Photoplethysmogram signal quality estimation using repeated Gaussian filters and cross-correlation

Signal completion using generative adversarial networks for enhanced photoplethysmography measurement accuracy

Despite the growing adoption of wearable photoplethysmography (PPG) devices in personal health management, their measurement accuracy remains limited due to susceptibility to noise. This paper proposes a novel signal completion technique using generative adversarial networks that ensures both global and local consistency. Our approach innovatively addresses both short- and long-term PPG variations to restore waveforms while maintaining waveform consistency within and between pulses. We evaluated our model by removing up to 50 % of segments from segmented PPG waveforms and comparing the original and reconstructed waveforms, including systolic peak information. The results demonstrate that our method accurately reconstructs waveforms with high fidelity, producing natural and seamless transitions without discontinuities at reconstructed boundaries. Additionally, the reconstructed waveforms preserve typical PPG shapes with minimal distortion, underscoring the effectiveness and novelty of our technique.

Pulse2AI: An Adaptive Framework to Standardize and Process Pulsatile Wearable Sensor Data for Clinical Applications

Goal: To establish Pulse2AI as a reproducible data preprocessing framework for pulsatile signals that generate high-quality machine-learning-ready datasets from raw wearable recordings. Methods: We proposed an end-to-end data preprocessing framework that adapts multiple pulsatile signal modalities and generates machine-learning-ready datasets agnostic to downstream medical tasks. Results: a dataset preprocessed by Pulse2AI improved systolic blood pressure estimation by 29.58%, from 11.41 to 8.03 mmHg in root-mean-square-error (RMSE) and its diastolic counterpart by 26.01%, from 7.93 to 5.87 mmHg in RMSE. For respiration rate (RR) estimation, Pulse2AI boosted performance by 19.69%, from 1.47 to 1.18 breaths per minute (BrPM) in mean-absolute-error (MAE). Conclusion: Pulse2AI turns pulsatile signals into machine learning (ML) ready datasets for arbitrary remote health monitoring tasks. We tested Pulse2AI on multiple pulsatile modalities and demonstrated its efficacy in two medical applications. This work bridges valuable assets in remote sensing and internet of medical things to ML-ready datasets for medical modeling.

PPGFeat: a novel MATLAB toolbox for extracting PPG fiducial points

Photoplethysmography is a non-invasive technique used for measuring several vital signs and for the identification of individuals with an increased disease risk. Its principle of work is based on detecting changes in blood volume in the microvasculature of the skin through the absorption of light. The extraction of relevant features from the photoplethysmography signal for estimating certain physiological parameters is a challenging task, where various feature extraction methods have been proposed in the literature. In this work, we present PPGFeat, a novel MATLAB toolbox supporting the analysis of raw photoplethysmography waveform data. PPGFeat allows for the application of various preprocessing techniques, such as filtering, smoothing, and removal of baseline drift; the calculation of photoplethysmography derivatives; and the implementation of algorithms for detecting and highlighting photoplethysmography fiducial points. PPGFeat includes a graphical user interface allowing users to perform various operations on photoplethysmography signals and to identify, and if required also adjust, the fiducial points. Evaluating the PPGFeat's performance in identifying the fiducial points present in the publicly available PPG-BP dataset, resulted in an overall accuracy of 99% and 3038/3066 fiducial points were correctly identified. PPGFeat significantly reduces the risk of errors in identifying inaccurate fiducial points. Thereby, it is providing a valuable new resource for researchers for the analysis of photoplethysmography signals.

LSTM-based real-time signal quality assessment for blood volume pulse analysis

Remote photoplethysmogram (rPPG) is a low-cost method to extract blood volume pulse (BVP). Some crucial vital signs, such as heart rate (HR) and respiratory rate (RR) etc. can be achieved from BVP for clinical medicine and healthcare application. As compared to the conventional PPG methods, rPPG is more promising because of its non-contacted measurement. However, both BVP detection methods, especially rPPG, are susceptible to motion and illumination artifacts, which lead to inaccurate estimation of vital signs. Signal quality assessment (SQA) is a method to measure the quality of BVP signals and ensure the credibility of estimated physiological parameters. But the existing SQA methods are not suitable for real-time processing. In this paper, we proposed an end-to-end BVP signal quality evaluation method based on a long short-term memory network (LSTM-SQA). Two LSTM-SQA models were trained using the BVP signals obtained with PPG and rPPG techniques so that the quality of BVP signals derived from these two methods can be evaluated, respectively. As there is no publicly available rPPG dataset with quality annotations, we designed a training sample generation method with blind source separation, by which two kinds of training datasets respective to PPG and rPPG were built. Each dataset consists of 38400 high and low-quality BVP segments. The achieved models were verified on three public datasets (IIP-HCI dataset, UBFC-Phys dataset, and LGI-PPGI dataset). The experimental results show that the proposed LSTM-SQA models can effectively predict the quality of the BVP signal in real-time.

COVID-19 Detection Using Photoplethysmography and Neural Networks

The early identification of microvascular changes in patients with Coronavirus Disease 2019 (COVID-19) may offer an important clinical opportunity. This study aimed to define a method, based on deep learning approaches, for the identification of COVID-19 patients from the analysis of the raw PPG signal, acquired with a pulse oximeter. To develop the method, we acquired the PPG signal of 93 COVID-19 patients and 90 healthy control subjects using a finger pulse oximeter. To select the good quality portions of the signal, we developed a template-matching method that excludes samples corrupted by noise or motion artefacts. These samples were subsequently used to develop a custom convolutional neural network model. The model accepts PPG signal segments as input and performs a binary classification between COVID-19 and control samples. The proposed model showed good performance in identifying COVID-19 patients, achieving 83.86% accuracy and 84.30% sensitivity (hold-out validation) on test data. The obtained results indicate that photoplethysmography may be a useful tool for microcirculation assessment and early recognition of SARS-CoV-2-induced microvascular changes. In addition, such a noninvasive and low-cost method is well suited for the development of a user-friendly system, potentially applicable even in resource-limited healthcare settings.

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.

Optimized Signal Quality Assessment for Photoplethysmogram Signals Using Feature Selection

OBJECTIVE

With the increasing use of wearable healthcare devices for remote patient monitoring, reliable signal quality assessment (SQA) is required to ensure the high accuracy of interpretation and diagnosis on the recorded data from patients. Photoplethysmographic (PPG) signals non-invasively measured by wearable devices are extensively used to provide information about the cardiovascular system and its associated diseases. In this study, we propose an approach to optimize the quality assessment of the PPG signals.

METHODS

We used an ensemble-based feature selection scheme to enhance the prediction performance of the classification model to assess the quality of the PPG signals. Our approach for feature and subset size selection yielded the best-suited feature subset, which was optimized to differentiate between the clean and artifact corrupted PPG segments.

CONCLUSION

A high discriminatory power was achieved between two classes on the test data by the proposed feature selection approach, which led to strong performance on all dependent and independent test datasets. We achieved accuracy, sensitivity, and specificity rates of higher than 0.93, 0.89, and 0.97, respectively, for dependent test datasets, independent of heartbeat type, i.e., atrial fibrillation (AF) or non-AF data including normal sinus rhythm (NSR), premature atrial contraction (PAC), and premature ventricular contraction (PVC). For independent test datasets, accuracy, sensitivity, and specificity rates were greater than 0.93, 0.89, and 0.97, respectively, on PPG data recorded from AF and non-AF subjects. These results were found to be more accurate than those of all of the contemporary methods cited in this work.

SIGNIFICANCE

As the results illustrate, the advantage of our proposed scheme is its robustness against dynamic variations in the PPG signal during long-term 14-day recordings accompanied with different types of physical activities and a diverse range of fluctuations and waveforms caused by different individual hemodynamic characteristics, and various types of recording devices. This robustness instills confidence in the application of the algorithm to various kinds of wearable devices as a reliable PPG signal quality assessment approach.

Automated Segmentation of the Systolic and Diastolic Phases in Wrist Pulse Signal Using Long Short-Term Memory Network

Purpose

Single-period segmentation is one of the important steps in time-domain analysis of pulse signals, which is the basis of time-domain feature extraction. The existing single-period segmentation methods have the disadvantages of generalization, reliability, and robustness.

Method

This paper proposed a period segmentation method of pulse signals based on long short-term memory (LSTM) network. The preprocessing was performed to remove noises and baseline drift of pulse signals. Thus, LabelMe was used to label each period of the pulse signals into two parts according to the location of the starting point of main wave and the dicrotic notch, and the dataset of the pulse signal period segmentation was established. Consequently, the labeled dataset was input into the LSTM for training and testing, and the results were compared with sum slope function method.

Result

The remarkable result with the whole period segmentation accuracy of 92.8% was achieved for the segmentation of seven types of pulse signals. And the segmentation accuracies of the systolic phase, diastolic phase, and whole period using this method were higher than those of the sum slope function method.

Conclusion

LSTM-based pulse signal segmentation method can achieve outstanding, robust, and reliable segmentation effects of the systolic phase, diastolic phase, and whole period of pulse signals. The research provides a new idea and method for the segmentation of pulse signals.

Wrist Photoplethysmography Signal Quality Assessment for Reliable Heart Rate Estimate and Morphological Analysis

Photoplethysmographic (PPG) signals are mainly employed for heart rate estimation but are also fascinating candidates in the search for cardiovascular biomarkers. However, their high susceptibility to motion artifacts can lower their morphological quality and, hence, affect the reliability of the extracted information. Low reliability is particularly relevant when signals are recorded in a real-world context, during daily life activities. We aim to develop two classifiers to identify PPG pulses suitable for heart rate estimation (Basic-quality classifier) and morphological analysis (High-quality classifier). We collected wrist PPG data from 31 participants over a 24 h period. We defined four activity ranges based on accelerometer data and randomly selected an equal number of PPG pulses from each range to train and test the classifiers. Independent raters labeled the pulses into three quality levels. Nineteen features, including nine novel features, were extracted from PPG pulses and accelerometer signals. We conducted ten-fold cross-validation on the training set (70%) to optimize hyperparameters of five machine learning algorithms and a neural network, and the remaining 30% was used to test the algorithms. Performances were evaluated using the full features and a reduced set, obtained downstream of feature selection methods. Best performances for both Basic- and High-quality classifiers were achieved using a Support Vector Machine (Acc: 0.96 and 0.97, respectively). Both classifiers outperformed comparable state-of-the-art classifiers. Implementing automatic signal quality assessment methods is essential to improve the reliability of PPG parameters and broaden their applicability in a real-world context.

Wearable Photoplethysmography for Cardiovascular Monitoring

Smart wearables provide an opportunity to monitor health in daily life and are emerging as potential tools for detecting cardiovascular disease (CVD). Wearables such as fitness bands and smartwatches routinely monitor the photoplethysmogram signal, an optical measure of the arterial pulse wave that is strongly influenced by the heart and blood vessels. In this survey, we summarize the fundamentals of wearable photoplethysmography and its analysis, identify its potential clinical applications, and outline pressing directions for future research in order to realize its full potential for tackling CVD.

Photoplethysmogram Analysis and Applications: An Integrative Review

Beyond its use in a clinical environment, photoplethysmogram (PPG) is increasingly used for measuring the physiological state of an individual in daily life. This review aims to examine existing research on photoplethysmogram concerning its generation mechanisms, measurement principles, clinical applications, noise definition, pre-processing techniques, feature detection techniques, and post-processing techniques for photoplethysmogram processing, especially from an engineering point of view. We performed an extensive search with the PubMed, Google Scholar, Institute of Electrical and Electronics Engineers (IEEE), ScienceDirect, and Web of Science databases. Exclusion conditions did not include the year of publication, but articles not published in English were excluded. Based on 118 articles, we identified four main topics of enabling PPG: (A) PPG waveform, (B) PPG features and clinical applications including basic features based on the original PPG waveform, combined features of PPG, and derivative features of PPG, (C) PPG noise including motion artifact baseline wandering and hypoperfusion, and (D) PPG signal processing including PPG preprocessing, PPG peak detection, and signal quality index. The application field of photoplethysmogram has been extending from the clinical to the mobile environment. Although there is no standardized pre-processing pipeline for PPG signal processing, as PPG data are acquired and accumulated in various ways, the recently proposed machine learning-based method is expected to offer a promising solution.

A supervised machine learning semantic segmentation approach for detecting artifacts in plethysmography signals from wearables

Objective. Wearable devices equipped with plethysmography (PPG) sensors provided a low-cost, long-term solution to early diagnosis and continuous screening of heart conditions. However PPG signals collected from such devices often suffer from corruption caused by artifacts. The objective of this study is to develop an effective supervised algorithm to locate the regions of artifacts within PPG signals.Approach. We treat artifact detection as a 1D segmentation problem. We solve it via a novel combination of an active-contour-based loss and an adapted U-Net architecture. The proposed algorithm was trained on the PPG DaLiA training set, and further evaluated on the PPG DaLiA testing set, WESAD dataset and TROIKA dataset.Main results. We evaluated with the DICE score, a well-established metric for segmentation accuracy evaluation in the field of computer vision. The proposed method outperforms baseline methods on all three datasets by a large margin (≈7 percentage points above the next best method). On the PPG DaLiA testing set, WESAD dataset and TROIKA dataset, the proposed method achieved 0.8734 ± 0.0018, 0.9114 ± 0.0033 and 0.8050 ± 0.0116 respectively. The next best method only achieved 0.8068 ± 0.0014, 0.8446 ± 0.0013 and 0.7247 ± 0.0050.Significance. The proposed method is able to pinpoint exact locations of artifacts with high precision; in the past, we had only a binary classification of whether a PPG signal has good or poor quality. This more nuanced information will be critical to further inform the design of algorithms to detect cardiac arrhythmia.

Learning based Quality Indicator Aiding Heart Rate Estimation in Wrist-Worn PPG

Technological advancements and miniaturization of wearable sensors have enabled long-term pervasive physiological monitoring. Wrist-worn photoplethysmography (PPG) sensors, although quite popular owing to their form factor, suffer from poor signal quality in ambulatory settings due to motion artifacts. This affects the reliable estimation of vital cardiac parameters, especially during motion/activities of daily living. Hence, in this paper, we have developed a learningbased quality indicator engine (QIE), evaluating on 23 PPG records of the TROIKA database. The engine comprises the fundamental steps of frequency-domain feature extraction, feature selection and classification by an ensemble of decision trees, achieving an accuracy of 83% in the testing set. To the best of our knowledge, the proposed quality engine is the first to be evaluated on wrist-PPG data acquired during various physical activities and with respect to improvement in heart rate (HR) estimation. The QIE demonstrated an average improvement of 43% in HR estimation, when used in conjunction with state-ofthe-art WFPV algorithm.Clinical Relevance- The proposed quality indicator engine helps to increase the efficacy of vital parameter estimation (e.g. heart rate) from pervasive, wrist-worn PPG sensors on the backdrop of motion artifacts when used in ambulatory settings (e.g. activities of daily living).

Night to night variability of pulse oximetry features in children at home and at the hospital

Objective. Investigation of the night-to-night (NtN) variability of pulse oximetry features in children with suspicion of Sleep Apnea.Approach. Following ethics approval and informed consent, 75 children referred to British Columbia Children's Hospital for overnight PSG were recorded on three consecutive nights, including one at the hospital simultaneously with polysomnography and 2 nights at home. During all three nights, a smartphone-based pulse oximeter sensor was used to record overnight pulse oximetry (SpO2 and photoplethysmogram). Features characterizing SpO2 dynamics and heart rate were derived. The NtN variability of these features over the three different nights was investigated using linear mixed models.Main results. Overall most pulse oximetry features (e.g. the oxygen desaturation index) showed no NtN variability. One of the exceptions is for the signal quality, which was significantly lower during at home measurements compared to measurements in the hospital.Significance. At home pulse oximetry screening shows an increasing predictive value to investigate obstructive sleep apnea (OSA) severity. Hospital recordings affect subjects normal sleep and OSA severity and recordings may vary between nights at home. Before establishing the role of home monitoring as a diagnostic test for OSA, we must first determine their NtN variability. Most pulse oximetry features showed no significant NtN variability and could therefore be used in future at-home testing to create a reliable and consistent OSA screening tool. A single night recording at home should be able to characterize pulse oximetry features in children.

Classification of blood pressure in critically ill patients using photoplethysmography and machine learning

OBJECTIVE

The aim of this study was to evaluate the capability of features extracted from photoplethysmography (PPG) based Pulse Rate Variability (PRV) to classify hypertensive, normotensive and hypotensive events, and to estimate mean arterial, systolic and diastolic blood pressure in critically ill patients.

METHODS

Time-domain, frequency-domain and non-linear indices from PRV were extracted from 5-min and 1-min segments obtained from PPG signals. These features were filtered using machine learning algorithms in order to obtain the optimal combination for the classification of hypertensive, hypotensive and normotensive events, and for the estimation of blood pressure.

RESULTS

5-min segments allowed for an improved performance in both classification and estimation tasks. Classification of blood pressure states showed around 70% accuracy and around 75% specificity. The sensitivity, precision and F1 scores were around 50%. In estimating mean arterial, systolic, and diastolic blood pressure, mean absolute errors as low as 2.55 ± 0.78 mmHg, 4.74 ± 2.33 mmHg, and 1.78 ± 0.14 mmHg were obtained, respectively. Bland-Altman analysis and Wilcoxon rank sum tests showed good agreement between real and estimated values, especially for mean and diastolic arterial blood pressures.

CONCLUSION

PRV-based features could be used for the classification of blood pressure states and the estimation of blood pressure values, although including additional features from the PPG waveform could improve the results.

SIGNIFICANCE

PRV contains information related to blood pressure, which may aid in the continuous, noninvasive, non-intrusive estimation of blood pressure and detection of hypertensive and hypotensive events in critically ill subjects.

Differential effects of the blood pressure state on pulse rate variability and heart rate variability in critically ill patients

Heart rate variability (HRV) utilizes the electrocardiogram (ECG) and has been widely studied as a non-invasive indicator of cardiac autonomic activity. Pulse rate variability (PRV) utilizes photoplethysmography (PPG) and recently has been used as a surrogate for HRV. Several studies have found that PRV is not entirely valid as an estimation of HRV and that several physiological factors, including the pulse transit time (PTT) and blood pressure (BP) changes, may affect PRV differently than HRV. This study aimed to assess the relationship between PRV and HRV under different BP states: hypotension, normotension, and hypertension. Using the MIMIC III database, 5 min segments of PPG and ECG signals were used to extract PRV and HRV, respectively. Several time-domain, frequency-domain, and nonlinear indices were obtained from these signals. Bland–Altman analysis, correlation analysis, and Friedman rank sum tests were used to compare HRV and PRV in each state, and PRV and HRV indices were compared among BP states using Kruskal–Wallis tests. The findings indicated that there were differences between PRV and HRV, especially in short-term and nonlinear indices, and although PRV and HRV were altered in a similar manner when there was a change in BP, PRV seemed to be more sensitive to these changes.

Sources of Inaccuracy in Photoplethysmography for Continuous Cardiovascular Monitoring

Photoplethysmography (PPG) is a low-cost, noninvasive optical technique that uses change in light transmission with changes in blood volume within tissue to provide information for cardiovascular health and fitness. As remote health and wearable medical devices become more prevalent, PPG devices are being developed as part of wearable systems to monitor parameters such as heart rate (HR) that do not require complex analysis of the PPG waveform. However, complex analyses of the PPG waveform yield valuable clinical information, such as: blood pressure, respiratory information, sympathetic nervous system activity, and heart rate variability. Systems aiming to derive such complex parameters do not always account for realistic sources of noise, as testing is performed within controlled parameter spaces. A wearable monitoring tool to be used beyond fitness and heart rate must account for noise sources originating from individual patient variations (e.g., skin tone, obesity, age, and gender), physiology (e.g., respiration, venous pulsation, body site of measurement, and body temperature), and external perturbations of the device itself (e.g., motion artifact, ambient light, and applied pressure to the skin). Here, we present a comprehensive review of the literature that aims to summarize these noise sources for future PPG device development for use in health monitoring.

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.

A standardized validity assessment protocol for physiological signals from wearable technology: Methodological underpinnings and an application to the E4 biosensor

Wearable physiological measurement devices for ambulatory research with novel sensing technology are introduced with ever increasing frequency, requiring fast, standardized, and rigorous validation of the physiological signals measured by these devices and their derived parameters. At present, there is a lack of consensus on a standardized protocol or framework with which to test the validity of this new technology, leading to the use of various (often unfit) methods. This study introduces a comprehensive validity assessment protocol for physiological signals (electrodermal activity and cardiovascular activity) and investigates the validity of the E4 wearable (an example of such a new device) on the three levels proposed by the protocol: (1) the signal level, with a cross-correlation; (2) the parameter level, with Bland–Altman plots; and (3) the event level, with the detection of physiological changes due to external stressor levels via event difference plots. The results of the protocol show that the E4 wearable is valid for heart rate, RMSSD, and SD at the parameter and event levels, and for the total amplitude of skin conductance responses at the event level when studying strong sustained stressors. These findings are in line with the prior literature and demonstrate the applicability of the protocol. The validity assessment protocol proposed in this study provides a comprehensive, standardized, and feasible method for assessment of the quality of physiological data coming from new wearable (sensor) technology aimed at ambulatory research.

On-Device Reliability Assessment and Prediction of Missing Photoplethysmographic Data Using Deep Neural Networks

Photoplethysmographic (PPG) measurements from ambulatory subjects may suffer from unreliability due to body movements and missing data segments due to loosening of sensor. This paper describes an on-device reliability assessment from PPG measurements using a stack denoising autoencoder (SDAE) and multilayer perceptron neural network (MLPNN). The missing segments were predicted by a personalized convolutional neural network (CNN) and long-short term memory (LSTM) model using a short history of the same channel data. Forty sets of volunteers' data, consisting of equal share of healthy and cardiovascular subjects were used for validation and testing. The PPG reliability assessment model (PRAM) achieved over 95% accuracy for correctly identifying acceptable PPG beats out of total 5000 using expert annotated data. Disagreement with experts' annotation was nearly 3.5%. The missing segment prediction model (MSPM) achieved a root mean square error (RMSE) of 0.22, and mean absolute error (MAE) of 0.11 for 40 missing beats prediction using only four beat history from the same channel PPG. The two models were integrated in a standalone device based on quad-core ARM Cortex-A53, 1.2 GHz, with 1 GB RAM, with 130 MB memory requirement and latency ∼0.35 s per beat prediction with a 30 s frame. The present method also provides improved performance with published works on PPG quality assessment and missing data prediction using two public datasets, CinC and MIMIC-II under PhysioNet.

Fuzzy-Inspired Photoplethysmography Signal Classification with Bio-Inspired Optimization for Analyzing Cardiovascular Disorders

The main aim of this paper is to optimize the output of diagnosis of Cardiovascular Disorders (CVD) in Photoplethysmography (PPG) signals by utilizing a fuzzy-based approach with classification. The extracted parameters such as Energy, Variance, Approximate Entropy (ApEn), Mean, Standard Deviation (STD), Skewness, Kurtosis, and Peak Maximum are obtained initially from the PPG signals, and based on these extracted parameters, the fuzzy techniques are incorporated to model the Cardiovascular Disorder(CVD) risk levels from PPG signals. Optimization algorithms such as Differential Search (DS), Shuffled Frog Leaping Algorithm (SFLA), Wolf Search (WS), and Animal Migration Optimization (AMO) are implemented to the fuzzy modeled levels to optimize them further so that the PPG cardiovascular classification can be characterized well. This kind of approach is totally new in PPG signal classification, and the results show that when fuzzy-inspired modeling is implemented with WS optimization and classified with the Radial Basis Function (RBF) classifier, a classification accuracy of 94.79% is obtained for normal cases. When fuzzy-inspired modeling is implemented with AMO and classified with the Support Vector Machine-Radial Basis Function (SVM-RBF) classifier, a classification accuracy of 95.05% is obtained for CVD cases.

Heart Rate Variability (HRV) and Pulse Rate Variability (PRV) for the Assessment of Autonomic Responses

Introduction: Heart Rate Variability (HRV) and Pulse Rate Variability (PRV), are non-invasive techniques for monitoring changes in the cardiac cycle. Both techniques have been used for assessing the autonomic activity. Although highly correlated in healthy subjects, differences in HRV and PRV have been observed under various physiological conditions. The reasons for their disparities in assessing the degree of autonomic activity remains unknown.

Methods: To investigate the differences between HRV and PRV, a whole-body cold exposure (CE) study was conducted on 20 healthy volunteers (11 male and 9 female, 30.3 ± 10.4 years old), where PRV indices were measured from red photoplethysmography signals acquired from central (ear canal, ear lobe) and peripheral sites (finger and toe), and HRV indices from the ECG signal. PRV and HRV indices were used to assess the effects of CE upon the autonomic control in peripheral and core vasculature, and on the relationship between HRV and PRV. The hypotheses underlying the experiment were that PRV from central vasculature is less affected by CE than PRV from the peripheries, and that PRV from peripheral and central vasculature differ with HRV to a different extent, especially during CE.

Results: Most of the PRV time-domain and Poincaré plot indices increased during cold exposure. Frequency-domain parameters also showed differences except for relative-power frequency-domain parameters, which remained unchanged. HRV-derived parameters showed a similar behavior but were less affected than PRV. When PRV and HRV parameters were compared, time-domain, absolute-power frequency-domain, and non-linear indices showed differences among stages from most of the locations. Bland-Altman analysis showed that the relationship between HRV and PRV was affected by CE, and that it recovered faster in the core vasculature after CE.

Conclusion: PRV responds to cold exposure differently to HRV, especially in peripheral sites such as the finger and the toe, and may have different information not available in HRV due to its non-localized nature. Hence, multi-site PRV shows promise for assessing the autonomic activity on different body locations and under different circumstances, which could allow for further understanding of the localized responses of the autonomic nervous system.

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.

A Supervised Approach to Robust Photoplethysmography Quality Assessment

Early detection of Atrial Fibrillation (AFib) is crucial to prevent stroke recurrence. New tools for monitoring cardiac rhythm are important for risk stratification and stroke prevention. As many of new approaches to long-term AFib detection are now based on photoplethysmogram (PPG) recordings from wearable devices, ensuring high PPG signal-to-noise ratios is a fundamental requirement for a robust detection of AFib episodes. Traditionally, signal quality assessment is often based on the evaluation of similarity between pulses to derive signal quality indices. There are limitations to using this approach for accurate assessment of PPG quality in the presence of arrhythmia, as in the case of AFib, mainly due to substantial changes in pulse morphology. In this paper, we first tested the performance of algorithms selected from a body of studies on PPG quality assessment using a dataset of PPG recordings from patients with AFib. We then propose machine learning approaches for PPG quality assessment in 30-s segments of PPG recording from 13 stroke patients admitted to the University of California San Francisco (UCSF) neuro intensive care unit and another dataset of 3764 patients from one of the five UCSF general intensive care units. We used data acquired from two systems, fingertip PPG (fPPG) from a bedside monitor system, and radial PPG (rPPG) measured using a wearable commercial wristband. We compared various supervised machine learning techniques including k-nearest neighbors, decisions trees, and a two-class support vector machine (SVM). SVM provided the best performance. fPPG signals were used to build the model and achieved 0.9477 accuracy when tested on the data from the fPPG exclusive to the test set, and 0.9589 accuracy when tested on the rPPG data.

A Pulse Signal Preprocessing Method Based on the Chauvenet Criterion

Pulse signals are widely used to evaluate the status of the human cardiovascular, respiratory, and circulatory systems. In the process of being collected, the signals are usually interfered by some factors, such as the spike noise and the poor-sensor-contact noise, which have severely affected the accuracy of the subsequent detection models. In recent years, some methods have been applied to processing the above noisy signals, such as dynamic time warping, empirical mode decomposition, autocorrelation, and cross-correlation. Effective as they are, those methods are complex and difficult to implement. It is also found that the noisy signals are tightly related to gross errors. The Chauvenet criterion, one of the gross error discrimination criterions, is highly efficient and widely applicable for being without the complex calculations like decomposition and reconstruction. Therefore, in this study, based on the Chauvenet criterion, a new pulse signal preprocessing method is proposed, in which adaptive thresholds are designed, respectively, to discriminate the abnormal signals caused by spike noise and poor-sensor-contact noise. 81 hours of pulse signals (with a sleep apnea annotated every 30 seconds and 9,720 segments in total) from the MIT-BIH Polysomnographic Database are used in the study, including 35 minutes of poor-sensor-contact noises and 25 minutes of spike noises. The proposed method was used to preprocess the pulse signals, in which 9,684 segments out of a total of 9,720 were correctly discriminated, and the accuracy of the method reached 99.63%. To quantitatively evaluate the noise removal effect, a simulation experiment is conducted to compare the Jaccard Similarity Coefficient (JSC) calculated before and after the noise removal, respectively, and the results show that the preprocessed signal obtains higher JSC, closer to the reference signal, which indicates that the proposed method can effectively improve the signal quality. In order to evaluate the method, three back-propagation (BP) sleep apnea detection models with the same network structure and parameters were established, respectively. Through comparing the recognition rate and the prediction rate of the models, higher rates were obtained by using the proposed method. To prove the efficiency, the comparison experiment between the proposed Chauvenet-based method and a Romanovsky-based method was conducted, and the execution time of the proposed method is much shorter than that of the Romanovsky method. The results suggest that the superiority in execution time of the Chauvenet-based method becomes more significant as the date size increases.

Classification of Photoplethysmographic Signal Quality with Fuzzy Neural Network for Improvement of Stroke Volume Measurement

Photoplethysmography (PPG) has been extensively employed to acquire some physiological parameters such as heart rate, oxygen saturation, and blood pressure. However, PPG signals are frequently corrupted by motion artifacts and baseline wandering, especially for the reflective PPG sensor. Several different algorithms have been studied for determining the signal quality of PPG by the characteristic parameters of its waveform and the rule-based methods. The levels of signal quality usually were defined by the manual operations. Thus, whether the good PPG waveforms are enough to increase the accuracy of the measurement is still a subjective issue. The aim of this study is to use a fuzzy neural network to determine the signal quality indexes (SQI) of PPG pulses measured by the impedance cardiography. To test the algorithm performance, the beat-to-beat stroke volumes (SV) were measured with our device and the medis® CS 2000, synchronously. A total of 1466 pulses from 10 subjects were used to validate our algorithm in which the SQIs of 1007 pulses were high, those of 71 pulses were in the middle, and those of 388 pulses were low. The total error of SV measurement was −18 ± 22.0 mL. The performances of the classification were that the sensitivity and specificity for the 1007 pulses with the high SQIs were 0.81 and 0.90, and the error of SV measurement was 6.4 ± 12.8 mL. The sensitivity and specificity for the 388 pulses with the low SQIs were 0.84 and 0.93, while the error of SV measurement was 30.4 ± 3.6 mL. The results show that the proposed algorithm could be helpful in choosing good-quality PPG pulses to increase the accuracy of SV measurement in the impedance plethysmography.

Airflow from nasal pulse oximetry in the screening of obstructive sleep apnea

Obstructive Sleep Apnea (OSA) is recognized as an increasing health risk, leading to daytime sleepiness and various medical conditions, such as hypertension and heart failure. Polysomnography (PSG), the gold standard to diagnose OSA, is a resource-intensive and expensive investigation confined to the hospital.Portable home monitoring, i.e. pulse oximetry, may become an acceptable OSA screening method. The novel nasal pulse oximeter sensor (Xhale Alar) adds the possibility of combining pulse oximetry (SpO2) with airflow analysis by an integrated thermistor, which might increase the diagnostic accuracy.In the Alar pilot study, 39 adults were measured during an overnight PSG recording together with the Alar sensor. This study aims to investigate the additional value of an airflow signal compared to SpO2 analysis in OSA screening. Both time and spectral features were extracted from SpO2 and airflow signals recorded with the Alar sensor. Leave one out cross-validation was used to develop Random Forest models in screening for apnea-hypopnea index (AHI) thresholds 5 and 10. Using both AHI ≥ 5 and AHI ≥ 10 as the diagnostic cutoff, the airflow signal shows respectively an AUC of 89% and 80% compared to 78% and 77% with SpO2 analysis, showing a higher performance using an airflow signal in screening adults for OSA.

Deep learning approaches for plethysmography signal quality assessment in the presence of atrial fibrillation

OBJECTIVE

Photoplethysmography (PPG) monitoring has been implemented in many portable and wearable devices we use daily for health and fitness tracking. Its simplicity and cost-effectiveness has enabled a variety of biomedical applications, such as continuous long-term monitoring of heart arrhythmias, fitness, and sleep tracking, and hydration monitoring. One major issue that can hinder PPG-based applications is movement artifacts, which can lead to false interpretations. In many implementations, noisy PPG signals are discarded. Misinterpreted or discarded PPG signals pose a problem in applications where the goal is to increase the yield of detecting physiological events, such as in the case of paroxysmal atrial fibrillation (AF)-a common episodic heart arrhythmia and a leading risk factor for stroke. In this work, we compared a traditional machine learning and deep learning approaches for PPG quality assessment in the presence of AF, in order to find the most robust method for PPG quality assessment.

APPROACH

The training data set was composed of 78 278 30 s long PPG recordings from 3764 patients using bedside patient monitors. Two different representations of PPG signals were employed-a time-series based (1D) one and an image-based (2D) one. Trained models were tested on an independent set of 2683 30 s PPG signals from 13 stroke patients.

MAIN RESULTS

ResNet18 showed a higher performance (0.985 accuracy, 0.979 specificity, and 0.988 sensitivity) than SVM and other deep learning approaches. 2D-based models were generally more accurate than 1D-based models.

SIGNIFICANCE

2D representation of PPG signal enhances the accuracy of PPG signal quality assessment.

Development of an Ambulatory Biofeedback App to Enhance Emotional Awareness in Patients with Borderline Personality Disorder: Multicycle Usability Testing Study

Background

Patients with borderline personality disorder experience great difficulties in regulating their emotions. They often are unable to effectively detect their emotional arousal and struggle to timely apply learned techniques for emotion regulation. Although the use of continuous wearable biofeedback has been repeatedly suggested as an option to improve patients’ emotional awareness, this type of app is not yet available for clinical use. Therefore, we developed an ambulatory biofeedback app named Sense-IT that can be integrated in mental health care.

Objective

The aim of the study was to develop an ambulatory biofeedback app for mental health care that helps with learning to better recognize changes in personal emotional arousal and increases emotional awareness.

Methods

Using several methods in a tailored User Centred Design (UCD) framework, we tested the app’s usability and user experience (UX) via a cyclic developmental process with multiple user groups (patients, therapists, and UCD experts; 3-5 per group, per cycle).

Results

The process resulted in a stable prototype of the app that meets most of the identified user requirements. The app was valued as useful and usable by involved patients, therapists, and UCD experts. On the Subjective Usability Scale (SUS), the patients rated the app as “Good” (average score of 78.8), whereas the therapists rated the app as “OK” (average score of 59.4). The UCD experts judged the app’s overall usability as between “OK” and “acceptable” (average score of 0.87 on a cognitive walkthrough). As most critical usability problems were identified and addressed in the first cycle of the prototyping process, subsequent cycles were mainly about implementing new or extending existing functions, and other adjustments to improve UX.

Conclusions

mHealth development within a clinical mental health setting is challenging, yet feasible and welcomed by targeted users. This paper shows how new mHealth interventions for mental health care can be met with enthusiasm and openness by user groups that are known to be reluctant to embrace technological innovations. The use of the UCD framework, involving multiple user groups, proved to be of added value during design and realization as evidenced by the complementary requirements and perspectives. Future directions on studying clinical effectiveness of the app, appliance of the app in other fields, and the implications of integration of the app for daily practice in mental health are discussed.

Physiologically driven, altitude-adaptive model for the interpretation of pediatric oxygen saturation at altitudes above 2,000 m a.s.l

Measuring peripheral oxygen saturation (SpO2) with pulse oximeters at the point of care is widely established. However, since SpO2 is dependent on ambient atmospheric pressure, the distribution of SpO2 values in populations living above 2000 m a.s.l. is largely unknown. Here, we propose and evaluate a computer model to predict SpO2 values for pediatric permanent residents living between 0 and 4,000 m a.s.l. Based on a sensitivity analysis of oxygen transport parameters, we created an altitude-adaptive SpO2 model that takes physiological adaptation of permanent residents into account. From this model, we derived an altitude-adaptive abnormal SpO2 threshold using patient parameters from literature. We compared the obtained model and threshold against a previously proposed threshold derived statistically from data and two empirical data sets independently recorded from Peruvian children living at altitudes up to 4,100 m a.s.l. Our model followed the trends of empirical data, with the empirical data having a narrower healthy SpO2 range below 2,000 m a.s.l. but the medians never differed more than 2.3% across all altitudes. Our threshold estimated abnormal SpO2 in only 17 out of 5,981 (0.3%) healthy recordings, whereas the statistical threshold returned 95 (1.6%) recordings outside the healthy range. The strength of our parametrized model is that it is rooted in physiology-derived equations and enables customization. Furthermore, as it provides a reference SpO2, it could assist practitioners in interpreting SpO2 values for diagnosis, prognosis, and oxygen administration at higher altitudes.NEW & NOTEWORTHY Our model describes the altitude-dependent decrease of SpO2 in healthy pediatric residents based on physiological equations and can be adapted based on measureable clinical parameters. The proposed altitude-specific abnormal SpO2 threshold might be more appropriate than rigid guidelines for administering oxygen that currently are only available for patients at sea level. We see this as a starting point to discuss and adapt oxygen administration guidelines.

Signal quality measure for pulsatile physiological signals using morphological features: Applications in reliability measure for pulse oximetry

Pulse oximetry is a noninvasive and low-cost physiological monitor that measures blood oxygen levels. While the noninvasive nature of pulse oximetry is advantageous, the estimates of oxygen saturation generated by these devices are prone to motion artifacts and ambient noise, reducing the reliability of such estimations. Clinicians combat this by assessing the quality of oxygen saturation estimation by visual inspection of the photoplethysmograph (PPG), which represents changes in pulsatile blood volume and is also generated by the pulse oximeter. In this paper, we propose six morphological features that can be used to determine the quality of the PPG signal and generate a signal quality index. Unlike many similar studies, this approach uses machine learning and does not require a separate signal, such as ECG, for reference. Multiple algorithms were tested against 46 30-min PPG segments of patients with cardiovascular and respiratory conditions, including atrial fibrillation, hypoxia, acute heart failure, pneumonia, ARDS, and pulmonary embolism. These signals were independently annotated for signal quality by two clinicians, with the union of their annotations used as the ground-truth. Similar to any physiological signal recorded in a clinical setting, the utilized dataset is also unbalanced in favor of good quality segments. The experiments showed that a cost-sensitive Support Vector Machine (SVM) outperformed other tested methods and was robust to the unbalanced nature of the data. Though the proposed algorithm was tested on PPG signals, the methodology remains agnostic to the dataset used, and may be applied to any type of pulsatile physiological signal.

Identification of Pulse Onset on Cerebral Blood Flow Velocity Waveforms: A Comparative Study

The low cost, simple, noninvasive, and continuous measurement of cerebral blood flow velocity (CBFV) by transcranial Doppler is becoming a common clinical tool for the assessment of cerebral hemodynamics. CBFV monitoring can also help with noninvasive estimation of intracranial pressure and evaluation of mild traumatic brain injury. Reliable CBFV waveform analysis depends heavily on its accurate beat-to-beat delineation. However, CBFV is inherently contaminated with various types of noise/artifacts and has a wide range of possible pathological waveform morphologies. Thus, pulse onset detection is in general a challenging task for CBFV signal. In this paper, we conducted a comprehensive comparative analysis of three popular pulse onset detection methods using a large annotated dataset of 92,794 CBFV pulses—collected from 108 subarachnoid hemorrhage patients admitted to UCLA Medical Center. We compared these methods not only in terms of their accuracy and computational complexity, but also for their sensitivity to the selection of their parameters' values. The results of this comprehensive study revealed that using optimal values of the parameters obtained from sensitivity analysis, one method can achieve the highest accuracy for CBFV pulse onset detection with true positive rate (TPR) of 97.06% and positive predictivity value (PPV) of 96.48%, when error threshold is set to just less than 10 ms. We conclude that the high accuracy and low computational complexity of this method (average running time of 4ms/pulse) makes it a reliable algorithm for CBFV pulse onset detection.

A novel diversity method for smartphone camera-based heart rhythm signals in the presence of motion and noise artifacts

The advent of smartphones has advanced the use of embedded sensors to acquire various physiological information. For example, smartphone camera sensors and accelerometers can provide heart rhythm signals to the subjects, while microphones can give respiratory signals. However, the acquired smartphone-based physiological signals are more vulnerable to motion and noise artifacts (MNAs) compared to using medical devices, since subjects need to hold the smartphone with proper contact to the smartphone camera and lens stably and tightly for a duration of time without any movement in the hand or finger. This results in more MNA than traditional methods, such as placing a finger inside a tightly enclosed pulse oximeter to get PPG signals, which provides stable contact between the sensor and the subject's finger. Moreover, a smartphone lens does not block ambient light in an effective way, while pulse oximeters are designed to block the ambient light effectively. In this paper, we propose a novel diversity method for smartphone signals that reduces the effect of MNAs during heart rhythm signal detection by 1) acquiring two heterogeneous signals from a color intensity signal and a fingertip movement signal, and 2) selecting the less MNA-corrupted signal of the two signals. The proposed method has advantages in that 1) diversity gain can be obtained from the two heterogeneous signals when one signal is clean while the other signal is corrupted, and 2) acquisition of the two heterogeneous signals does not double the acquisition procedure but maintains a single acquisition procedure, since two heterogeneous signals can be obtained from a single smartphone camera recording. In our diversity method, we propose to choose the better signal based on the signal quality indices (SQIs), i.e., standard deviation of instantaneous heart rate (STD-HR), root mean square of the successive differences of peak-to-peak time intervals (RMSSD-T), and standard deviation of peak values (STD-PV). As a performance metric evaluating the proposed diversity method, the ratio of usable period is considered. Experimental results show that our diversity method increases the usable period 19.53% and 6.25% compared to the color intensity or the fingertip movement signals only, respectively.

Photoplethysmography in dogs and cats: a selection of alternative measurement sites for a pet monitor

OBJECTIVE

Photoplethysmography (PPG) is an increasingly popular health and well-being tool for monitoring heart rate and oxygen saturation. Due to the pigmentation and hairiness of dogs and cats, a pulse oximeter is routinely placed solely on the tongue. As this approach is feasible only for pet monitor use during surgical procedures, we investigate PPG signal quality on several other measurement sites that would be better tolerated by conscious animals.

APPROACH

Acquired PPG signals are analyzed by four signal quality indices: mean baseline, signal power, kurtosis, and tolerance score.

MAIN RESULTS

In dogs, the metacarpus and tail can be substituted for oral pulse oximeter placement since both measurement sites exhibited high PPG signal kurtosis and were considered well-tolerated. In cats, the digit could be used with some limitations.

SIGNIFICANCE

Pet monitors with pulse oximeter probes adjusted to promising measurement sites could enable veterinarians and owners to monitor animals when fully awake.

Data Integrity-Based Methodology and Checklist for Identifying Implementation Risks of Physiological Sensing in Mobile Health Projects: Quantitative and Qualitative Analysis

Background

Mobile health (mHealth) technologies have the potential to bring health care closer to people with otherwise limited access to adequate health care. However, physiological monitoring using mobile medical sensors is not yet widely used as adding biomedical sensors to mHealth projects inherently introduces new challenges. Thus far, no methodology exists to systematically evaluate these implementation challenges and identify the related risks.

Objective

This study aimed to facilitate the implementation of mHealth initiatives with mobile physiological sensing in constrained health systems by developing a methodology to systematically evaluate potential challenges and implementation risks.

Methods

We performed a quantitative analysis of physiological data obtained from a randomized household intervention trial that implemented sensor-based mHealth tools (pulse oximetry combined with a respiratory rate assessment app) to monitor health outcomes of 317 children (aged 6-36 months) that were visited weekly by 1 of 9 field workers in a rural Peruvian setting. The analysis focused on data integrity such as data completeness and signal quality. In addition, we performed a qualitative analysis of pretrial usability and semistructured posttrial interviews with a subset of app users (7 field workers and 7 health care center staff members) focusing on data integrity and reasons for loss thereof. Common themes were identified using a content analysis approach. Risk factors of each theme were detailed and then generalized and expanded into a checklist by reviewing 8 mHealth projects from the literature. An expert panel evaluated the checklist during 2 iterations until agreement between the 5 experts was achieved.

Results

Pulse oximetry signals were recorded in 78.36% (12,098/15,439) of subject visits where tablets were used. Signal quality decreased for 1 and increased for 7 field workers over time (1 excluded). Usability issues were addressed and the workflow was improved. Users considered the app easy and logical to use. In the qualitative analysis, we constructed a thematic map with the causes of low data integrity. We sorted them into 5 main challenge categories: environment, technology, user skills, user motivation, and subject engagement. The obtained categories were translated into detailed risk factors and presented in the form of an actionable checklist to evaluate possible implementation risks. By visually inspecting the checklist, open issues and sources for potential risks can be easily identified.

Conclusions

We developed a data integrity–based methodology to assess the potential challenges and risks of sensor-based mHealth projects. Aiming at improving data integrity, implementers can focus on the evaluation of environment, technology, user skills, user motivation, and subject engagement challenges. We provide a checklist to assist mHealth implementers with a structured evaluation protocol when planning and preparing projects.

Sinus or not: a new beat detection algorithm based on a pulse morphology quality index to extract normal sinus rhythm beats from wrist-worn photoplethysmography recordings

OBJECTIVE

Wrist-worn photoplethysmography (PPG) can enable free-living physiological monitoring of people during diverse activities, ranging from sleep to physical exercise. In many applications, it is important to remove the pulses not related to sinus rhythm beats from the PPG signal before using it as a cardiovascular descriptor. In this manuscript, we propose an algorithm to assess the morphology of the PPG signal in order to reject non-sinus rhythm pulses, such as artefacts or pulses related to arrhythmic beats.

APPROACH

The algorithm segments the PPG signal into individual pulses and dynamically evaluates their morphological likelihood of being normal sinus rhythm pulses via a template-matching approach that accounts for the physiological variability of the signal. The normal sinus rhythm likelihood of each pulse is expressed as a quality index that can be employed to reject artefacts and pulses related to arrhythmic beats.

MAIN RESULTS

Thresholding the pulse quality index enables near-perfect detection of normal sinus rhythm beats by rejecting most of the non-sinus rhythm pulses (positive predictive value 98%-99%), both in healthy subjects and arrhythmic patients. The rejection of arrhythmic beats is almost complete (sensitivity to arrhythmic beats 7%-3%), while the sensitivity to sinus rhythm beats is not compromised (96%-91%).

SIGNIFICANCE

The developed algorithm consistently detects normal sinus rhythm beats in a PPG signal by rejecting artefacts and, as a first of its kind, arrhythmic beats. This increases the reliability in the extraction of features which are adversely influenced by the presence of non-sinus pulses, whether related to inter-beat intervals or to pulse morphology, from wrist-worn PPG signals recorded in free-living conditions.

Adaptive template matching of photoplethysmogram pulses to detect motion artefact

OBJECTIVE

The photoplethysmography (PPG) signal, commonly used in the healthcare settings, is easily affected by movement artefact leading to errors in the extracted heart rate and SpO₂ estimates. This study aims to develop an online artefact detection system based on adaptive (dynamic) template matching, suitable for continuous PPG monitoring during daily living activities or in the intensive care units (ICUs).

APPROACH

Several master templates are initially generated by applying principal component analysis to data obtained from the PhysioNet MIMIC II database. The master template is then updated with each incoming clean PPG pulse. The correlation coefficient is used to classify the PPG pulse into either good or bad quality categories. The performance of our algorithm was evaluated using data obtained from two different sources: (i) our own data collected from 19 healthy subjects using the wearable Sotera Visi Mobile system (Sotera Wireless Inc.) as they performed various movement types; and (ii) ICU data provided by the PhysioNet MIMIC II database. The developed algorithm was evaluated against a manually annotated 'gold standard' (GS).

MAIN RESULTS

Our algorithm achieved an overall accuracy of 91.5%  ±  2.9%, with a sensitivity of 94.1%  ±  2.7% and a specificity of 89.7%  ±  5.1%, when tested on our own data. When applying the algorithm to data from the PhysioNet MIMIC II database, it achieved an accuracy of 98.0%, with a sensitivity and specificity of 99.0% and 96.1%, respectively.

SIGNIFICANCE

The proposed method is simple and robust against individual variations in the PPG characteristics, thus making it suitable for a diverse range of datasets. Integration of the proposed artefact detection technique into remote monitoring devices could enhance reliability of the PPG-derived physiological parameters.

Pediatric pulse oximetry-based OSA screening at different thresholds of the apnea-hypopnea index with an expression of uncertainty for inconclusive classifications

BACKGROUND

Assessments of pediatric obstructive sleep apnea (OSA) are underutilized across Canada due to a lack of resources. Polysomnography (PSG) measures OSA severity through the average number of apnea/hypopnea events per hour (AHI), but is resource intensive and requires a specialized sleep laboratory, which results in long waitlists and delays in OSA detection. Prompt diagnosis and treatment of OSA are crucial for children, as untreated OSA is linked to behavioral deficits, growth failure, and negative cardiovascular consequences. We aim to assess the performance of a portable pediatric OSA screening tool at different AHI cut-offs using overnight smartphone-based pulse oximetry.

MATERIAL AND METHODS

Following ethics approval and informed consent, children referred to British Columbia Children's Hospital for overnight PSG were recruited for two studies including 160 and 75 children, respectively. An additional smartphone-based pulse oximeter sensor was used in both studies to record overnight pulse oximetry [SpO₂ and photoplethysmogram (PPG)] alongside the PSG. Features characterizing SpO₂ dynamics and heart rate variability from pulse peak intervals of the PPG signal were derived from pulse oximetry recordings. Three multivariate logistic regression screening models, targeted at three different levels of OSA severity (AHI ≥ 1, 5, and 10), were developed using stepwise-selection of features using the Bayesian information criterion (BIC). The "Gray Zone" approach was also implemented for different tolerance values to allow for more precise detection of children with inconclusive classification results.

RESULTS

The optimal diagnostic tolerance values defining the "Gray Zone" borders (15, 10, and 5, respectively) were selected to develop the final models to screen for children at AHI cut-offs of 1, 5, and 10. The final models evaluated through cross-validation showed good accuracy (75%, 82% and 89%), sensitivity (80%, 85% and 82%) and specificity (65%, 79% and 91%) values for detecting children with AHI ≥ 1, AHI ≥ 5 and AHI ≥ 10. The percentage of children classified as inconclusive was 28%, 38% and 16% for models detecting AHI ≥ 1, AHI ≥ 5, and AHI ≥ 10, respectively.

CONCLUSIONS

The proposed pulse oximetry-based OSA screening tool at different AHI cut-offs may assist clinicians in identifying children at different OSA severity levels. Using this tool at home prior to PSG can help with optimizing the limited resources for PSG screening. Further validation with larger and more heterogeneous datasets is required before introducing in clinical practice.

Photoplethysmography beat detection and pulse morphology quality assessment for signal reliability estimation

Photoplethysmography (PPG) is one of the key technologies for unobtrusive physiological monitoring, with ongoing attempts to use it in several medical fields, ranging from night to night sleep analysis to continuous cardiac arrhythmia monitoring. However, the PPG signals are susceptible to be corrupted by noise and artifacts, caused, e.g., by limb or sensor movement. These artifacts affect the morphology of PPG waves and prevent the accurate detection and localization of beats and subsequent cardiovascular feature extraction. In this paper a new algorithm for beat detection and pulse quality assessment is described. The algorithm segments the PPG signal in pulses, localizes each beat and grades each segment with a quality index. The obtained index results from a comparison between each pulse and a template derived from the surrounding pulses, by mean of dynamic time warping barycenter averaging. The quality index is used to discard corrupted pulse beats. The algorithm is evaluated by comparing the detected beats with annotated PPG signals and the results are published over the same data. The described method achieves an improved sensitivity and a higher predictive value.

Assessing mental stress from the photoplethysmogram: a numerical study

OBJECTIVE

Mental stress is detrimental to cardiovascular health, being a risk factor for coronary heart disease and a trigger for cardiac events. However, it is not currently routinely assessed. The aim of this study was to identify features of the photoplethysmogram (PPG) pulse wave which are indicative of mental stress.

APPROACH

A numerical model of pulse wave propagation was used to simulate blood pressure signals, from which simulated PPG pulse waves were estimated using a transfer function. Pulse waves were simulated at six levels of stress by changing the model input parameters both simultaneously and individually, in accordance with haemodynamic changes associated with stress. Thirty-two feature measurements were extracted from pulse waves at three measurement sites: the brachial, radial and temporal arteries. Features which changed significantly with stress were identified using the Mann-Kendall monotonic trend test.

MAIN RESULTS

Seventeen features exhibited significant trends with stress in measurements from at least one site. Three features showed significant trends at all three sites: the time from pulse onset to peak, the time from the dicrotic notch to pulse end, and the pulse rate. More features showed significant trends at the radial artery (15) than the brachial (8) or temporal (7) arteries. Most features were influenced by multiple input parameters.

SIGNIFICANCE

The features identified in this study could be used to monitor stress in healthcare and consumer devices. Measurements at the radial artery may provide superior performance than the brachial or temporal arteries. In vivo studies are required to confirm these observations.

Computationally efficient algorithm for photoplethysmography-based atrial fibrillation detection using smartphones

Atrial fibrillation (AF) is one of the major causes of stroke, heart failure, sudden death, and cardiovascular morbidity and the most common type of arrhythmia. Its diagnosis and the initiation of treatment, however, currently requires electrocardiogram (ECG)-based heart rhythm monitoring. The photoplethysmogram (PPG) offers an alternative method, which is convenient in terms of its recording and allows for self-monitoring, thus relieving clinical staff and enabling early AF diagnosis. We introduce a PPG-based AF detection algorithm using smartphones that has a low computational cost and low memory requirements. In particular, we propose a modified PPG signal acquisition, explore new statistical discriminating features and propose simple classification equations by using sequential forward selection (SFS) and support vector machines (SVM). The algorithm is applied to clinical data and evaluated in terms of receiver operating characteristic (ROC) curve and statistical measures. The combination of Shannon entropy and the median of the peak rise height achieves perfect detection of AF on the recorded data, highlighting the potential of PPG for reliable AF detection.

SeismoWatch: Wearable Cuffless Blood Pressure Monitoring Using Pulse Transit Time

The current norm for measuring blood pressure (BP) at home is using an automated BP cuff based on oscillometry. Despite providing a viable and familiar method of tracking BP at home, oscillometric devices can be both cumbersome and inaccurate with the inconvenience of the hardware typically limiting measurements to once or twice per day. To address these limitations, a wrist-watch BP monitor was developed to measure BP through a simple maneuver: holding the watch against the sternum to detect micro-vibrations of the chest wall associated with the heartbeat. As a pulse wave propagates from the heart to the wrist, an accelerometer and optical sensor on the watch measure the travel time - pulse transit time (PTT) - to estimate BP. In this paper, we conducted a study to test the accuracy and repeatability of our device. After calibration, the diastolic pressure estimations reached a root-mean-square error of 2.9 mmHg. The watch-based system significantly outperformed (p<0.05) conventional pulse arrival time (PAT) based wearable blood pressure estimations - the most commonly used method for wearable BP sensing in the existing literature and commercial devices. Our device can be a convenient means for wearable BP monitoring outside of clinical settings in both health-conscious and hypertensive populations.1.

Identifying individual sleep apnea/hypoapnea epochs using smartphone-based pulse oximetry

Sleep apnea, characterized by frequent pauses in breathing during sleep, poses a serious threat to the healthy growth and development of children. Polysomnography (PSG), the gold standard for sleep apnea diagnosis, is resource intensive and confined to sleep laboratories, thus reducing its accessibility. Pulse oximetry alone, providing blood oxygen saturation (SpO2) and blood volume changes in tissue (PPG), has the potential to identify children with sleep apnea. Thus, we aim to develop a tool for at-home sleep apnea screening that provides a detailed and automated 30 sec epoch-by-epoch sleep apnea analysis. We propose to extract features characterizing pulse oximetry (SpO2 and pulse rate variability [PRV], a surrogate measure of heart rate variability) to create a multivariate logistic regression model that identifies epochs containing apnea/hypoapnea events. Overnight pulse oximetry was collected using a smartphone-based pulse oximeter, simultaneously with standard PSG from 160 children at the British Columbia Children's hospital. The sleep technician manually scored all apnea/hypoapnea events during the PSG study. Based on these scores we labeled each epoch as containing or not containing apnea/hypoapnea. We randomly divided the subjects into training data (40%), used to develop the model applying the LASSO method, and testing data (60%), used to validate the model. The developed model was assessed epoch-by-epoch for each subject. The test dataset had a median area under the receiver operating characteristic (ROC) curve of 81%; the model provided a median accuracy of 74% sensitivity of 75%, and specificity of 73% when using a risk threshold similar to the percentage of apnea/hypopnea epochs. Thus, providing a detailed epoch-by-epoch analysis with at-home pulse oximetry alone is feasible with accuracy, sensitivity and specificity values above 73% However, the performance might decrease when analyzing subjects with a low number of apnea/hypoapnea events.

Sleep Apnea Detection Based on Thoracic and Abdominal Movement Signals of Wearable Piezo-Electric Bands

Physiologically, the thoracic (THO) and abdominal (ABD) movement signals, captured using wearable piezo-electric bands, provide information about various types of apnea, including central sleep apnea (CSA) and obstructive sleep apnea (OSA). However, the use of piezo-electric wearables in detecting sleep apnea events has been seldom explored in the literature. This study explored the possibility of identifying sleep apnea events, including OSA and CSA, by solely analyzing one or both the THO and ABD signals. An adaptive non-harmonic model was introduced to model the THO and ABD signals, which allows us to design features for sleep apnea events. To confirm the suitability of the extracted features, a support vector machine was applied to classify three categories - normal and hypopnea, OSA, and CSA. According to a database of 34 subjects, the overall classification accuracies were on average 75.9%±11.7% and 73.8%±4.4%, respectively, based on the cross validation. When the features determined from the THO and ABD signals were combined, the overall classification accuracy became 81.8%±9.4%. These features were applied for designing a state machine for online apnea event detection. Two event-byevent accuracy indices, S and I, were proposed for evaluating the performance of the state machine. For the same database, the S index was 84.01%±9.06%, and the I index was 77.21%±19.01%. The results indicate the considerable potential of applying the proposed algorithm to clinical examinations for both screening and homecare purposes.

A Robust Motion Artifact Detection Algorithm for Accurate Detection of Heart Rates From Photoplethysmographic Signals Using Time-Frequency Spectral Features

Motion and noise artifacts (MNAs) impose limits on the usability of the photoplethysmogram (PPG), particularly in the context of ambulatory monitoring. MNAs can distort PPG, causing erroneous estimation of physiological parameters such as heart rate (HR) and arterial oxygen saturation (SpO2). In this study, we present a novel approach, "TifMA," based on using the time-frequency spectrum of PPG to first detect the MNA-corrupted data and next discard the nonusable part of the corrupted data. The term "nonusable" refers to segments of PPG data from which the HR signal cannot be recovered accurately. Two sequential classification procedures were included in the TifMA algorithm. The first classifier distinguishes between MNA-corrupted and MNA-free PPG data. Once a segment of data is deemed MNA-corrupted, the next classifier determines whether the HR can be recovered from the corrupted segment or not. A support vector machine (SVM) classifier was used to build a decision boundary for the first classification task using data segments from a training dataset. Features from time-frequency spectra of PPG were extracted to build the detection model. Five datasets were considered for evaluating TifMA performance: (1) and (2) were laboratory-controlled PPG recordings from forehead and finger pulse oximeter sensors with subjects making random movements, (3) and (4) were actual patient PPG recordings from UMass Memorial Medical Center with random free movements and (5) was a laboratory-controlled PPG recording dataset measured at the forehead while the subjects ran on a treadmill. The first dataset was used to analyze the noise sensitivity of the algorithm. Datasets 2-4 were used to evaluate the MNA detection phase of the algorithm. The results from the first phase of the algorithm (MNA detection) were compared to results from three existing MNA detection algorithms: the Hjorth, kurtosis-Shannon entropy, and time-domain variability-SVM approaches. This last is an approach recently developed in our laboratory. The proposed TifMA algorithm consistently provided higher detection rates than the other three methods, with accuracies greater than 95% for all data. Moreover, our algorithm was able to pinpoint the start and end times of the MNA with an error of less than 1 s in duration, whereas the next-best algorithm had a detection error of more than 2.2 s. The final, most challenging, dataset was collected to verify the performance of the algorithm in discriminating between corrupted data that were usable for accurate HR estimations and data that were nonusable. It was found that on average 48% of the data segments were found to have MNA, and of these, 38% could be used to provide reliable HR estimation.