Skip to main content

Advertisement

Springer Nature Link
Log in

Blood pressure estimation and classification using a reference signal-less photoplethysmography signal: a deep learning framework

  • Scientific Paper
  • Published:
Physical and Engineering Sciences in Medicine Aims and scope Submit manuscript

Abstract

The markers that help to predict th function of a cardiovascular system are hemodynamic parameters like blood pressure (BP), stroke volume, heart rate, and cardiac output. Continuous analysis of hemodynamic parameters such as BP can detect abnormalities earlier, preventing cardiovascular diseases (CVDs). However, sometimes due to motion artifacts, it becomes difficult to monitor the BP accurately and classify it. This work presents an optimized deep learning model having the capability to estimate the systolic blood pressure (SBP) and diastolic blood pressure (DBP) and classify the BP stages simultaneously from the same network using only a single channel photoplethysmography (PPG) signal. The proposed model is designed by exploiting the deep learning framework of a convolutional neural network (CNN), exhibiting the inherent ability to extract features automatically. Moreover, the proposed framework utilizes the superlet transform method to transform a 1-D PPG signal into a 2-D super-resolution time–frequency (TF) spectrogram. A superlet transform separates the peaks related to true PPG signal components and motion artifacts components. Thus, the superlet provides a robust realtime approach to accurately estimating and classifying BP using a single PPG sensor signal and does not require additional ECG and PPG sensor signals for reference. Using a super-resolution spectrogram and CNN model makes the method profitable in motion artifact removal, feature selection, and extraction. Hence the proposed framework becomes less complex for deployment on wearable devices having limited battery resources. The performance of the proposed framework is demonstrated on the publicly available larger dataset MIMIC-III. This work obtained a mean absolute error (MAE) of 2.71 mmHg and 2.42 mmHg for SBP and DBP, respectively. The classification accuracy for the SBP prediction is about 96.79%, whereas it is 98.94% for DBP. From a motion artifact-affected PPG signal, SBP and DBP are estimated. Then the estimated BP is classified into three categories: normotension, prehypertension, and hypertension, and is compared with the state of art methods to show the effectiveness of the proposed optimized framework.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Explore related subjects

Discover the latest articles and news from researchers in related subjects, suggested using machine learning.

References

  1. Esgalhado F, Fernandes B, Vassilenko V, Batista A, Russo S (2021) The application of deep learning algorithms for PPG signal processing and classification. Computers 10(12):1–15. https://doi.org/10.3390/computers10120158

    Article  Google Scholar 

  2. Sharma M et al (2017) Cuff-less and continuous blood pressure monitoring: a methodological review. Technologies (Basel) 5(2):21. https://doi.org/10.3390/technologies5020021

    Article  Google Scholar 

  3. Pankaj, Kumar A, Komaragiri R, Kumar M (2022) A review on computation methods used in photoplethysmography signal analysis for heart rate estimation. Arch Comput Methods Eng 29(2):921–940. https://doi.org/10.1007/s11831-021-09597-4

  4. Ismail SNA, Nayan NA, Jaafar R, May Z (2022) Recent advances in non-invasive blood pressure monitoring and prediction using a machine learning approach. Sensors. https://doi.org/10.3390/s22166195

    Article  PubMed  PubMed Central  Google Scholar 

  5. Pankaj, Kumar A, Komaragiri R, Kumar M (2023) Optimized deep neural network models for blood pressure classification using Fourier analysis-based time–frequency spectrogram of photoplethysmography signal. Biomed Eng Lett. https://doi.org/10.1007/s13534-023-00296-6

  6. Wang R, Jia W, Mao ZH, Sclabassi RJ, Sun M (2014) Cuff-free blood pressure estimation using pulse transit time and heart rate. In: International conference on signal processing proceedings (ICSP). Institute of Electrical and Electronics Engineers Inc., pp 115–118. https://doi.org/10.1109/ICOSP.2014.7014980

  7. Ganti VG, Carek AM, Nevius BN, Heller JA, Etemadi M, Inan OT (2021) Wearable cuff-less blood pressure estimation at home via pulse transit time. IEEE J Biomed Health Inform 25(6):1926–1937. https://doi.org/10.1109/JBHI.2020.3021532

    Article  PubMed  PubMed Central  Google Scholar 

  8. Byfield R, Miller M, Miles J, Guidoboni G, Lin J (2022) Towards robust blood pressure estimation from pulse wave velocity measured by photoplethysmography sensors. IEEE Sens J 22(3):2475–2483. https://doi.org/10.1109/JSEN.2021.3134890

    Article  CAS  Google Scholar 

  9. Fotiadis DI et al (2018) Biomedical and health informatics and the body sensor networks conferences, 4–7 March 2018, Treasure Island Hotel, Las Vegas

  10. Liu W et al (2022) A wearable and flexible photoplethysmogram sensor patch for cuffless blood pressure estimation with high accuracy. IEEE Sens J 22(20):19818–19825. https://doi.org/10.1109/JSEN.2022.3202803

    Article  Google Scholar 

  11. Yang S, Sohn J, Lee S, Lee J, Kim HC (2021) Estimation and validation of arterial blood pressure using photoplethysmogram morphology features in conjunction with pulse arrival time in large open databases. IEEE J Biomed Health Inform 25(4):1018–1030. https://doi.org/10.1109/JBHI.2020.3009658

    Article  PubMed  Google Scholar 

  12. Zhang Y, Zhang X, Cui P, Li S, Tang J (2021) Key feature selection and model analysis for blood pressure estimation from electrocardiogram, ballistocardiogram and photoplethysmogram. IEEE Access 9:54350–54359. https://doi.org/10.1109/ACCESS.2021.3070636

    Article  Google Scholar 

  13. Li P, Laleg-Kirati TM (2021) Central blood pressure estimation from distal PPG measurement using semiclassical signal analysis features. IEEE Access 9:44963–44973. https://doi.org/10.1109/ACCESS.2021.3065576

    Article  Google Scholar 

  14. Yao P et al (2022) Multi-dimensional feature combination method for continuous blood pressure measurement based on wrist PPG sensor. IEEE J Biomed Health Inform 26(8):3708–3719. https://doi.org/10.1109/JBHI.2022.3167059

    Article  PubMed  Google Scholar 

  15. Gupta S, Singh A, Sharma A, Tripathy RK (2022) Higher order derivative-based integrated model for cuff-less blood pressure estimation and stratification using PPG signals. IEEE Sens J 22(22):22030–22039. https://doi.org/10.1109/JSEN.2022.3211993

    Article  Google Scholar 

  16. Dey J, Gaurav A, Tiwari VN (2018) InstaBP: cuff-less blood pressure monitoring on smartphone using single PPG sensor. In: Annual international conference of the IEEE engineering in medicine and biology—proceedings. https://doi.org/10.1109/EMBC.2018.8513189

  17. Chakraborty A, Goswami D, Mukhopadhyay J, Chakrabarti S (2021) Measurement of arterial blood pressure through single-site acquisition of photoplethysmograph signal. IEEE Trans Instrum Meas. https://doi.org/10.1109/TIM.2020.3011304

    Article  Google Scholar 

  18. Cardoso GS, Lucas MG, Cardoso SS, Ruzicki JCM, Junior AAS (2022) Using PPG and machine learning to measure blood pressure. In: Bastos-Filho TF, de Oliveira Caldeira EM, Frizera-Neto A (eds) XXVII Brazilian congress on biomedical engineering. Springer, Cham, pp 1909–1915

    Chapter  Google Scholar 

  19. Wang D, Yang X, Liu X, Ma L, Li L, Wang W (2021) Photoplethysmography-based blood pressure estimation combining filter-wrapper collaborated feature selection with LASSO-LSTM Model. IEEE Trans Instrum Meas. https://doi.org/10.1109/TIM.2021.3109986

    Article  PubMed  PubMed Central  Google Scholar 

  20. Ruiz-Rodríguez JC et al (2013) Innovative continuous non-invasive cuffless blood pressure monitoring based on photoplethysmography technology. Intensive Care Med. https://doi.org/10.1007/s00134-013-2964-2

    Article  PubMed  Google Scholar 

  21. Panwar M, Gautam A, Biswas D, Acharyya A (2020) PP-Net: a deep learning framework for PPG-based blood pressure and heart rate estimation. IEEE Sens J 20(17):10000–10011

    Article  Google Scholar 

  22. Esgalhado F, Fernandes B, Vassilenko V, Batista A, Russo S (2021) The application of deep learning algorithms for ppg signal processing and classification. Computers. https://doi.org/10.3390/computers10120158

    Article  Google Scholar 

  23. Chen Y, Zhang D, Karimi HR, Deng C, Yin W (2022) A new deep learning framework based on blood pressure range constraint for continuous cuffless BP estimation. Neural Netw 152:181–190

    Article  PubMed  Google Scholar 

  24. Yen CT, Chang SN, Liao CH (2022) Estimation of Beat-by-beat blood pressure and heart rate from ECG and PPG Using a fine-tuned deep CNN model. IEEE Access 10:85459–85469. https://doi.org/10.1109/ACCESS.2022.3195857

    Article  Google Scholar 

  25. Leitner J, Chiang PH, Dey S (2022) Personalized blood pressure estimation using photoplethysmography: a transfer learning approach. IEEE J Biomed Health Inform 26(1):218–228. https://doi.org/10.1109/JBHI.2021.3085526

    Article  PubMed  Google Scholar 

  26. Wang W, Mohseni P, Kilgore KL, Najafizadeh L (2022) Cuff-less blood pressure estimation from photoplethysmography via visibility graph and transfer learning. IEEE J Biomed Health Inform 26(5):2075–2085. https://doi.org/10.1109/JBHI.2021.3128383

    Article  PubMed  Google Scholar 

  27. Song K, Chung KY, Chang JH (2020) Cuffless deep learning-based blood pressure estimation for smart wristwatches. IEEE Trans Instrum Meas 69(7):4292–4302. https://doi.org/10.1109/TIM.2019.2947103

    Article  Google Scholar 

  28. Yen CT, Liao JX, Huang YK (2022) Applying a deep learning network in continuous physiological parameter estimation based on photoplethysmography sensor signals. IEEE Sens J 22(1):385–392. https://doi.org/10.1109/JSEN.2021.3126744

    Article  Google Scholar 

  29. Athaya T, Choi S (2021) An estimation method of continuous non-invasive arterial blood pressure waveform using photoplethysmography: a u-net architecture-based approach. Sensors 21(5):1–18. https://doi.org/10.3390/s21051867

    Article  Google Scholar 

  30. Kim DK, Kim YT, Kim H, Kim DJ (2022) DeepCNAP: a deep learning approach for continuous non-invasive arterial blood pressure monitoring using photoplethysmography. IEEE J Biomed Health Inform 26(8):3697–3707. https://doi.org/10.1109/JBHI.2022.3172514

    Article  PubMed  Google Scholar 

  31. Qiu S, Zhang YT, Lau SK, Zhao N (2022) Scenario adaptive cuffless blood pressure estimation by integrating cardiovascular coupling effects. IEEE J Biomed Health Inform. https://doi.org/10.1109/JBHI.2022.3227235

    Article  PubMed  Google Scholar 

  32. Pankaj, Kumar A, Komaragiri R, Kumar M (2023) A novel CS-NET architecture based on the unification of CNN, SVM and super-resolution spectrogram to monitor and classify blood pressure using photoplethysmography. Comput Methods Programs Biomed 240:107716. https://doi.org/10.1016/j.cmpb.2023.107716

  33. Johnson AEW et al (2016) Data descriptor : MIMIC-III, a freely accessible critical care database. Sci Data 3:1–9

    Article  Google Scholar 

  34. Arunkumar KR, Bhasker M (2020) Heart rate estimation from wrist-type photoplethysmography signals during physical exercise. Biomed Signal Process Control. https://doi.org/10.1016/j.bspc.2019.101790

    Article  Google Scholar 

  35. Pankaj, Kumar A, Kumar M, Komaragiri R (2022) STSR: spectro-temporal super-resolution analysis of a reference signal less photoplethysmogram for heart rate estimation during physical activity. IEEE Trans Instrum Meas 71:1–10. https://doi.org/10.1109/TIM.2022.3192831

  36. Tanveer MS, Hasan MK (2019) Cuffless blood pressure estimation from electrocardiogram and photoplethysmogram using waveform based ANN-LSTM network. Biomed Signal Process Control 51:382–392

    Article  Google Scholar 

  37. Yan C et al (2019) Novel deep convolutional neural network for cuff-less blood pressure measurement using ECG and PPG signals. In: 2019 41st Annual international conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE, pp 1917–1920

  38. Slapničar G, Mlakar N, Luštrek M (2019) Blood pressure estimation from photoplethysmogram using a spectro-temporal deep neural network. Sensors (Switzerland). https://doi.org/10.3390/s19153420

    Article  Google Scholar 

  39. Baek S, Jang J, Yoon S (2019) End-to-end blood pressure prediction via fully convolutional networks. IEEE Access 7:185458–185468. https://doi.org/10.1109/ACCESS.2019.2960844

    Article  Google Scholar 

  40. Eom H et al (2020) End-to-end deep learning architecture for continuous blood pressure estimation using attention mechanism. Sensors (Switzerland). https://doi.org/10.3390/s20082338

    Article  Google Scholar 

  41. Hsu YC, Li YH, Chang CC, Harfiya LN (2020) Generalized deep neural network model for cuffless blood pressure estimation with photoplethysmogram signal only. Sensors (Switzerland) 20(19):1–18. https://doi.org/10.3390/s20195668

    Article  Google Scholar 

  42. Li YH, Harfiya LN, Purwandari K, der Lin Y (2020) Real-time cuffless continuous blood pressure estimation using deep learning model. Sensors (Switzerland) 20(19):1–19. https://doi.org/10.3390/s20195606

    Article  Google Scholar 

  43. Aguirre N, Grall-Maës E, Cymberknop LJ, Armentano RL (2021) Blood pressure morphology assessment from photoplethysmogram and demographic information using deep learning with attention mechanism. Sensors 21(6):1–19. https://doi.org/10.3390/s21062167

    Article  Google Scholar 

  44. Lee D et al (2021) Beat-to-beat continuous blood pressure estimation using bidirectional long short-term memory network. Sensors (Switzerland) 21(1):1–15. https://doi.org/10.3390/s21010096

    Article  CAS  Google Scholar 

  45. Harfiya LN, Chang CC, Li YH (2021) Continuous blood pressure estimation using exclusively photopletysmography by lstm-based signal-to-signal translation. Sensors. https://doi.org/10.3390/s21092952

    Article  PubMed  PubMed Central  Google Scholar 

  46. Mahmud S et al (2022) A shallow U-Net architecture for reliably predicting blood pressure (BP) from photoplethysmogram (PPG) and electrocardiogram (ECG) signals. Sensors 22(3):919

    Article  PubMed  PubMed Central  Google Scholar 

  47. Rastegar S, Gholam Hosseini H, Lowe A (2023) Hybrid CNN-SVR blood pressure estimation model using ECG and PPG signals. Sensors. https://doi.org/10.3390/s23031259

    Article  PubMed  PubMed Central  Google Scholar 

  48. Nour M, Polat K, Şentürk Ü, Arıcan M (2023) A novel cuffless blood pressure prediction: uncovering new features and new hybrid ML models. Diagnostics. https://doi.org/10.3390/diagnostics13071278

    Article  PubMed  PubMed Central  Google Scholar 

  49. Qin C, Li Y, Liu C, Ma X (2023) Cuff-less blood pressure prediction based on photoplethysmography and modified ResNet. Bioengineering 10(4):400. https://doi.org/10.3390/bioengineering10040400

    Article  PubMed  PubMed Central  Google Scholar 

  50. Kachuee M, Kiani MM, Mohammadzade H, Shabany M (2017) Cuffless blood pressure estimation algorithms for continuous healthcare monitoring. IEEE Trans Biomed Eng 64(4):859–869. https://doi.org/10.1109/TBME.2016.2580904

    Article  PubMed  Google Scholar 

  51. El-Hajj C, Kyriacou PA (2021) Cuffless blood pressure estimation from PPG signals and its derivatives using deep learning models. Biomed Signal Process Control. https://doi.org/10.1016/j.bspc.2021.102984

    Article  Google Scholar 

  52. Cheng J, Xu Y, Song R, Liu Y, Li C, Chen X (2021) Prediction of arterial blood pressure waveforms from photoplethysmogram signals via fully convolutional neural networks. Comput Biol Med 138:104877. https://doi.org/10.1016/j.compbiomed.2021.104877

    Article  PubMed  Google Scholar 

  53. Ibtehaz N, Rahman MS (2020) PPG2ABP: translating photoplethysmogram (PPG) signals to arterial blood pressure (ABP) waveforms using fully convolutional neural networks. ArXiv Preprint. https://arxiv.org/abs/2005.01669

  54. Treebupachatsakul T, Boosamalee A, Shinnakerdchoke S, Pechprasarn S, Thongpance N (2022) Cuff-less blood pressure prediction from ECG and PPG signals using fourier transformation and amplitude randomization pre-processing for context aggregation network training. Biosensors (Basel). https://doi.org/10.3390/bios12030159

    Article  PubMed  Google Scholar 

Download references

Funding

No funding available.

Author information

Authors and Affiliations

  1. Department of Electronics and Communication Engineering, Bennett University, Greater Noida, India

    Pankaj, Ashish Kumar & Rama Komaragiri

  2. School of Computer science engineering and technology, Bennett University, Greater Noida, India

    Ashish Kumar

  3. Department of Electronics and Communication Engineering, Delhi Technological University, Delhi, India

    Manjeet Kumar

Authors
  1. Pankaj
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Ashish Kumar
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Rama Komaragiri
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Manjeet Kumar
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Manjeet Kumar.

Ethics declarations

Conflict of interest

All Authors of this work declare no conflict of interest.

Ethical approval

This article contains no studies with human participants or animals performed by authors.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Pankaj, Kumar, A., Komaragiri, R. et al. Blood pressure estimation and classification using a reference signal-less photoplethysmography signal: a deep learning framework. Phys Eng Sci Med 46, 1589–1605 (2023). https://doi.org/10.1007/s13246-023-01322-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13246-023-01322-8

Keywords