Photoplethysmograph signal reconstruction based on a novel hybrid motion artifact detection-reduction approach. Part I: Motion and noise artifact detection

A Novel Signal Restoration Method of Noisy Photoplethysmograms for Uninterrupted Health Monitoring

Health-tracking from photoplethysmography (PPG) signals is significantly hindered by motion artifacts (MAs). Although many algorithms exist to detect MAs, the corrupted signal often remains unexploited. This work introduces a novel method able to reconstruct noisy PPGs and facilitate uninterrupted health monitoring. The algorithm starts with spectral-based MA detection, followed by signal reconstruction by using the morphological and heart-rate variability information from the clean segments adjacent to noise. The algorithm was tested on (a) 30 noisy PPGs of a maximum 20 s noise duration and (b) 28 originally clean PPGs, after noise addition (2-120 s) (1) with and (2) without cancellation of the corresponding clean segment. Sampling frequency was 250 Hz after resampling. Noise detection was evaluated by means of accuracy, sensitivity, and specificity. For the evaluation of signal reconstruction, the heart-rate (HR) was compared via Pearson correlation (PC) and absolute error (a) between ECGs and reconstructed PPGs and (b) between original and reconstructed PPGs. Bland-Altman (BA) analysis for the differences in HR estimation on original and reconstructed segments of (b) was also performed. Noise detection accuracy was 90.91% for (a) and 99.38-100% for (b). For the PPG reconstruction, HR showed 99.31% correlation in (a) and >90% for all noise lengths in (b). Mean absolute error was 1.59 bpm for (a) and 1.26-1.82 bpm for (b). BA analysis indicated that, in most cases, 90% or more of the recordings fall within the confidence interval, regardless of the noise length. Optimal performance is achieved even for signals of noise up to 2 min, allowing for the utilization and further analysis of recordings that would otherwise be discarded. Thereby, the algorithm can be implemented in monitoring devices, assisting in uninterrupted health-tracking.

A Sliding Scale Signal Quality Metric of Photoplethysmography Applicable to Measuring Heart Rate across Clinical Contexts with Chest Mounting as a Case Study

Photoplethysmography (PPG) signal quality as a proxy for accuracy in heart rate (HR) measurement is useful in various public health contexts, ranging from short-term clinical diagnostics to free-living health behavior surveillance studies that inform public health policy. Each context has a different tolerance for acceptable signal quality, and it is reductive to expect a single threshold to meet the needs across all contexts. In this study, we propose two different metrics as sliding scales of PPG signal quality and assess their association with accuracy of HR measures compared to a ground truth electrocardiogram (ECG) measurement.

METHODS

We used two publicly available PPG datasets (BUT PPG and Troika) to test if our signal quality metrics could identify poor signal quality compared to gold standard visual inspection. To aid interpretation of the sliding scale metrics, we used ROC curves and Kappa values to calculate guideline cut points and evaluate agreement, respectively. We then used the Troika dataset and an original dataset of PPG data collected from the chest to examine the association between continuous metrics of signal quality and HR accuracy. PPG-based HR estimates were compared with reference HR estimates using the mean absolute error (MAE) and the root-mean-square error (RMSE). Point biserial correlations were used to examine the association between binary signal quality and HR error metrics (MAE and RMSE).

RESULTS

ROC analysis from the BUT PPG data revealed that the AUC was 0.758 (95% CI 0.624 to 0.892) for signal quality metrics of STD-width and 0.741 (95% CI 0.589 to 0.883) for self-consistency. There was a significant correlation between criterion poor signal quality and signal quality metrics in both Troika and originally collected data. Signal quality was highly correlated with HR accuracy (MAE and RMSE, respectively) between PPG and ground truth ECG.

CONCLUSION

This proof-of-concept work demonstrates an effective approach for assessing signal quality and demonstrates the effect of poor signal quality on HR measurement. Our continuous signal quality metrics allow estimations of uncertainties in other emergent metrics, such as energy expenditure that relies on multiple independent biometrics. This open-source approach increases the availability and applicability of our work in public health settings.

Artifacts classification and apnea events detection in neck photoplethysmography signals

The novel pulse oximetry measurement site of the neck is a promising location for multi-modal physiological monitoring. Specifically, in the context of respiratory monitoring, in which it is important to have direct information about airflow. The neck makes this possible, in contrast to common photoplethysmography (PPG) sensing sites. However, this PPG signal is susceptible to artifacts that critically impair the signal quality. To fully exploit neck PPG for reliable physiological parameters extraction and apneas monitoring, this paper aims to develop two classification algorithms for artifacts and apnea detection. Features from the time, correlogram, and frequency domains were extracted. Two SVM classifiers with RBF kernels were trained for different window (W) lengths and thresholds (Thd) of corruption. For artifacts classification, the maximum performance was attained for the parameters combination of [W = 6s-Thd= 20%], with an average accuracy= 85.84%(ACC), sensitivity= 85.43%(SE) and specificity= 86.26%(SP). For apnea detection, the model [W = 10s-Thd= 50%] maximized all the performance metrics significantly (ACC= 88.25%, SE= 89.03%, SP= 87.42%). The findings of this proof of concept are significant for denoising novel neck PPG signals, and demonstrate, for the first time, that it is possible to promptly detect apnea events from neck PPG signals in an instantaneous manner. This could make a big impact in crucial real-time applications, like devices to prevent sudden-unexpected-death-in-epilepsy (SUDEP).

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.

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.

Non-Contact HR Monitoring via Smartphone and Webcam During Different Respiratory Maneuvers and Body Movements

As a reliable indicator for individual's healthiness conditions, heart rate (HR) has been widely considered and used. Imaging photoplethysmography (iPPG) is recently highlighted as a promising HR measurement method, due to its non-contact characteristics, by extracting the HR from facial video recordings. In this study, we propose a camera-based HR monitoring technique that estimates HR information from iPPG signals extracted from a video sequence. Videos were recorded using a smartphone or a laptop camera. We adopted the plane-orthogonal-to-skin (POS) method to compute iPPG. The proposed method is evaluated by applying it to extract HR of 9 subjects at rest and during two motion conditions (lateral and frontal) while they were performing several respiratory maneuvers-spontaneous, metronome, and forced. Automatic face detection algorithms were implemented in the proposed method. Our experimental results show that mean values of HR have 0.56% error and 99.4% accuracy when compared to HR calculated from the gold-standard electrocardiography (ECG) reference in diverse conditions of motions and respiratory maneuvers.

SmartFit: Smartphone Application for Garment Fit Detection

The apparel e-commerce industry is growing day by day. In recent times, consumers are particularly interested in an easy and time-saving way of online apparel shopping. In addition, the COVID-19 pandemic has generated more need for an effective and convenient online shopping solution for consumers. However, online shopping, particularly online apparel shopping, has several challenges for consumers. These issues include sizing, fit, return, and cost concerns. Especially, the fit issue is one of the cardinal factors causing hesitance and drawback in online apparel purchases. The conventional method of clothing fit detection based on body shapes relies upon manual body measurements. Since no convenient and easy-to-use method has been proposed for body shape detection, we propose an interactive smartphone application, “SmartFit”, that will provide the optimal fitting clothing recommendation to the consumer by detecting their body shape. This optimal recommendation is provided by using image processing and machine learning that are solely dependent on smartphone images. Our preliminary assessment of the developed model shows an accuracy of 87.50% for body shape detection, producing a promising solution to the fit detection problem persisting in the digital apparel market.

Detection and Characterization of Physical Activity and Psychological Stress from Wristband Data

Wearable devices continuously measure multiple physiological variables to inform users of health and behavior indicators. The computed health indicators must rely on informative signals obtained by processing the raw physiological variables with powerful noise- and artifacts-filtering algorithms. In this study, we aimed to elucidate the effects of signal processing techniques on the accuracy of detecting and discriminating physical activity (PA) and acute psychological stress (APS) using physiological measurements (blood volume pulse, heart rate, skin temperature, galvanic skin response, and accelerometer) collected from a wristband. Data from 207 experiments involving 24 subjects were used to develop signal processing, feature extraction, and machine learning (ML) algorithms that can detect and discriminate PA and APS when they occur individually or concurrently, classify different types of PA and APS, and estimate energy expenditure (EE). Training data were used to generate feature variables from the physiological variables and develop ML models (naïve Bayes, decision tree, k-nearest neighbor, linear discriminant, ensemble learning, and support vector machine). Results from an independent labeled testing data set demonstrate that PA was detected and classified with an accuracy of 99.3%, and APS was detected and classified with an accuracy of 92.7%, whereas the simultaneous occurrences of both PA and APS were detected and classified with an accuracy of 89.9% (relative to actual class labels), and EE was estimated with a low mean absolute error of 0.02 metabolic equivalent of task (MET).The data filtering and adaptive noise cancellation techniques used to mitigate the effects of noise and artifacts on the classification results increased the detection and discrimination accuracy by 0.7% and 3.0% for PA and APS, respectively, and by 18% for EE estimation. The results demonstrate the physiological measurements from wristband devices are susceptible to noise and artifacts, and elucidate the effects of signal processing and feature extraction on the accuracy of detection, classification, and estimation of PA and APS.

Optical difference in the frequency domain to suppress disturbance for wearable electronics

Measurements based on optics offer a wide range of unprecedented opportunities in the biological application due to the noninvasive or non-destructive detection. Wearable skin-like optoelectronic devices, capable of deforming with the human skin, play significant roles in future biomedical engineering such as clinical diagnostics or daily healthcare. However, the detected signals based on light intensity are very sensitive to the light path. The performance degradation of the wearable devices occurs due to device deformation or motion artifact. In this work, we propose the optical difference in the frequency domain of signals for suppressing the disturbance generated by wearable device deformation or motion artifact during the photoplethysmogram (PPG) monitoring. The signal processing is simulated with different input waveforms for analyzing the performance of this method. Then we design and fabricate a wearable optoelectronic device to monitor the PPG signal in the condition of motion artifact and use the optical difference in the frequency domain of signals to suppress irregular disturbance. The proposed method reduced the average error in heart rate estimation from 13.04 beats per minute (bpm) to 3.41 bpm in motion and deformation situations. These consequences open up a new prospect for improving the performance of the wearable optoelectronic devices and precise medical monitoring in the future.

Robust PPG motion artifact detection using a 1-D convolution neural network

BACKGROUND AND OBJECTIVES

Continuous monitoring of physiological parameters such as photoplethysmography (PPG) has attracted increased interest due to advances in wearable sensors. However, PPG recordings are susceptible to various artifacts, and thus reducing the reliability of PPG-driven parameters, such as oxygen saturation, heart rate, blood pressure and respiration. This paper proposes a one-dimensional convolution neural network (1-D-CNN) to classify five-second PPG segments into clean or artifact-affected segments, avoiding data-dependent pulse segmentation techniques and heavy manual feature engineering.

METHODS

Continuous raw PPG waveforms were blindly allocated into segments with an equal length (5s) without leveraging any pulse location information and were normalized with Z-score normalization methods. A 1-D-CNN was designed to automatically learn the intrinsic features of the PPG waveform, and perform the required classification. Several training hyperparameters (initial learning rate and gradient threshold) were varied to investigate the effect of these parameters on the performance of the network. Subsequently, this proposed network was trained and validated with 30 subjects, and then tested with eight subjects, with our local dataset. Moreover, two independent datasets downloaded from the PhysioNet MIMIC II database were used to evaluate the robustness of the proposed network.

RESULTS

A 13 layer 1-D-CNN model was designed. Within our local study dataset evaluation, the proposed network achieved a testing accuracy of 94.9%. The classification accuracy of two independent datasets also achieved satisfactory accuracy of 93.8% and 86.7% respectively. Our model achieved a comparable performance with most reported works, with the potential to show good generalization as the proposed network was evaluated with multiple cohorts (overall accuracy of 94.5%).

CONCLUSION

This paper demonstrated the feasibility and effectiveness of applying blind signal processing and deep learning techniques to PPG motion artifact detection, whereby manual feature thresholding was avoided and yet a high generalization ability was achieved.

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.

Emerging Technologies for Identifying Atrial Fibrillation

Atrial fibrillation (AF) is a major cause of morbidity and mortality globally, and much of this is driven by challenges in its timely diagnosis and treatment. Existing and emerging mobile technologies have been used to successfully identify AF in a variety of clinical and community settings, and while these technologies offer great promise for revolutionizing AF detection and screening, several major barriers may impede their effectiveness. The unclear clinical significance of device-detected AF, potential challenges in integrating patient-generated data into existing healthcare systems and clinical workflows, harm resulting from potential false positives, and identifying the appropriate scope of population-based screening efforts are all potential concerns that warrant further investigation. It is crucial for stakeholders such as healthcare providers, researchers, funding agencies, insurers, and engineers to actively work together in fulfilling the tremendous potential of mobile technologies to improve AF identification and management on a population level.

Smartwatch Based Atrial Fibrillation Detection from Photoplethysmography Signals

Atrial fibrillation (AF) detection from wristwatch is important as it can lead to non-invasive, long-term and continuous monitoring of AF from photoplethysmogram (PPG) signal. In this paper, we propose a novel method not only to detect AF from wristwatch PPG, but also to automatically distinguish between clean and corrupted PPG segments. We use accelerometer data as well as variable frequency complex demodulation based time-frequency analysis of the PPG signal to detect motion and noise artifacts in the PPG signal waveform. Next, root mean square of successive differences and sample entropy are extracted from the beat-to-beat intervals of the clean detected PPG signals, which we use to separate AF from normal sinus rhythm. UMass dataset consisting of 20 subjects has been used in this study to test the efficacy of the proposed algorithm. Our method achieves sensitivity, specificity and accuracy of 96.15%, 97.37% and 97.11%, respectively, which shows the potential of a practical and reliable AF monitoring scheme.

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.

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.

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.

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.

Accuracy and Usability of a Novel Algorithm for Detection of Irregular Pulse Using a Smartwatch Among Older Adults: Observational Study

BACKGROUND

Atrial fibrillation (AF) is often paroxysmal and minimally symptomatic, hindering its diagnosis. Smartwatches may enhance AF care by facilitating long-term, noninvasive monitoring.

OBJECTIVE

This study aimed to examine the accuracy and usability of arrhythmia discrimination using a smartwatch.

METHODS

A total of 40 adults presenting to a cardiology clinic wore a smartwatch and Holter monitor and performed scripted movements to simulate activities of daily living (ADLs). Participants' clinical and sociodemographic characteristics were abstracted from medical records. Participants completed a questionnaire assessing different domains of the device's usability. Pulse recordings were analyzed blindly using a real-time realizable algorithm and compared with gold-standard Holter monitoring.

RESULTS

The average age of participants was 71 (SD 8) years; most participants had AF risk factors and 23% (9/39) were in AF. About half of the participants owned smartphones, but none owned smartwatches. Participants wore the smartwatch for 42 (SD 14) min while generating motion noise to simulate ADLs. The algorithm determined 53 of the 314 30-second noise-free pulse segments as consistent with AF. Compared with the gold standard, the algorithm demonstrated excellent sensitivity (98.2%), specificity (98.1%), and accuracy (98.1%) for identifying irregular pulse. Two-thirds of participants considered the smartwatch highly usable. Younger age and prior cardioversion were associated with greater overall comfort and comfort with data privacy with using a smartwatch for rhythm monitoring, respectively.

CONCLUSIONS

A real-time realizable algorithm analyzing smartwatch pulse recordings demonstrated high accuracy for identifying pulse irregularities among older participants. Despite advanced age, lack of smartwatch familiarity, and high burden of comorbidities, participants found the smartwatch to be highly acceptable.

Current progress of photoplethysmography and SPO2 for health monitoring

A photoplethysmograph (PPG) is a simple medical device for monitoring blood flow and transportation of substances in the blood. It consists of a light source and a photodetector for measuring transmitted and reflected light signals. Clinically, PPGs are used to monitor the pulse rate, oxygen saturation, blood pressure, and blood vessel stiffness. Wearable unobtrusive PPG monitors are commercially available. Here, we review the principle issues and clinical applications of PPG for monitoring oxygen saturation.

A Novel Personalized Motion and Noise Artifact (MNA) Detection Method for Smartphone Photoplethysmograph (PPG) Signals

Photoplethysmography (PPG) is a technique to detect blood volume changes in an optical way. Representative PPG applications are the measurements of oxygen saturation, heart rate, and respiratory rate. However, PPG signals are sensitive to motion and noise artifacts (MNAs) especially when they are obtained from smartphone cameras. Moreover, PPG signals are different among users and each individual's PPG signal has a unique characteristic. Hence, an effective MNA detection and reduction method for smartphone PPG signals, which adapts itself to each user in a personalized way, is highly demanded. Here, a concept of the probabilistic neural network (PNN) is introduced to be used with the proposed extracted parameters. The signal amplitude, standard deviation of peak to peak time intervals and amplitudes, along with the mean of moving standard deviation, signal slope changes, and the optimal autoregressive (AR) model order are proposed for effective MNA detection. Accordingly, the performance of the proposed personalized algorithm is compared with conventional MNA detection algorithms. As performance metrics, we considered accuracy, sensitivity, and specificity. The results show that the overall performance of the personalized MNA detection is enhanced compared to the generalized algorithm. The average values of the accuracy, sensitivity and specificity of the personalized one are 98.07%, 92.6%, and 99.78%, respectively, while these are 89.92%, 84.21%, and 93.63% for the general one.

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.

Quantifying Movement in Preterm Infants Using Photoplethysmography

Long-term recordings of movement in preterm infants might reveal important clinical information. However, measurement of movement is limited because of time-consuming and subjective analysis of video or reluctance to attach additional sensors to the infant. We evaluated whether photoplethysmogram (PPG), routinely used for oximetry in preterm infants in the neonatal intensive care unit (NICU), can provide reliable long-term measurements of movement. In 18 infants [mean post-conceptional age (PCA) 31.10 weeks, range 29-34.29 weeks], we designed and tested a wavelet-based algorithm that detects movement signals from the PPG. The algorithm's performance was optimized relative to subjective assessments of movement using video and accelerometers attached to two limbs and force sensors embedded within the mattress (five infants, three raters). We then applied the optimized algorithm to infants receiving routine care in the NICU without additional sensors. The algorithm revealed a decline in brief movements (< 5 s) with increasing PCA (13 infants, r = - 0.87, p < 0.001, PCA range 27.3-33.9 weeks). Our findings suggest that quantitative relationships between motor activity and clinical outcomes in preterm infants can be studied using routine photoplethysmography.

Evaluation of key design parameters for mitigating motion artefact in the mobile reflectance PPG signal to improve estimation of arterial oxygenation

OBJECTIVE

Pulse oximetry, a widely accepted method for non-invasive estimation of arterial oxygen saturation (SpO₂) and pulse rate (PR), is increasingly being adapted for mobile applications. Previous work in mitigating motion artefact, which corrupts the photoplethysmogram (PPG) used in pulse oximetry, has focused on reducing noise using signal processing algorithms or through sensor design that controlled only one variable at a time. In this work, we have investigated the effect of several variables such as sensor weight, relative motion, placement, and contact force against the skin that can impact motion artefact independently or by interacting with each other.

APPROACH

We have identified a unique combination of these variables that is most optimal in reducing motion artefacts using a full factorial design of experiments methodology and evaluated the effect of these factors on PPG readings with and without motion.

MAIN RESULTS

Data collected on 10 diverse subjects showed that placement (p  =  0.03), contact force (p  =  0.004), and sensor-to-skin adhesion or relative motion when combined with force (p  <  0.001) had the most significant effect on reducing the motion artefact signal. Sensor weight (p  =  0.822) by itself had no significant effect, however when combined with sensor adhesion (p  <  0.001) had a significant impact.

SIGNIFICANCE

This lays the foundation for future development of more robust sensors that can significantly reduce the effect of motion artefacts in reflectance-based pulse oximetry and could have great clinical value due to significant reduction of SpO₂ errors and false alarms associated with motion artefact, making wearable pulse oximetry more reliable in mobile applications.

Automated Method for Discrimination of Arrhythmias Using Time, Frequency, and Nonlinear Features of Electrocardiogram Signals

We developed an automated approach to differentiate between different types of arrhythmic episodes in electrocardiogram (ECG) signals, because, in real-life scenarios, a software application does not know in advance the type of arrhythmia a patient experiences. Our approach has four main stages: (1) Classification of ventricular fibrillation (VF) versus non-VF segments—including atrial fibrillation (AF), ventricular tachycardia (VT), normal sinus rhythm (NSR), and sinus arrhythmias, such as bigeminy, trigeminy, quadrigeminy, couplet, triplet—using four image-based phase plot features, one frequency domain feature, and the Shannon entropy index. (2) Classification of AF versus non-AF segments. (3) Premature ventricular contraction (PVC) detection on every non-AF segment, using a time domain feature, a frequency domain feature, and two features that characterize the nonlinearity of the data. (4) Determination of the PVC patterns, if present, to categorize distinct types of sinus arrhythmias and NSR. We used the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia database, Creighton University’s VT arrhythmia database, the MIT-BIH atrial fibrillation database, and the MIT-BIH malignant ventricular arrhythmia database to test our algorithm. Binary decision tree (BDT) and support vector machine (SVM) classifiers were used in both stage 1 and stage 3. We also compared our proposed algorithm’s performance to other published algorithms. Our VF detection algorithm was accurate, as in balanced datasets (and unbalanced, in parentheses) it provided an accuracy of 95.1% (97.1%), sensitivity of 94.5% (91.1%), and specificity of 94.2% (98.2%). The AF detection was accurate, as the sensitivity and specificity in balanced datasets (and unbalanced, in parentheses) were found to be 97.8% (98.6%) and 97.21% (97.1%), respectively. Our PVC detection algorithm was also robust, as the accuracy, sensitivity, and specificity were found to be 99% (98.1%), 98.0% (96.2%), and 98.4% (99.4%), respectively, for balanced and (unbalanced) datasets.

Motion and Noise Artifact-Resilient Atrial Fibrillation Detection using a Smartphone

We have recently found that our previously-developed atrial fibrillation (AF) detection algorithm for smartphones can give false positives when subjects' fingers or hands move, as we rely on proper finger placement over the smartphone camera to collect the signal of interest. Specifically, smartphone camera pulsatile signals that are obtained from normal sinus rhythm (NSR) subjects but are corrupted by motion and noise artifacts (MNAs) are frequently detected as AF. AF and motion-corrupted episodes have the similar characteristic that pulse-to-pulse intervals (PPIs) are irregular. We have developed an MNA-resilient smartphone-based AF detection algorithm that first discriminates and eliminates MNA-corrupted episodes in smartphone camera recordings, and then detects AF in MNA-free recordings. We found that MNA-corrupted episodes have highly-varying pulse slope, large turning point ratio, or large kurtosis values in smartphone signals compared to MNA-free AF and NSR episodes. We first use these three metrics for MNA discrimination and exclusion. Then, AF is detected in MNA-free signals using our previous algorithm. The capability to discriminate MNAs and AFs separately in smartphone signals increases the specificity of AF detection. To evaluate the performance of the proposed MNA-resilient AF algorithm, 99 subjects, including 88 study participants with AF at baseline and in NSR after electrical cardioversion as well as 11 participants with MNA-corrupted NSR, were recruited. Using iPhone 4S, 5S, and 6S models, we collected 2-minute pulsatile time series from each subject. The clinical results show that the accuracy, sensitivity and specificity of the proposed AF algorithm are 0.97, 0.98, 0.97, respectively, which are higher than those of the previous AF algorithm.

OxiMA: A Frequency-Domain Approach to Address Motion Artifacts in Photoplethysmograms for Improved Estimation of Arterial Oxygen Saturation and Pulse Rate

OBJECTIVE

The purpose of this paper is to demonstrate that a new algorithm for estimating arterial oxygen saturation can be effective even with data corrupted by motion artifacts (MAs).

METHODS

OxiMA, an algorithm based on the time-frequency components of a photoplethysmogram (PPG), was evaluated using 22-min datasets recorded from 10 subjects during voluntarily-induced hypoxia, with and without subject-induced MAs. A Nellcor OxiMax transmission sensor was used to collect an analog PPG while reference oxygen saturation and pulse rate (PR) were collected simultaneously from an FDA-approved Masimo SET Radical RDS-1 pulse oximeter.

RESULTS

The performance of our approach was determined by computing the mean relative error between the PR/oxygen saturation estimated by OxiMA and the reference Masimo oximeter. The average estimation error using OxiMA was 3 beats/min for PR and 3.24% for oxygen saturation, respectively.

CONCLUSION

The results show that OxiMA has great potential for improving the accuracy of PR and oxygen saturation estimation during MAs.

SIGNIFICANCE

This is the first study to demonstrate the feasibility of a reconstruction algorithm to improve oxygen saturation estimates on a dataset with MAs and concomitant hypoxia.

Using support vector machines on photoplethysmographic signals to discriminate between hypovolemia and euvolemia

Identifying trauma patients at risk of imminent hemorrhagic shock is a challenging task in intraoperative and battlefield settings given the variability of traditional vital signs, such as heart rate and blood pressure, and their inability to detect blood loss at an early stage. To this end, we acquired N = 58 photoplethysmographic (PPG) recordings from both trauma patients with suspected hemorrhage admitted to the hospital, and healthy volunteers subjected to blood withdrawal of 0.9 L. We propose four features to characterize each recording: goodness of fit (r²), the slope of the trend line, percentage change, and the absolute change between amplitude estimates in the heart rate frequency range at the first and last time points. Also, we propose a machine learning algorithm to distinguish between blood loss and no blood loss. The optimal overall accuracy of discriminating between hypovolemia and euvolemia was 88.38%, while sensitivity and specificity were 88.86% and 87.90%, respectively. In addition, the proposed features and algorithm performed well even when moderate blood volume was withdrawn. The results suggest that the proposed features and algorithm are suitable for the automatic discrimination between hypovolemia and euvolemia, and can be beneficial and applicable in both intraoperative/emergency and combat casualty care.

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.

Cardiac signal estimation based on the arterial and venous pressure signals of a hemodialysis machine

Continuous cardiac monitoring is usually not performed during hemodialysis treatment, although a majority of patients with kidney failure suffer from cardiovascular disease. In the present paper, a method is proposed for estimating a cardiac pressure signal by combining the arterial and the venous pressure sensor signals of the hemodialysis machine. The estimation is complicated by the periodic pressure disturbance caused by the peristaltic blood pump, with an amplitude much larger than that of the cardiac pressure signal. Using different techniques for combining the arterial and venous pressure signals, the performance is evaluated and compared to that of an earlier method which made use of the venous pressure only. The heart rate and the heartbeat occurrence times, determined from the estimated cardiac pressure signal, are compared to the corresponding quantities determined from a photoplethysmographic reference signal. Signals from 9 complete hemodialysis treatments were analyzed. For a heartbeat amplitude of 0.5 mmHg, the median absolute deviation between estimated and reference heart rate was 1.3 bpm when using the venous pressure signal only, but dropped to 0.6 bpm when combining the pressure signals. The results show that the proposed method offers superior estimation at low heartbeat amplitudes. Consequently, more patients can be successfully monitored during treatment without the need of extra sensors. The results are preliminary, and need to be verified on a separate dataset.

Detection of artifacts on photoplethysmography signals using random distortion testing

In this work, we describe a novel method based on waveform morphology for detecting artifacts in photoplethysmography (PPG) signals and, thus, improve reliability of PPG. By considering inter-individual and measure condition variability, specific parameters are estimated for each record. We introduce a novel metric for comparing pulses, which is the derivative of the correlation coefficient. Then, we propose a detection method based on Random Distortion Testing (RDT), to perform adaptive threasholding for each record. The results show that the proposed method provides pertinent detection of pulses with artifacts. Tested on 104 PPG records, the mean of sensitivity, specificity and accuracy were 84 ± 16%, 83 ± 12% and 83 ± 8%, respectively.

Improving Pulse Rate Measurements during Random Motion Using a Wearable Multichannel Reflectance Photoplethysmograph

Photoplethysmographic (PPG) waveforms are used to acquire pulse rate (PR) measurements from pulsatile arterial blood volume. PPG waveforms are highly susceptible to motion artifacts (MA), limiting the implementation of PR measurements in mobile physiological monitoring devices. Previous studies have shown that multichannel photoplethysmograms can successfully acquire diverse signal information during simple, repetitive motion, leading to differences in motion tolerance across channels. In this paper, we investigate the performance of a custom-built multichannel forehead-mounted photoplethysmographic sensor under a variety of intense motion artifacts. We introduce an advanced multichannel template-matching algorithm that chooses the channel with the least motion artifact to calculate PR for each time instant. We show that for a wide variety of random motion, channels respond differently to motion artifacts, and the multichannel estimate outperforms single-channel estimates in terms of motion tolerance, signal quality, and PR errors. We have acquired 31 data sets consisting of PPG waveforms corrupted by random motion and show that the accuracy of PR measurements achieved was increased by up to 2.7 bpm when the multichannel-switching algorithm was compared to individual channels. The percentage of PR measurements with error ≤ 5 bpm during motion increased by 18.9% when the multichannel switching algorithm was compared to the mean PR from all channels. Moreover, our algorithm enables automatic selection of the best signal fidelity channel at each time point among the multichannel PPG data.

An Algorithm for Real-Time Pulse Waveform Segmentation and Artifact Detection in Photoplethysmograms

Photoplethysmography has been used in a wide range of medical devices for measuring oxygen saturation, cardiac output, assessing autonomic function, and detecting peripheral vascular disease. Artifacts can render the photoplethysmogram (PPG) useless. Thus, algorithms capable of identifying artifacts are critically important. However, the published PPG algorithms are limited in algorithm and study design. Therefore, the authors developed a novel embedded algorithm for real-time pulse waveform (PWF) segmentation and artifact detection based on a contour analysis in the time domain. This paper provides an overview about PWF and artifact classifications, presents the developed PWF analysis, and demonstrates the implementation on a 32-bit ARM core microcontroller. The PWF analysis was validated with data records from 63 subjects acquired in a sleep laboratory, ergometry laboratory, and intensive care unit in equal parts. The output of the algorithm was compared with harmonized experts' annotations of the PPG with a total duration of 31.5 h. The algorithm achieved a beat-to-beat comparison sensitivity of 99.6%, specificity of 90.5%, precision of 98.5%, and accuracy of 98.3%. The interrater agreement expressed as Cohen's kappa coefficient was 0.927 and as F-measure was 0.990. In conclusion, the PWF analysis seems to be a suitable method for PPG signal quality determination, real-time annotation, data compression, and calculation of additional pulse wave metrics such as amplitude, duration, and rise time.

Real alerts and artifact classification in archived multi-signal vital sign monitoring data: implications for mining big data

Huge hospital information system databases can be mined for knowledge discovery and decision support, but artifact in stored non-invasive vital sign (VS) high-frequency data streams limits its use. We used machine-learning (ML) algorithms trained on expert-labeled VS data streams to automatically classify VS alerts as real or artifact, thereby "cleaning" such data for future modeling. 634 admissions to a step-down unit had recorded continuous noninvasive VS monitoring data [heart rate (HR), respiratory rate (RR), peripheral arterial oxygen saturation (SpO₂) at 1/20 Hz, and noninvasive oscillometric blood pressure (BP)]. Time data were across stability thresholds defined VS event epochs. Data were divided Block 1 as the ML training/cross-validation set and Block 2 the test set. Expert clinicians annotated Block 1 events as perceived real or artifact. After feature extraction, ML algorithms were trained to create and validate models automatically classifying events as real or artifact. The models were then tested on Block 2. Block 1 yielded 812 VS events, with 214 (26 %) judged by experts as artifact (RR 43 %, SpO₂ 40 %, BP 15 %, HR 2 %). ML algorithms applied to the Block 1 training/cross-validation set (tenfold cross-validation) gave area under the curve (AUC) scores of 0.97 RR, 0.91 BP and 0.76 SpO₂. Performance when applied to Block 2 test data was AUC 0.94 RR, 0.84 BP and 0.72 SpO₂. ML-defined algorithms applied to archived multi-signal continuous VS monitoring data allowed accurate automated classification of VS alerts as real or artifact, and could support data mining for future model building.