Using Deep Supervised UNet Network for Continuous Estimation of Blood Pressure Based on Photoplethysmography Signal

Khaleghian, Masoumeh; Shojaeilangari, Seyedehsamaneh; Mohseni, Mahdi; Beigzadeh, Maryam

Using Deep Supervised UNet Network for Continuous Estimation of Blood Pressure Based on Photoplethysmography Signal

Document Type : Original Research

Authors

masoumeh Khaleghian ¹

Seyedehsamaneh Shojaeilangari ²

mahdi Mohseni ³

Maryam Beigzadeh ⁴

¹ Department of Electrical and Computer Engineering, Faculty of Artificial Intelligence, Kharazmi University

² Biomedical Engineering group, Department of Electrical and Information Technology, Iranian Research Organization (IROST

³ Faculty of Electrical Engineering (Electronics and Telecommunications), Shahid Beheshti University, Tehran

⁴ Biomedical Engineering group, Department of Electrical and Information Technology, Iranian Research Organization (IROST)

Abstract

Blood pressure monitoring is a vital component of maintaining overall health. High blood pressure values, as a risk factor, can lead to heart attacks, strokes, and heart and kidney failures. Similarly, low blood pressure values can also be dangerous, causing dizziness, weakness, fainting, and impaired oxygen delivery to organs, resulting in brain and heart damage. Consequently, continuous monitoring of blood pressure levels in high-risk individuals is very important. A Holter blood pressure monitoring device is prescribed for many patients due to its ability to provide long-term and valuable blood pressure data. The pursuit of software techniques and the development of cuffless blood pressure measurement devices, while ensuring patient comfort and convenience, are among the significant challenges that researchers are focusing on. In this study, a deep learning framework based on the UNet network is proposed for continuous blood pressure estimation from photoplethysmography signals. The proposed model was evaluated on the UCI database, involving 942 patients under intensive care, and achieved mean absolute errors of 8.88, 4.43, and 3.32, with standard deviations of 11.01, 6.18, and 4.15, respectively, for systolic, diastolic, and mean arterial blood pressure values. According to the international BHS standard, the proposed method meets grade A criteria for diastolic and mean blood pressure estimations and grade C for systolic blood pressure estimation. The results of this study demonstrate that the suggested deep learning framework has the necessary potential for blood pressure estimation from PPG signals in real-world applications.

Keywords

Photoplethysmography signal

Blood pressure estimation

Non-invasive technique

artificial intelligence

deep learning

Machine learning

Subjects

Bioinformatics

L. Peter, N. Noury, and M. Cerny, “A review of methods for non-invasive and continuous blood pressure monitoring: Pulse transit time method is promising?,” IRBM, vol. 35, no. 5, pp. 271–282, 2014.
[2] K. Qin, W. Huang, T. Zhang, and S. Tang, “Machine learning and deep learning for blood pressure prediction : a methodological review from multiple perspectives,” in Artificial Intelligence Review, Springer, 2022, pp. 8095–8196.
[3] س. س. موسوی, “طراحی و ساخت هولتر فشارخون مبتنی بر تلفن همراه با به کارگیری سیگنال های الکتروکاردیوگرام و فوتوپلتیسموگرافی، ” زنجان، 1397.
[4] R. Mukkamala, J. Hahn, and A. Chandrasekhar, “Photoplethysmography in noninvasive blood pressure monitoring,” in Photoplethysmography Technology, Signal Analysis and Applications, Academic Press, 2022, pp. 359–400.
[5] X. DUAN, “The Analysis of Photoplethysmography Signal: Investigating the Current Methods of Cuff-Less Blood Pressure Monitoring,” Vrije Universiteit Brussel & Universiteit Gent, 2021.
[6] C. Landry, S. Peterson, and A. Arami, “Nonlinear Dynamic Modelling of the Blood Pressure Waveform: Towards an Accurate Cuffless Monitoring System,” IEEE Sens J, vol. 20, pp. 5368–5378, 2020.
[7] م. شهابی ، و. نفیسی، “تخمین بدون کاف فشارخون مبتنی بر ویژگی‎های زمانی سیگنال نبض” ، پردازش علائم وداده‎ ها، صفحات 103-113، 1397.
[8] S. S. Mousavi, M. Charmi, M. Firouzmand, and M. Hemmati, “Design and Manufacturing a Mobile-Based Ambulatory Monitoring of Blood Pressure Using Electrocardiogram and Photoplethysmography Signals,” University of Zanjan, Zanjan, 2018.
[9] S. Mahmud et al., “A Shallow U-Net Architecture for Reliably Predicting Blood Pressure (BP) from Photoplethysmogram (PPG) and Electrocardiogram (ECG) Signals,” sensors, vol. 22, 2022.
[10] D. U. Jeong and K. M. Lim, “Combined deep CNN – LSTM network based multitasking learning architecture for noninvasive continuous blood pressure estimation using difference in ECG PPG features,” Sci Rep, no. 0123456789, pp. 1–8, 2021, doi: 10.1038/s41598-021-92997-0.
[11] Y. H. Li, L. N. Harfiya, K. Purwandari, and Y. Der Lin, “Real-time cuffless continuous blood pressure estimation using deep learning model,” Sensors (Switzerland), vol. 20, no. 19, pp. 1–19, 2020, doi: 10.3390/s20195606.
[12] S. González, W. Hsieh, and T. P. Chen, “A benchmark for machine- learning based non-invasive blood pressure estimation using photoplethysmogram,” Sci. Rep., vol. 10, no. 149, pp. 1–16, 2023.
[13] N. Ibtehaz et al., “PPG2ABP : Translating Photoplethysmogram ( PPG ) Signals to Arterial Blood Pressure ( ABP ) Waveforms,” Bioengineering, vol. 9, no. 11, 2022.
[14] S. Lee, M. Lee, and J. Y. Sim, “DSE-NN: Deeply Supervised Efficient Neural Network for Real-Time Remote Photoplethysmography,” Bioengineering, vol. 10, no. 12, 2023.
[15] S. Ali, J. Li, Y. Pei, and K. U. Rehman, “A Multi-module 3D U-Net Learning Architecture for Brain Tumor Segmentation A Multi-module 3D U-Net Learning Architecture for Brain Tumor,” in Data Mining and Big Data, Springer, 2022, pp. 57–69.
[16] Y. Li, K. Li, and X. Wang, “Deeply-Supervised CNN Model for Action Recognition with Trainable Feature Aggregation,” in Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence(IJCAI), 2017, pp. 807–813.
[17] G. Dheeru and D.Casey, “UCI Machine Learning Repository.”
[18] M. Kachuee, M.M. Kiani, H. Mohammadzade, and M. Shaban, “Cuffless blood pressure estimation algorithms for continuous health-care monitoring,” IEEE Trans. Biomed. Eng., vol. 64, pp. 859–869, 2016.
[19] D. P. Kingma and L. Ba, “Adam: A method for stochastic optimization,” in 3rd International Conference for Learning Representations, San Diego, 2015.
[20] P. Lv2, J. Wang, X. Zhang, and Ch. Shi3, “Deep supervision and atrous inception based U Net combining CRF for automatic liver segmentation from CT,” Sci. Rep., vol. 12, no. 16995, 2022.
[21] J. Cheng, Y. Xu, R. Song, Y. Liu, Ch. Li, and X. Chen, “Prediction of arterial blood pressure waveforms from photoplethysmogram signals via fully convolutional neural networks,” Comput. Biol. Med., vol. 138, 2021.
[22] م. قنواتی, س. ف. مولایی زاده, و م. نویدی, “یک روش شخصی‎سازی شده برای تخمین فشارخون بدون کاف از یک سنسور PPG مبتنی بر یادگیری انتقالی عمیق” سی‎امین کنفرانس ملی و هشتمین کنفرانس بین‎المللی مهندسی زیست پزشکی ایران, تهران, 1402.
[23] N. Hasanzadeh and M.M. Ahmadi, “Blood pressure estimation using photoplethysmogram signal and its morphological features,” IEEE Sens. J., vol. 20, no. 8, pp. 4300–4310, 2019.
[24] S. Bose S and A. Kandaswamy, “Sparse characterization of PPG based on K- SVD for beat-to-beat blood pressure prediction,” Biomedical Research, vol. 29, no. 4, pp. 835–843, 2018.
[25] S. S. Mousavi et al., “Blood pressure estimation from appropriate and inappropriate PPG signals using a whole-based method,” Biomed Signal Process Control, vol. 47, pp. 196–206, 2019.
[26] S. Baek et al., “End-to-End Blood Pressure Prediction via Fully Convolutional Networks,” IEEE Access, vol. 7, pp. 185458–185468, 2019.
[27] M. Panwar, A. Gautam, D. Biswas, and A. Acharyya, “PP-Net: a deep learning framework for PPG-based blood pressure and heart rate estimation,” IEEE Sens. J., vol. 20, no. 17, pp. 10000–10011, 2020.
[28] M. Rong and K. Li, “A multi-type features fusion neural network for blood pressure prediction based on photoplethysmography,” Biomed Signal Process Control, vol. 68, p. 102772, 2021, vol. 68, 2021.
[29] Y. Qiu et al., “Blood pressure estimation based on composite neural network and graphics information,” Biomed. Signal Process. Control, vol. 70, no. 103001, 2021.
[30] A. B. Malayeri and M. B. Khodabakhshi, “Concatenated convolutional neural network model for cufless blood pressure estimation using fuzzy recurrence properties of PPG signals,” Sci. Rep., vol. 12, no. 6633, 2022.
[31] Y-C. Hsu, Y-H. Li, C-C. Chang, and L. N. Harfiya, “Generalized deep neural network model for cuffless blood pressure estimation with photoplethysmogram signal only,” Sensors, vol. 20, no. 19, 2020.
[32] Z. Li and W. He, “A continuous blood pressure estimation method using photoplethysmography by GRNNbased model,” Sensors, vol. 21, no. 21, 2021.
[33] L. N. Harfya, C-C. Chang, and Y-H. Li, “Continuous blood pressure estimation using exclusively photopletysmography by LSTM-based signal-to-signal translation,” Sensors, vol. 21, no. 9, 2021.