Photoplethysmographic Pulse Quality Assessment Methods Based on Similarity Analysis

Seok, Hyeon Seok; Han, Sangjin; Park, Junyung; Roh, Donggeun; Shin, Hyunki

doi:10.1109/scis-isis.2018.00067

Cited by 4 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Manual annotation [51][52][53][54] Guided By rules [55,56] By reference signal [35,[57][58][59] Perturbations artificially created during recording PR = Pulse Rate, HR = Heart Rate, ECG = Electrocardiogram, cPPG = Contact Photoplethysmography.…”

Section: References Detailsmentioning

confidence: 99%

“…The difference is based on how the pulses are selected for the building of the template (Li et al [65] used all pulses in a 30 s windows, while Karlen et al [43] preselected the pulses by performing normalized cross-correlation) and how the signals are aligned ( [46,77,78] applied dynamic time warping (DTW) for the alignment of the pulses that [80] used to build the template; John et al [76] first spotted a portion of signal presenting interest points and then iterated over the signal to find aligned portions of signals to add to the template). Comparing the template with new pulses is mainly done with the correlation [43,65,70,79] and the DTW distance [53,65,77,78]. Sabeti et al [46] made a comparison using the Kullback-Leibler divergence, while John et al [76] suggested a more original way to compare the signals by first computing a point-to-point difference between the template and the signal and then computing the variance of the obtained signal.…”

Section: Stability Of the Ppg Waveformmentioning

confidence: 99%

“…Data Performance [68] 13 subjects Cohen's κ = 0.64 8 records of 1 min per subject Sen = 0.89 Spe = 0.77 Acc = 0.83 [58] 24 subjects Acc = 0.888 >134 min of recording Sen = 0.869 Spe = 0.983 [43] Capnobase [83] 90% of the signals with artifacts had a score Complex System Laboratory [84] below 95/100 14% of good-quality signals are labelled as artifacts for a score below 85/100 [65] MIMIC II [82] Evaluation by the impact on false alarm reduction with suppression [70] Physionet/CinC 2011 Sen = 0.91 + author-collected database Spe = 0.95 [44,45] 63 subjects Performance of extended algorithm: 31.5 h of annotated signals Acc = 0.984 Sen = 0.995 Spe = 0.916 Pre = 0.986 [77] Capnobase [83] Performance on Capnobase Complex System Laboratory [84] for a threshold of 0.8: Sen = 0.9664 PPV = 0.9926 [81] 19 subjects (>5 min per record) Mean performance (over authors' dataset): + PhysioNet MIMIC II Acc = 0.935 Sen = 0.869 Spe = 0.902 [53] 3 subjects Best performance: 6 min records Acc = 0.9258 Sen = 0.9297 Spe = 0.9218 PPV = 0.9225 [48] 14 subjects Classification performance: 158 records of 10 s Acc = 0.9268 Sen = 0.9286 Spe = 0.9245 Pre = 0.6420 F1-score = 0.9353 [79] Capnobase [83] Sen = 0.9466 Complex System Laboratory PPV = 0.9678 [66] 15,000 records of 5 s from 3 different devices Acc = 0.9321 + MIMIC II [82] + Complex System Sen = 0.9822 Laboratory [84] + Wrist [85] + Cup [86] Spe = 0.9071…”

Section: Referencementioning

confidence: 99%

See 2 more Smart Citations

A Survey of Photoplethysmography and Imaging Photoplethysmography Quality Assessment Methods

et al. 2022

View full text Add to dashboard Cite

Photoplethysmography is a method to visualize the variation in blood volume within tissues with light. The signal obtained has been used for the monitoring of patients, interpretation for diagnosis or for extracting other physiological variables (e.g., pulse rate and blood oxygen saturation). However, the photoplethysmography signal can be perturbed by external and physiological factors. Implementing methods to evaluate the quality of the signal allows one to avoid misinterpretation while maintaining the performance of its applications. This paper provides an overview on signal quality index algorithms applied to photoplethysmography. We try to provide a clear view on the role of a quality index and its design. Then, we discuss the challenges arising in the quality assessment of imaging photoplethysmography.

show abstract

Section: References Detailsmentioning

confidence: 99%

Section: Stability Of the Ppg Waveformmentioning

confidence: 99%

Section: Referencementioning

confidence: 99%

See 1 more Smart Citation

A Survey of Photoplethysmography and Imaging Photoplethysmography Quality Assessment Methods

et al. 2022

View full text Add to dashboard Cite

show abstract

A LSTM-Based Realtime Signal Quality Assessment for Photoplethysmogram and Remote Photoplethysmogram

Gao

Shi

et al. 2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

A Deep Learning–based PPG Quality Assessment Approach for Heart Rate and Heart Rate Variability

Naeini,

Sarhaddi,

Azimi

et al. 2023

ACM Trans. Comput. Healthcare

View full text Add to dashboard Cite

Photoplethysmography (PPG) is a non-invasive optical method to acquire various vital signs, including heart rate (HR) and heart rate variability (HRV). The PPG method is highly susceptible to motion artifacts and environmental noise. Unfortunately, such artifacts are inevitable in ubiquitous health monitoring, as the users are involved in various activities in their daily routines. Such low-quality PPG signals negatively impact the accuracy of the extracted health parameters, leading to inaccurate decision-making. PPG-based health monitoring necessitates a quality assessment approach to determine the signal quality according to the accuracy of the health parameters. Different studies have thus far introduced PPG signal quality assessment methods, exploiting various indicators and machine learning algorithms. These methods differentiate reliable and unreliable signals, considering morphological features of the PPG signal and focusing on the cardiac cycles. Therefore, they can be utilized for HR detection applications. However, they do not apply to HRV, as only having an acceptable shape is insufficient, and other signal factors may also affect the accuracy. In this paper, we propose a deep learning-based PPG quality assessment method for HR and various HRV parameters. We employ one customized one-dimensional (1D) and three two-dimensional (2D) Convolutional Neural Networks (CNN) to train models for each parameter. Reliability of each of these parameters will be evaluated against the corresponding electrocardiogram signal, using 210 hours of data collected from a home-based health monitoring application. Our results show that the proposed 1D CNN method outperforms the other 2D CNN approaches. Our 1D CNN model obtains the accuracy of 95.63%, 96.71%, 91.42%, 94.01%, and 94.81% for the HR, average of normal to normal interbeat (NN) intervals (AVNN), root mean square of successive NN interval differences (RMSSD), standard deviation of NN intervals (SDNN), and ratio of absolute power in low frequency to absolute power in high frequency (LF/HF) ratios, respectively. Moreover, we compare the performance of our proposed method with state-of-the-art algorithms. We compare our best models for HR-HRV health parameters with six different state-of-the-art PPG signal quality assessment methods. Our results indicate that the proposed method performs better than the other methods. We also provide the open-source model implemented in Python for the community to be integrated into their solutions.

show abstract

Photoplethysmographic Pulse Quality Assessment Methods Based on Similarity Analysis

Cited by 4 publications

References 10 publications

A Survey of Photoplethysmography and Imaging Photoplethysmography Quality Assessment Methods

A Survey of Photoplethysmography and Imaging Photoplethysmography Quality Assessment Methods

A LSTM-Based Realtime Signal Quality Assessment for Photoplethysmogram and Remote Photoplethysmogram

A Deep Learning–based PPG Quality Assessment Approach for Heart Rate and Heart Rate Variability

Contact Info

Product

Resources

About