the full age spectrum from child to senior and for different peripheral measurement sites. The objectives of this study were to determine the association between age and pulse risetime characteristics over an 8-decade age range at the ears, fingers, and toes, and to consider effects arising from differences in systolic blood pressure (SBP), height and heart rate. Approach: Multi-site photoplethysmography (MPPG) pulse waveforms were recorded non-invasively from the right and left ears, fingers, and toes of 304 normal healthy human subjects (range 6–87 years; 156 male and 148 female). SBP, height, and heart rate were also measured. Multi-site PPG pulse risetimes, and their site differences, were determined. Main results: Univariate regression analysis showed positive correlations with risetime for age (ears, fingers and toes: + 0.8, + 1.9, and + 1.1 ms/year, respectively), SBP (+0.5, + 1.3, and + 0.9 ms/mmHg) and height (+0.5, + 1.2, and + 1.0 ms/cm), but with a clear inverse association with heart rate (−1.8, − 2.5, and − 1.6 ms min) (P < 0.0001). No significant differences between male and female subjects were found for pulse risetime. Significance: Normative multi-site PPG risetime characteristics have been defined in over 300 subjects and are shown to increase with age linearly up to the 8th decade. In contrast, we have shown that heart rate has a clear inverse relationship with risetime for all measurement sites.

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.