Skip to main content

Advertisement

Springer Nature Link
Log in

A non-invasive heart rate prediction method using a convolutional approach

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

The research focuses on leveraging convolutional neural networks (CNNs) to enhance the analysis of physiological signals, specifically photoplethysmogram (PPG) data which is a valuable tool for non-invasive heart rate prediction. Recognizing the global challenge of heart failure, the study seeks to provide a rapid, accurate, and non-invasive alternative to traditional, uncomfortable blood pressure cuffs. To achieve more accurate and efficient heart rate estimates, a k-fold CNN model with an optimal number of convolutional layers is employed. While the findings show promising results, the study addresses potential sources of error in cuffless PPG-based heart rate measurement, including motion artifacts and skin color variations, emphasizing the need for validation against gold standard methods. The research optimizes a CNN model with optimal layers, operating on 1D arrays of 8-s data slices and employing k-fold cross-validation to mitigate probabilistic uncertainties. Finally, the model yields a remarkable minimum absolute error (MAE) rate of 6.98 beats per minute (bpm), marking a significant 10% improvement over recent studies. The study also advances medical diagnostics and data analysis, then lays a strong foundation for developing cost-effective, reliable devices that offer a more comfortable and efficient way of predicting heart rate.

Graphical abstract

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
Algorithm 1
Fig. 6
Fig. 7

Similar content being viewed by others

Availability of data and materials

Any data and material can be presented as desired.

Code availibility

Code is available upon request.

References

  1. Parati G, Ongaro G, Bilo G, Glavina F, Castiglioni P, Di Rienzo M, Mancia G (2003) Non-invasive beat-to-beat blood pressure monitoring: new developments. Blood Pressure Monitor 8(1):31–36

  2. Yen C-T, Chang S-N, Liao C-H (2022) Estimation of beat-by-beat blood pressure and heart rate from ECG and ppg using a fine-tuned deep CNN model. IEEE Access

  3. 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 

  4. Shuzan MNI, Chowdhury MH, Hossain MS, Chowdhury ME, Reaz MBI, Uddin MM, Khandakar A, Mahbub ZB, Ali SHM (2021) A novel non-invasive estimation of respiration rate from motion corrupted photoplethysmograph signal using machine learning model. IEEE Access 9:96775–96790

    Article  Google Scholar 

  5. Hamedani NE, Sadredini SZ, Khodabakhshi MB (2021) A CNN model for cuffless blood pressure estimation from nonlinear characteristics of PPG signals. In: 2021 28th National and 6th International Iranian Conference on Biomedical Engineering (ICBME), IEEE, pp 228–235

  6. Yavarimanesh M, Block RC, Natarajan K, Mestha LK, Inan OT, Hahn J-O, Mukkamala R (2021) Assessment of calibration models for cuff-less blood pressure measurement after one year of aging. IEEE Trans Biomed Eng 69(6):2087–2093

    Article  Google Scholar 

  7. Aguirregomezcorta IB, Blazek V, Leonhardt S, Antink CH (2021) Learning about reflective ppg for spo2 determination using machine learning. Current Directions Biomed Eng 7(2):33–36

    Article  Google Scholar 

  8. Berwal D, Kuruba A, Shaikh AM, Udupa A, Baghini MS (2022) Spo2 measurement: non-idealities and ways to improve estimation accuracy in wearable pulse oximeters. IEEE Sensors J

  9. Paliakaitė B, Charlton PH, Rapalis A, Pluščiauskaitė V, Piartli P, Kaniusas E, Marozas V (2021) Blood pressure estimation based on photoplethysmography: finger versus wrist. In: 2021 Computing in Cardiology (CinC), IEEE, vol 48, pp 1–4

  10. Lee I, Park N, Lee H, Hwang C, Kim JH, Park S (2021) Systematic review on human skin-compatible wearable photoplethysmography sensors. Appl Sci 11(5):2313

    Article  CAS  Google Scholar 

  11. Mena LJ, Felix VG, Ostos R, Gonzalez AJ, Martinez-Pelaez R, Melgarejo JD, Maestre GE (2020) Mobile personal healthcare system for non-invasive, pervasive and continuous blood pressure monitoring: a feasibility study. JMIR Mhealth and Uhealth

  12. Seok D, Lee S, Kim M, Cho J, Kim C (2021) Motion artifact removal techniques for wearable EEG and PPG sensor systems. Front Electron 2:685513

  13. Labati RD, Piuri V, Rundo F, Scotti F (2022) Photoplethysmographic biometrics: a comprehensive survey. Pattern Recognition Lett

  14. Lin Q, Van Helleptte N (2021) Ppg sensors for the new normal: a review. In: 2021 18th International SoC Design Conference (ISOCC), IEEE, pp 276–277

  15. Zhang G, Shin S, Jung J (2023) Cascade forest regression algorithm for non-invasive blood pressure estimation using PPG signals. Appl Soft Comput 110520

  16. Gupta S, Singh A, Sharma A (2023) Exploiting moving slope features of PPG derivatives for estimation of mean arterial pressure. Biomed Eng Lett 13(1):1–9

    Article  PubMed  Google Scholar 

  17. Johansson A (2003) Neural network for photoplethysmographic respiratory rate monitoring. Med Biological Eng Comput 41:242–248

  18. Jeong DU, Lim KM (2021) Combined deep CNN-LSTM network-based multitasking learning architecture for noninvasive continuous blood pressure estimation using difference in ECG-PPG features. Sci Rep 11(1):1–8

  19. Sevinç E (2022) An empowered adaboost algorithm implementation: a COVID-19 dataset study. Comput Industrial Eng 165:107912

  20. Sharma A, Tanwar RS, Singh Y, Sharma A, Daudra S, Singal G, Gadekallu TR, Pancholi S (2022) Heart rate and blood pressure measurement based on photoplethysmogram signal using fast Fourier transform. Comput Electrical Eng 101:108057

  21. Salehizadeh SM, Dao D, Bolkhovsky J, Cho C, Mendelson Y, Chon KH (2015) A novel time-varying spectral filtering algorithm for reconstruction of motion artifact corrupted heart rate signals during intense physical activities using a wearable photoplethysmogram sensor. Sensors 16(1):10

    Article  PubMed  PubMed Central  Google Scholar 

  22. Reiss A, Schmidt P, Indlekofer I, Van Laerhoven K (2018) Ppg-based heart rate estimation with time-frequency spectra: a deep learning approach. In: Proceedings of the 2018 ACM international joint conference and 2018 international symposium on pervasive and ubiquitous computing and wearable computers, pp 1283–1292

  23. Schäck T, Muma M, Zoubir AM (2017) Computationally efficient heart rate estimation during physical exercise using photoplethysmographic signals. In: 2017 25th European signal processing conference (EUSIPCO), IEEE, pp 2478–2481

  24. Reiss A, Indlekofer I, Schmidt P, Van Laerhoven K (2019) Deep ppg: large-scale heart rate estimation with convolutional neural networks. Sensors 19(14):3079

    Article  PubMed  PubMed Central  Google Scholar 

  25. Moraes JL, Rocha MX, Vasconcelos GG, Vasconcelos Filho JE, De Albuquerque VHC, Alexandria AR (2018) Advances in photopletysmography signal analysis for biomedical applications. Sensors 18(6):1894

  26. UCI machine learning repository (2022). http://archive.ics.uci.edu/ml/datasets.php

  27. Deep PPG: Large-scale heart rate estimation with convolutional neural networks (2022). https://ubicomp.eti.uni-siegen.de/home/datasets/sensors19/

  28. Sevinc E (2018) Activation functions in single hidden layer feed-forward neural networks. Selcuk University J Eng Sci 1–13

Download references

Funding

This study is not funded by any party. There is no conflict of interest related to this publication and there is no financial support that influenced the outcome.

Author information

Author notes

  1. Ender Sevinc contributed equally to this work.

Authors and Affiliations

  1. Elect. Eng. Department, Ankara Science University, Maltepe Mah. Sehit Gonenc Cad. No:5, Ankara, 06570, Turkey

    Ercument Karapinar

  2. Comp. Eng. Department, Ankara Science University, Maltepe Mah. Sehit Gonenc Cad. No:5, Ankara, 06570, Turkey

    Ender Sevinc

Authors
  1. Ercument Karapinar
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Ender Sevinc
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

Authors have equally contributed to the study.

Corresponding author

Correspondence to Ender Sevinc.

Ethics declarations

Ethics approval

This study does not involve studies with human or animal subjects and has no content involving animal or human studies that would require informed consent.

Consent to participate

Both authors consent for participate.

Consent for publication

Both authors consent for publication.

Conflict of interest

The two authors have read and approved the entire text and declared that there are no other persons who meet the criteria for authorship. They also declare that there is no conflict of interest with any party directly or indirectly related to the research.

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

Karapinar, E., Sevinc, E. A non-invasive heart rate prediction method using a convolutional approach. Med Biol Eng Comput 63, 901–914 (2025). https://doi.org/10.1007/s11517-024-03217-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-024-03217-6

Keywords