Continuous Blood Pressure Estimation Without a Cuff Using Deep Learning on PPG and ECG Signals
DOI:
https://doi.org/10.64296/vijir.v1i2.03Keywords:
Blood Pressure Monitoring, LSTM, PPG, ECG, Non-invasive Healthcare TechnologyAbstract
Regular monitoring of blood pressure (BP) is essential for the early detection and management of hypertension and other cardiovascular diseases. However, traditional cuff-based BP measurement methods are bulky, uncomfortable, and unsuitable for continuous monitoring. This study proposes a novel, non-invasive, and cuffless approach for continuous BP estimation by leveraging physiological signals. The proposed framework utilizes photoplethysmogram (PPG) and electrocardiogram (ECG) signals to capture the mechanical and electrical activities of the cardiovascular system. It includes signal preprocessing, segmentation, statistical feature extraction, and pattern analysis to establish a correlation between signal characteristics and BP values. A variety of features are extracted from the signals, including time-domain, frequency- domain, and morphological attributes. A deep learning model is then trained on these features using a publicly available dataset containing synchronized PPG, ECG, and reference BP readings. The model is validated using key performance metrics such as Mean Absolute Error (MAE) and Root Mean Square Error (RMSE), which confirm its effectiveness in accurately predicting systolic and diastolic BP. The results meet established clinical standards, demonstrating that the proposed system can reliably estimate BP in real time. This study highlights the potential of integrating PPG and ECG signals for continuous, non-invasive BP monitoring, offering a foundation for wearable health technologies and remote healthcare solutions.
References
[1] “Blood flow and blood pressure regulation | biology for majors ii.” [https://courses.lumenlearning.com/suny-wmopen-biology2/chapter/blood-flow-and-blood-pressure-regulation/](https://courses.lumenlearning.com/suny-wmopen-biology2/chapter/blood-flow-and-blood-pressure-regulation/). Accessed: 2025-12-02.
[2] C. M. P. F. F. E. L. Schiffrin, “The immune system: Role in hypertension,” Canadian Journal of Cardiology, vol. 29, no. 5, pp. 543–548, 2013.
[3] J. C. P. and J. E. Davis, “Hematology/oncology emergencies,” Hematology/Oncology Clinics, vol. 31, no. 6, 2017.
[4] S. L. M. W. S. Z. Tewelde, “Cardiogenic shock,” Cardiology Clinics, vol. 36, no. 1, pp. 53–61, 2018.
[5] R. C.-L. G. D. L. R. C. P. G. S. E. G. J. B. B. S. R. S. B. Zhou, “Worldwide trends in hypertension prevalence and progress in treatment and control from 1990 to 2019: a pooled analysis of 1201 population-representative studies with 104 million participants,” Lancet, vol. 398, no. 10304, pp. 957–980, 2021.
[6] R. S. and G. P. S. S. Singh, “Prevalence and associated risk factors of hypertension: A cross-sectional study in urban varanasi,” International Journal of Hypertension, 2017.
[7] A. E. S. et al., “May measurement month 2019: The global blood pressure screening campaign of the international society of hypertension,” Hypertension, vol. 76, no. 2, pp. 333–341, 2020.
[8] M. Rashed, M. B. A. Z. Shammo, M. I. Hossain, M. A. Hossain, and J. Habib, “A machine learning framework for stress detection using photoplethysmography (ppg) signals,” in 2025 International Conference on Quantum Photonics, Artificial Intelligence, and Networking (QPAIN), pp. 1–5, IEEE, 2025.
[9] T. J. A. Kitterman, “Catheterization of umbilical vessels in newborn infants,” Pediatric Clinics of North America, vol. 17, no. 4, pp. 895–912, 1970.
[10] G. C. B. A. M. C. E. Chung, “Non-invasive continuous blood pressure monitoring: A review of current applications,” Frontiers of Medicine, vol. 7, no. 1, pp. 91–101, 2013.
[11] S. N. A. Ismail, N. A. Nayan, R. Jaafar, and Z. May, “Recent advances in non-invasive blood pressure monitoring and prediction using a machine learning approach,” Sensors, vol. 22, no. 16, p. 6195, 2022.
[12] I. P.-G. et al., “Accuracy of non-invasive and minimally invasive hemodynamic monitoring: where do we stand?,” Annals of Translational Medicine, vol. 7, no. 17, p. 421, 2019.
[13] M. F. C. H. M. G. S. S. Mousavi, “Blood pressure estimation from appropriate and inappropriate ppg signals using a whole-based method,” Biomedical Signal Processing and Control, vol. 47, pp. 196–206, 2019.
[14] G. C. et al., “Multi-site photoplethysmography technology for blood pressure assessment: Challenges and recommendations,” Journal of Clinical Medicine, vol. 8, no. 11, p. 1827, 2019.
[15] M. H. Islam, M. Rashed, N. K. Podder, M. I. Hossain, and A. K. Mondol, “Enhancing copd detection with wavenet: Assessing the efficacy of deep learning model,” in 2025 International Conference on Quantum Photonics, Artificial Intelligence, and Networking (QPAIN), pp. 1–6, IEEE, 2025.
[16] A. N. et al., “A continuous cuffless blood pressure measurement from optimal ppg characteristic features using machine learning algorithms,” Heliyon, vol. 10, no. 6, 2024.
[17] M. Kachuee, M. M. Kiani, H. Mohammadzade, and M. Shabany, “Cuffless blood pressure estimation algorithms for continuous health-care monitoring,” IEEE Trans. Biomed. Eng., vol. 64, no. 4, pp. 859–869, 2016.
[18] S. Maqsood, S. Xu, M. Springer, and R. Mohawesh, “A benchmark study of machine learning for analysis of signal feature extraction techniques for blood pressure estimation using photoplethysmography (ppg),” IEEE Access, vol. 9, pp. 138817–138833, 2021.
[19] Y. Kurylyak, F. Lamonaca, and D. Grimaldi, “A neural network-based method for continuous blood pressure estimation from a ppg signal,” in Proc. IEEE Int. Instrum. Meas. Technol. Conf., pp. 280–283, 2013.
[20] X. Chen, S. Yu, Y. Zhang, F. Chu, and B. Sun, “Machine learning method for continuous noninvasive blood pressure detection based on random forest,” IEEE Access, vol. 9, pp. 34112–34118, 2021.
[21] Z. Tian, A. Liu, G. Zhu, and X. Chen, “A paralleled cnn and transformer network for ppg-based cuffless blood pressure estimation,” Biomedical Signal Processing and Control, vol. 99, p. 106741, 2025.
[22] S. G. Khalid, J. Zhang, F. Chen, and D. Zheng, “Blood pressure estimation using photoplethysmography only: comparison between different machine learning approaches,” Journal of Healthcare Engineering, vol. 2018, p. 1548647, 2018.
[23] J. Dey, A. Gaurav, and V. N. Tiwari, “Instabp: cuff-less blood pressure monitoring on smartphone using single ppg sensor,” in Proc. IEEE Eng. Med. Biol. Soc. Annu. Int. Conf., pp. 5002–5005, 2018.
[24] A. J. R.-D. J. E. G.-D. M. A. Arroyo-Ramírez, I. Machorro-Cano and J. L. Sánchez-Cervantes, “Cuff-less estimation of blood pressure and detection of hypertension/arteriosclerosis from fingertip ppg using machine learning: An experimental study,” Applied Sciences, vol. 15, no. 21, p. 11829, 2025.
[25] G. Slapničar, N. Mlakar, and M. Luštrek, “Blood pressure estimation from photoplethysmogram using a spectro-temporal deep neural network,” Sensors, vol. 19, no. 15, p. 3420, 2019.
[26] K. Sel, A. Mohammadi, R. I. Pettigrew, and R. Jafari, “Physics-informed neural networks for modeling physiological time series for cuffless blood pressure estimation,” npj Digit. Med., vol. 6, no. 1, p. 110, 2023.
[27] D. C. K. S. et al., “A computational intelligence tool for the detection of hypertension using empirical mode decomposition,” Computers in Biology and Medicine, vol. 118, p. 103630, 2020.
[28] M. N. I. S. M. E. H. C. Z. B. M. M. M. U. A. K. M. B. I. R. M. H. Chowdhury, “Estimating blood pressure from the photoplethysmogram signal and demographic features using machine learning techniques,” Sensors, vol. 20, no. 11, 2020.
[29] A. F. et al., “A novel clustering-based algorithm for continuous and accurate blood pressure monitoring,” Journal of Healthcare Engineering, vol. 2022, 2022.
[30] S. S. M. et al., “Cuff-less blood pressure estimation using only the ecg signal in frequency domain,” IEEE Xplore, 2018.
[31] M. R. H. et al., “A novel technique for non-invasive measurement of human blood component levels from fingertip video using dnn-based models,” IEEE Access, vol. 9, pp. 19025–19042, 2021.
[32] T. G. Thambiraj, U. Gandhi, U. Mangalanathan, V. J. M. Jose, and M. Anand, “Investigation on the effect of womersley number, ecg and ppg features for cuffless blood pressure estimation using machine learning,” Biomedical Signal Processing and Control, vol. 60, p. 101942, 2020.
[33] F. M. et al., “Continuous blood pressure measurement from one-channel electrocardiogram signal using deep learning techniques,” Artificial Intelligence in Medicine, vol. 108, p. 101919, 2020.
[34] Y. Zhang and Z. Feng, “A svm method for continuous blood pressure estimation from a ppg signal,” in Proc. 9th Int. Conf. Mach. Learn. Comput., pp. 128–132, 2017.
[35] F. C. M. El-Hajj and P. A. Kyriacou, “Cuffless blood pressure estimation from ppg signals and its derivatives using deep learning models,” Biomedical Signal Processing and Control, vol. 70, p. 102984, 2021.
