A novel and low-complexity peak detection algorithm for heart rate estimation from low-amplitude photoplethysmographic (PPG) signals

Prada, Erick Javier Argüello; Maldonado, Rafael Daniel Serna

doi:10.1080/03091902.2019.1572237

Cited by 18 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Four metrics were used to quantify the performance of the peak detection algorithms. The metrics were: (1) averaged value of beat-by-beat root mean squared error (RMSE) between the PPG’s and the reference ECG’s heart rates [ 7 , 40 ], (2) averaged RMSE of the mean heart rates between the PPG and the reference ECG [ 7 , 41 ], (3) false positive (FP) beats [ 1 , 4 , 7 , 42 , 43 , 44 ], and (4) false negative (FN) beats [ 1 , 4 , 7 , 42 , 43 , 44 ]. Since peak detection is a single-class classification problem, there are no true negative (TN) values to evaluate.…”

Section: Methodsmentioning

confidence: 99%

A Real-Time PPG Peak Detection Method for Accurate Determination of Heart Rate during Sinus Rhythm and Cardiac Arrhythmia

et al. 2022

View full text Add to dashboard Cite

Objective: We have developed a peak detection algorithm for accurate determination of heart rate, using photoplethysmographic (PPG) signals from a smartwatch, even in the presence of various cardiac rhythms, including normal sinus rhythm (NSR), premature atrial contraction (PAC), premature ventricle contraction (PVC), and atrial fibrillation (AF). Given the clinical need for accurate heart rate estimation in patients with AF, we developed a novel approach that reduces heart rate estimation errors when compared to peak detection algorithms designed for NSR. Methods: Our peak detection method is composed of a sequential series of algorithms that are combined to discriminate the various arrhythmias described above. Moreover, a novel Poincaré plot scheme is used to discriminate between basal heart rate AF and rapid ventricular response (RVR) AF, and to differentiate PAC/PVC from NSR and AF. Training of the algorithm was performed only with Samsung Simband smartwatch data, whereas independent testing data which had more samples than did the training data were obtained from Samsung’s Gear S3 and Galaxy Watch 3. Results: The new PPG peak detection algorithm provides significantly lower average heart rate and interbeat interval beat-to-beat estimation errors—30% and 66% lower—and mean heart rate and mean interbeat interval estimation errors—60% and 77% lower—when compared to the best of the seven other traditional peak detection algorithms that are known to be accurate for NSR. Our new PPG peak detection algorithm was the overall best performers for other arrhythmias. Conclusion: The proposed method for PPG peak detection automatically detects and discriminates between various arrhythmias among different waveforms of PPG data, delivers significantly lower heart rate estimation errors for participants with AF, and reduces the number of false negative peaks. Significance: By enabling accurate determination of heart rate despite the presence of AF with rapid ventricular response or PAC/PVCs, we enable clinicians to make more accurate recommendations for heart rate control from PPG data.

show abstract

Section: Methodsmentioning

confidence: 99%

A Real-Time PPG Peak Detection Method for Accurate Determination of Heart Rate during Sinus Rhythm and Cardiac Arrhythmia

et al. 2022

View full text Add to dashboard Cite

show abstract

“…where TP, FN and FP denote, respectively, the number of true positives (pulses correctly detected as such), the number of false negatives (un-detected pulses) and the number of false positives (false or error pulses detected as true pulses). As done in (Karlen et al 2012, Argüello and Serna 2018, Argüello-Prada 2019, time deviations within 0.03 s between beats were accepted. Both FNs and FPs were considered as erroneous detections for this study, so the failed detection rate (FDR) was defined as follows:…”

Section: Data Acquisition and Processingmentioning

confidence: 99%

A low-complexity PPG pulse detection method for accurate estimation of the pulse rate variability (PRV) during sudden decreases in the signal amplitude

Prada

Higinio

2020

Physiol. Meas.

Self Cite

View full text Add to dashboard Cite

Background: One of the biggest obstacles to reliable pulse rate variability (PRV) analysis is the erroneous detection of photoplethysmographic (PPG) pulses. Among all the disturbances that may hinder pulse detection, the ripples appearing at the smooth segments of the PPG signal can become a serious problem when the amplitude of the signal decreases considerably. Objective: To present a low-complexity PPG pulse detection method for reliable PRV estimation under conditions in which a sudden decrease in the amplitude of the PPG signal can be expected. Approach: 2-min ECG and PPG data (sampling rate at 500 Hz) were obtained from thirty healthy subjects, who were asked to take a deep inspiration to provoke a sudden amplitude decrease (SAD) of the PPG signal. After introducing a new parameter denoted as C, through which it is possible to jump over the ripples hindering the accurate detection of the systolic peaks, 500 Hz-sampled PPG recordings were down-sampled (400, 300, 200 and 100 Hz) to investigate the effect of the sampling rate on pulse detection. For ECG recordings, automatic R-peak detection was performed by the Pan and Tompkins (PT) algorithm, whereas PPG pulse detection was performed by the well-known maximum of the first derivative (M1D) and the proposed method, once the C-value for best detection results on 500 Hz-sampled PPG recordings was found. The agreement between heart rate variability (HRV) and PRVs estimated from each pulse detection method was assessed and the correlation between HRV and PRV-derived indexes was computed for comparison. Main results: The proposed method can perform well on PPG-SAD segments, provided that the proper value of the parameter C is used. Moreover, a good agreement between HRV and PRV series, as well as lower relative errors and higher correlation coefficients between HRV and PRV indexes, were achieved by the proposed pulse detection method during SADs. Significance: Results show that the proposed method can dynamically adapt to circumstances in which a decrease in the amplitude of the PPG signal can be expected, providing continuous systolic peak detection and reliable PRV estimation under those conditions. However, more extensive testing under a wide range of conditions is needed to perform a more rigorous validation.

show abstract

“…An example of such a method is the Empirical Mode Decomposition (EMD) method ( Vadrevu and Manikandan, 2017 ), which has been used to decompose PPG signals into a set of intrinsic mode functions (IMFs). The use of Discrete Wavelet Transform (DWT) has also been proposed and acceptable results have been achieved when used in the analysis of PPG signals ( Paradkar and Chowdhury, 2015 ; Ricardo Ferro et al, 2015 ; Argüello Prada and Serna Maldonado, 2018 ).…”

Section: Introductionmentioning

confidence: 99%

PPGFeat: a novel MATLAB toolbox for extracting PPG fiducial points

Abdullah

Hafid

Folke

et al. 2023

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

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.

show abstract

A novel and low-complexity peak detection algorithm for heart rate estimation from low-amplitude photoplethysmographic (PPG) signals

Cited by 18 publications

References 11 publications

A Real-Time PPG Peak Detection Method for Accurate Determination of Heart Rate during Sinus Rhythm and Cardiac Arrhythmia

A Real-Time PPG Peak Detection Method for Accurate Determination of Heart Rate during Sinus Rhythm and Cardiac Arrhythmia

A low-complexity PPG pulse detection method for accurate estimation of the pulse rate variability (PRV) during sudden decreases in the signal amplitude

PPGFeat: a novel MATLAB toolbox for extracting PPG fiducial points

Contact Info

Product

Resources

About