A method for photoplethysmography signal quality assessment fusing multi-class features with multi-scale series information_Journal of Biomedical Engineering

Authors：

QI Yusheng ^1,2,3 ,  ZHANG Aihua ^1,2,3 , MA Yurun ^1,2,3 , WANG Huidong ^1,2,3 , LI Jiaqi ^1,2,3 , CHEN Cheng ^1,2,3

1. College of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, P. R. China;
2. Key Laboratory of Gansu Advanced Control for Industrial Processes, Lanzhou University of Technology, Lanzhou 730050, P. R. China;
3. National Demonstration Center for Experimental Electrical and Control Engineering Education, Lanzhou University of Technology, Lanzhou 730050, P. R. China;

Corresponding author：

ZHANG Aihua, Email: zhangaihua@lut.edu.cn

Keywords：

Photoplethysmography; Multi-class features; Multi-scale time series information; Quality assessment

DOI：

10.7507/1001-5515.202211054

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Photoplethysmography (PPG) is often affected by interference, which could lead to incorrect judgment of physiological information. Therefore, performing a quality assessment before extracting physiological information is crucial. This paper proposed a new PPG signal quality assessment by fusing multi-class features with multi-scale series information to address the problems of traditional machine learning methods with low accuracy and deep learning methods requiring a large number of samples for training. The multi-class features were extracted to reduce the dependence on the number of samples, and the multi-scale series information was extracted by a multi-scale convolutional neural network and bidirectional long short-term memory to improve the accuracy. The proposed method obtained the highest accuracy of 94.21%. It showed the best performance in all sensitivity, specificity, precision, and F1-score metrics, compared with 6 quality assessment methods on 14 700 samples from 7 experiments. This paper provides a new method for quality assessment in small samples of PPG signals and quality information mining, which is expected to be used for accurate extraction and monitoring of clinical and daily PPG physiological information.

Citation： QI Yusheng, ZHANG Aihua, MA Yurun, WANG Huidong, LI Jiaqi, CHEN Cheng. A method for photoplethysmography signal quality assessment fusing multi-class features with multi-scale series information. Journal of Biomedical Engineering, 2023, 40(3): 536-543. doi: 10.7507/1001-5515.202211054 Copy

1.	张剑锋, 陈光华, 高博. 基于光电容积脉搏波的脉搏信息提取研究. 电子测量技术, 2019, 42(13): 117-120.
2.	Banik P P, Hossain S, Kwon T H, et al. Development of a wearable reflection-type pulse oximeter system to acquire clean PPG signals and measure pulse rate and SpO₂ with and without finger motion. Electronics, 2020, 9(11): 1905.
3.	吴海燕, 季忠, 李孟泽. 基于脉搏波的无创连续血压监测模型簇研究. 仪器仪表学报, 2020, 41(7): 224-234.
4.	Sardana H K, Kanwade R, Tewary S. Arrhythmia detection and classification using ECG and PPG techniques: A review. Phys Eng Sci Med, 2021, 44(4): 1027-1048.
5.	戴凤智, 芦鹏, 朱宇璇. 基于多传感器的睡眠监测与评估系统设计. 国外电子测量技术, 2022, 41(4): 126-133.
6.	Passman R. Mobile health technologies in the diagnosis and management of atrial fibrillation. Curr Opin Cardiol, 2022, 37(1): 1-9.
7.	Kasambe P V, Rathod S S. VLSI wavelet based denoising of PPG signal. Proc Comput Sci, 2015, 49: 282-288.
8.	Li Q, Clifford G D. Dynamic time warping and machine learning for signal quality assessment of pulsatile signals. Physiol Meas, 2012, 33(9): 1491-1501.
9.	Petterson M T, Begnoche V L, Graybeal J M. The effect of motion on pulse oximetry and its clinical significance. Anesth Analg, 2007, 105(6): S78-S84.
10.	张爱华, 常婷婷, 漆宇晟, 等. 基于脉搏信号融合分析的心率监测方法. 电子测量与仪器学报, 2020, 34(10): 163-171.
11.	Fisher C, Dömer B, Wibmer T, et al. An algorithm for real-time pulse waveform segmentation and artifact detection in photoplethysmograms. IEEE J Biomed Health Inform, 2017, 21(2): 372-381.
12.	Pereira T, Gadhoumi K, Ma M, et al. A supervised approach to robust photoplethysmography quality assessment. IEEE J Biomed Health Inform, 2020, 24(3): 649-657.
13.	Pradhan N, Rajan S, Adler A. Evaluation of the signal quality of wrist-based photoplethysmography. Physiol Meas, 2019, 40(6): 065008.
14.	Naeini E K, Azimi I, Rahmani A M, et al. A real-time PPG quality assessment approach for healthcare Internet-of-Things. Proc Comput Sci, 2019, 151: 551-558.
15.	Gao H, Wu X, Shi C, et al. A LSTM-based realtime signal quality assessment for photoplethysmogram and remote photoplethysmogram// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 3831-3840.
16.	Liu S H, Li R X, Wang J J, et al. Classification of photoplethysmographic signal quality with deep convolution neural networks for accurate measurement of cardiac stroke volume. Appl Sci, 2020, 10(13): 1-16.
17.	Pereira T, Ding C, Gadhoumi K, et al. Deep learning approaches for plethysmography signal quality assessment in the presence of atrial fibrillation. Physiol Meas, 2019, 40(12): 125002.
18.	漆宇晟, 张爱华, 马玉润. 日常无监督状态下的脉率变异性提取方法研究. 生物医学工程学杂志, 2019, 36(2): 298-305.
19.	Beh W K, Wu Y H, Wu A Y A. Robust PPG-based mental workload assessment system using wearable devices. IEEE J Biomed Health Inform, 2021, 27(5): 2323-2333.
20.	Yen C T, Chen U H, Wang G C, et al. Non-Invasive blood glucose estimation system based on a neural network with dual-wavelength photoplethysmography and bioelectrical impedance measuring. Sensors, 2022, 22(12): 4452.
21.	Cincotta P M, Giordano C M, Silva R A, et al. The Shannon entropy: an efficient indicator of dynamical stability. Phys D, 2021, 417: 132816.
22.	Niyirora J. Entropic measures of complexity in a new medical coding system. BMC Med Inform Decis Mak, 2021, 21(1): 124.
23.	Ismail S, Siddiqi I, Akram U. Heart rate estimation in PPG signals using Convolutional-Recurrent Regressor. Comput Biol Med, 2022, 145: 105470.
24.	Sonck J, Mizukami T, Johnson N P, et al. Development, validation, and reproducibility of the pullback pressure gradient (PPG) derived from manual fractional flow reserve pullbacks. Catheter Cardiovasc Interv, 2022, 99(5): 1518-1525.
25.	Alzubaidi L, Zhang J, Humaidi A J, et al. Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. J Big Data, 2021, 8(1): 53.
26.	Yen C T, Chang S N, Liao C H. Estimation of beat-by-beat blood pressure and heart rate from ECG and PPG using a fine-tuned deep CNN model. IEEE Access, 2022, 10: 85459-85469.
27.	Liu W, Jing W, Li Y. Incorporating feature representation into BiLSTM for deceptive review detection. Computing, 2020, 102(3): 701-715.
28.	Esgalhado F, Fernandes B, Vassilenko V, et al. The application of deep learning algorithms for PPG signal processing and classification. Computers, 2021, 10(12): 1-15.
29.	Xu G, Meng Y, Qiu X, et al. Sentiment analysis of comment texts based on BiLSTM. IEEE Access, 2019, 7: 51522-51532.
30.	Thakur S, Kumar A. X-ray and CT-scan-based automated detection and classification of covid-19 using convolutional neural networks (CNN). Biomed Signal Process Control, 2021, 69: 102920.

1. 张剑锋, 陈光华, 高博. 基于光电容积脉搏波的脉搏信息提取研究. 电子测量技术, 2019, 42(13): 117-120.
2. Banik P P, Hossain S, Kwon T H, et al. Development of a wearable reflection-type pulse oximeter system to acquire clean PPG signals and measure pulse rate and SpO₂ with and without finger motion. Electronics, 2020, 9(11): 1905.
3. 吴海燕, 季忠, 李孟泽. 基于脉搏波的无创连续血压监测模型簇研究. 仪器仪表学报, 2020, 41(7): 224-234.
4. Sardana H K, Kanwade R, Tewary S. Arrhythmia detection and classification using ECG and PPG techniques: A review. Phys Eng Sci Med, 2021, 44(4): 1027-1048.
5. 戴凤智, 芦鹏, 朱宇璇. 基于多传感器的睡眠监测与评估系统设计. 国外电子测量技术, 2022, 41(4): 126-133.
6. Passman R. Mobile health technologies in the diagnosis and management of atrial fibrillation. Curr Opin Cardiol, 2022, 37(1): 1-9.
7. Kasambe P V, Rathod S S. VLSI wavelet based denoising of PPG signal. Proc Comput Sci, 2015, 49: 282-288.
8. Li Q, Clifford G D. Dynamic time warping and machine learning for signal quality assessment of pulsatile signals. Physiol Meas, 2012, 33(9): 1491-1501.
9. Petterson M T, Begnoche V L, Graybeal J M. The effect of motion on pulse oximetry and its clinical significance. Anesth Analg, 2007, 105(6): S78-S84.
10. 张爱华, 常婷婷, 漆宇晟, 等. 基于脉搏信号融合分析的心率监测方法. 电子测量与仪器学报, 2020, 34(10): 163-171.
11. Fisher C, Dömer B, Wibmer T, et al. An algorithm for real-time pulse waveform segmentation and artifact detection in photoplethysmograms. IEEE J Biomed Health Inform, 2017, 21(2): 372-381.
12. Pereira T, Gadhoumi K, Ma M, et al. A supervised approach to robust photoplethysmography quality assessment. IEEE J Biomed Health Inform, 2020, 24(3): 649-657.
13. Pradhan N, Rajan S, Adler A. Evaluation of the signal quality of wrist-based photoplethysmography. Physiol Meas, 2019, 40(6): 065008.
14. Naeini E K, Azimi I, Rahmani A M, et al. A real-time PPG quality assessment approach for healthcare Internet-of-Things. Proc Comput Sci, 2019, 151: 551-558.
15. Gao H, Wu X, Shi C, et al. A LSTM-based realtime signal quality assessment for photoplethysmogram and remote photoplethysmogram// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 3831-3840.
16. Liu S H, Li R X, Wang J J, et al. Classification of photoplethysmographic signal quality with deep convolution neural networks for accurate measurement of cardiac stroke volume. Appl Sci, 2020, 10(13): 1-16.
17. Pereira T, Ding C, Gadhoumi K, et al. Deep learning approaches for plethysmography signal quality assessment in the presence of atrial fibrillation. Physiol Meas, 2019, 40(12): 125002.
18. 漆宇晟, 张爱华, 马玉润. 日常无监督状态下的脉率变异性提取方法研究. 生物医学工程学杂志, 2019, 36(2): 298-305.
19. Beh W K, Wu Y H, Wu A Y A. Robust PPG-based mental workload assessment system using wearable devices. IEEE J Biomed Health Inform, 2021, 27(5): 2323-2333.
20. Yen C T, Chen U H, Wang G C, et al. Non-Invasive blood glucose estimation system based on a neural network with dual-wavelength photoplethysmography and bioelectrical impedance measuring. Sensors, 2022, 22(12): 4452.
21. Cincotta P M, Giordano C M, Silva R A, et al. The Shannon entropy: an efficient indicator of dynamical stability. Phys D, 2021, 417: 132816.
22. Niyirora J. Entropic measures of complexity in a new medical coding system. BMC Med Inform Decis Mak, 2021, 21(1): 124.
23. Ismail S, Siddiqi I, Akram U. Heart rate estimation in PPG signals using Convolutional-Recurrent Regressor. Comput Biol Med, 2022, 145: 105470.
24. Sonck J, Mizukami T, Johnson N P, et al. Development, validation, and reproducibility of the pullback pressure gradient (PPG) derived from manual fractional flow reserve pullbacks. Catheter Cardiovasc Interv, 2022, 99(5): 1518-1525.
25. Alzubaidi L, Zhang J, Humaidi A J, et al. Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. J Big Data, 2021, 8(1): 53.
26. Yen C T, Chang S N, Liao C H. Estimation of beat-by-beat blood pressure and heart rate from ECG and PPG using a fine-tuned deep CNN model. IEEE Access, 2022, 10: 85459-85469.
27. Liu W, Jing W, Li Y. Incorporating feature representation into BiLSTM for deceptive review detection. Computing, 2020, 102(3): 701-715.
28. Esgalhado F, Fernandes B, Vassilenko V, et al. The application of deep learning algorithms for PPG signal processing and classification. Computers, 2021, 10(12): 1-15.
29. Xu G, Meng Y, Qiu X, et al. Sentiment analysis of comment texts based on BiLSTM. IEEE Access, 2019, 7: 51522-51532.
30. Thakur S, Kumar A. X-ray and CT-scan-based automated detection and classification of covid-19 using convolutional neural networks (CNN). Biomed Signal Process Control, 2021, 69: 102920.

Journal of Biomedical Engineering

A method for photoplethysmography signal quality assessment fusing multi-class features with multi-scale series information

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content