Browse > Article
http://dx.doi.org/10.4218/etrij.2020-0394

Real-time photoplethysmographic heart rate measurement using deep neural network filters  

Kim, Ji Woon (Interdisciplinary Program in Biohealth-Machinery Convergence Engineering, Kangwon National University)
Park, Sung Min (School of Medicine, Kangwon National University)
Choi, Seong Wook (Interdisciplinary Program in Biohealth-Machinery Convergence Engineering, Kangwon National University)
Publication Information
ETRI Journal / v.43, no.5, 2021 , pp. 881-890 More about this Journal
Abstract
Photoplethysmography (PPG) is a noninvasive technique that can be used to conveniently measure heart rate (HR) and thus obtain relevant health-related information. However, developing an automated PPG system is difficult, because its waveforms are susceptible to motion artifacts and between-patient variation, making its interpretation difficult. We use deep neural network (DNN) filters to mimic the cognitive ability of a human expert who can distinguish the features of PPG altered by noise from various sources. Systolic (S), onset (O), and first derivative peaks (W) are recognized by three different DNN filters. In addition, the boundaries of uninformative regions caused by artifacts are identified by two different filters. The algorithm reliably derives the HR and presents recognition scores for the S, O, and W peaks and artifacts with only a 0.7-s delay. In the evaluation using data from 11 patients obtained from PhysioNet, the algorithm yields 8643 (86.12%) reliable HR measurements from a total of 10 036 heartbeats, including some with uninformative data resulting from arrhythmias and artifacts.
Keywords
deep learning; deep neural network filter; heart rate; photoplethysmography; recognition score;
Citations & Related Records
연도 인용수 순위
  • Reference
1 G. Lu et al., A comparison of photoplethysmography and ECG recording to analyse heart rate variability in healthy subjects, J. Med. Eng. Technol. 33 (2009), no. 8, 634-641.   DOI
2 M. Nitzan, A. Babchenko, and B. Khanokh, Very low frequency variability in arterial blood pressure and blood volume pulse, Med. Biol. Eng. Comput. 37 (1999), no. 1, 54-58.   DOI
3 Q. Zhang et al., A machine learning-empowered system for long-term motion-tolerant wearable monitoring of blood pressure and heart rate with ear-ECG/PPG, IEEE Access 5 (2017), 10547-10561.   DOI
4 J. L. Reuss and D. E. Bahr, Period domain analysis in fetal pulse oximetry, in Proc. Conf. Annu. Fall Meeting Biomed. Eng. Soc. (Houston, TX, USA), Oct. 2002, pp. 1742-1743.
5 K. H. Shelley, Photoplethysmography: Beyond the calculation of arterial oxygen saturation and heart rate, Anesth. Analg. 105 (2007), no. 6, S31-S36.   DOI
6 V. Jindal et al., An adaptive deep learning approach for PPG-based identification, in Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. (EMBC), (Orlando, FL, USA), Aug. 2016, pp. 6401-6404.
7 L. Everson et al., Biometricnet: Deep learning based biometric identification using wrist-worn PPG, in Proc. IEEE Int. Symp. Circuits Syst. (ISCAS), (Florence, Italy), May 2018, pp. 1-5.
8 Y. L. Yang et al., Postoperative pain assessment indices based on photoplethysmography waveform analysis, Front. Physiol. 9 (2018), 1199.   DOI
9 K. Zhou et al., Practical evaluation of encrypted traffic classification based on a combined method of entropy estimation and neural networks, ETRI J. 42 (2020), no. 3, 311-323.   DOI
10 A. Reiss et al., Deep PPG: Large-scale heart rate estimation with convolutional neural networks, Sensors 19 (2019), no. 14, 3079-3106.   DOI
11 M. A. F. Pimentel et al., Toward a robust estimation of respiratory rate from pulse oximeters, IEEE Trans. Biomed. Eng. 64 (2016), no. 8, 1914-1923.   DOI
12 K. Her et al., Windkessel model of hemodynamic state supported by a pulsatile ventricular assist device in premature ventricle contraction, Biomed. Eng. Online 17 (2018), no. 1, article no. 18.   DOI
13 S. F. Cooke and T. V. P. Bliss, Plasticity in the human central nervous system, Brain 129 (2006), no. 7, 1659-1673.   DOI
14 B. M. Lake et al., Building machines that learn and think like people, Behav. Brain Sci. 40 (2017), E253.   DOI
15 J. Kim, S. Park, and S. Choi, Automatic parameter acquisition of 12 leads ECG using continuous data processing deep neural network, J. Biomed. Eng. Res. 41 (2020), no. 2, 107-119.   DOI
16 M. Elgendi, On the analysis of fingertip photoplethysmogram signals, Curr. Cardiol. Rev. 8 (2012), no. 1, 14-25.   DOI
17 U. Senturk, I. Yucedag, and K. Polat, Repetitive neural network (RNN) based blood pressure estimation using PPG and ECG signals, in Proc. Int. Symp. Multidiscip. Stud. Innov. Technol. (Ankara, Turkey), Oct. 2018, pp. 1-4.
18 L. G. Rocha et al., Real-time HR estimation from wrist PPG using binary LSTMs, in Proc. IEEE Biomed. Circuits Syst. Conf. (BioCAS), (Nara, Japan), Oct. 2019, pp. 1-4.
19 R. Gonzalez et al., A computer based photoplethysmographic vascular analyzer through derivatives, in Proc. Comput. Cardiol. (Bologna, Italy), Sept. 2008, pp. 177-180.
20 V. Jeyhani et al., Comparison of HRV parameters derived from photoplethysmography and electrocardiography signals, in Proc. Annu. Int. Conf. Eng. Med. Biol. Soc. (EMBC), (Milan, Italy), Aug. 2015, pp. 5952-5955.
21 A. Moshfegh et al., Development of an innovative technology to segment luminal borders of intravascular ultrasound image sequences in a fully automated manner, Comput. Biol. Med. 108 (2019), pp. 111-121.   DOI
22 T. G. Karimpanal and R. Bouffanais, Self-Organizing maps for storage and transfer of knowledge in reinforcement learning, Adapt. Behav. 27 (2019), no. 2, 111-126.   DOI
23 W. Khan et al., Deep recurrent neural networks with word embeddings for urdu named entity recognition, ETRI J. 42 (2020), no. 1, 90-100.   DOI
24 G. M. London and A. P. Guerin, Influence of arterial pulse and reflected waves on blood pressure and cardiac function, Am. Heart J. 138 (1999), no. 3, S220-S224.   DOI
25 K. Takazawa et al., Assessment of vasoactive agents and vascular aging by the second derivative of photoplethysmogram waveform, Hypertension 32 (1998), no. 2, 365-370.   DOI
26 D. Biswas et al., CorNET: Deep learning framework for PPG-based heart rate estimation and biometric identification in ambulant environment, IEEE Trans. 13 (2019), no. 2, 282-291.
27 A. Reiss et al., PPG-based heart rate estimation with time-frequency spectra: A deep learning approach, in Proc. ACM Int. Joint Conf. Int. Symp. Pervasive Ubiquitous Comput. Wearable Comput. (Singapore, Singapore), Oct. 2018, pp. 1283-1292.
28 M. S. Lee et al., Fast emotion recognition based on single pulse PPG signal with convolutional neural network, Appl. Sci. 9 (2019), no. 16, 3355.   DOI
29 N. Karimian et al., Human recognition from photoplethysmography (PPG) based on non-fiducial features, in Proc. IEEE Int. Conf. Acoust., Speech Signal Process. (ICASSP), (New Orleans, LA, USA), Mar. 2017, pp. 4636-4640
30 M. Elgendi, Y. Liang, and R. Ward, Toward generating gore diagnostic features from photoplethysmogram waveforms, Dis. 6 (2018), no. 1, 20.   DOI
31 A. L. Goldberger et al., PhysioBank, PhysioToolkit, and Physio-Net: Components of a new research resource for complex physiologic signals, Circulation 101 (2000), no. 23, e215-e220.
32 V. F. Blanc et al., Computerized photo-plethysmography of the finger, Can. J. Anaesth. 40 (1993), no. 3, 271-278.   DOI