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

Abstract

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.

Non-Invasive Detection of Mechanical Alternans Utilizing Photoplethysmography

“…Movement artifacts affect both the PPG and noninvasive BP. Although noise reduction in the PPG is an active field of study, sophisticated techniques of signal reconstruction during movement have focused on accurate estimations of heart rate [39], [40]. PPG motion artifact reduction remains a challenging task.…”

Enhancing the Robustness of Smartphone Photoplethysmography: A Signal Quality Index Approach

“…Third, there are many methods for improving smartphone PPG accuracy [27,[29][30][31][32][33]. For example, adding a suitable bandpass filter for signal processing [28] or excluding data with RR intervals that differ more than a certain threshold [70] are simple and effective approaches to reduce noise.…”

“…Given that smartphones with in-built cameras have become a part of modern life, using them to access health information is an ideal alternative when ECGs or similar medical devices are not available [26]. In addition, there have been several reported techniques for increasing the accuracy of smartphone PPG, such as point-of-interest selection [27], bandpass filtering [28], adaptive signal thresholding [29], motion detection techniques [30][31][32], interpolation techniques [33], and signal decomposition methods [34][35][36]. Bioengineering studies indicate that the average HR [37] and HRV measured using smartphone PPG are comparable with those measured using gold standard ECGs [21,28,[38][39][40].Although it is a promising solution for practical data collection and has an accuracy that has been well proved in several experiments, using smartphone PPG to measure HRV has received limited research attention in applied disciplines such as medicine or psychology [41]; a possible explanation is the lack of robustness in practical scenarios.…”

An Efficient Motion and Noise Artifacts Removal Method using GAIT and Machine Learning Model

“…Vital signs extraction along with the other physiological parameters, which is generated using the pulse oximetry, is already predicted on the given artifact free motion photoplethysmogram data. It is also known that photoplethysmogram signals are the high-sensitive data to the artifacts specially the one which is recorded when the patient were in motion [10] and this phenomena has the restricted use of the photoplethysmogram for application of ambulatory monitoring. Moreover, motion and noise artifacts also known as MNAs leads to the estimation of SPO2 and HR [10].…”

“…It is also known that photoplethysmogram signals are the high-sensitive data to the artifacts specially the one which is recorded when the patient were in motion [10] and this phenomena has the restricted use of the photoplethysmogram for application of ambulatory monitoring. Moreover, motion and noise artifacts also known as MNAs leads to the estimation of SPO2 and HR [10]. However the various sensors may be able to minimize the motion disturbance and it makes sure that sensor are placed securely and it is found that they are not enough capable for removing the MNA.…”