Classification of Hypertension Using Support Vector Machine Based on Data Photoplethysmography and Blood Pressure Estimator

##plugins.themes.academic_pro.article.sidebar##

Published Oct 29, 2025
https://doi.org/10.34012/jutikomp.v8i2.7658
Download
PDF
Statistic
Vol. 8 No. 2 (2025): Jurnal Teknologi dan Ilmu Komputer Prima (JUTIKOMP)

##plugins.themes.academic_pro.article.main##

Glen Virdho Sirait
Universitas Prima Indonesia
Anand Roshan
Universitas Prima Indonesia
Delima Sitanggang
Universitas Prima Indonesia
Reyhan Achmad Rizal
Universitas Prima Indonesia

Abstract

This study formulates a Support Vector Machine (SVM)-based hypertension classification model using physiological features from Photoplethysmograph (PPG) signals and systolicdiastolic blood pressure estimates. PPG data were collected from 276 participants in three locations using a non-invasive device integrated into the MR-IAT Robot Covid web platform. Feature extraction and preprocessing were performed in MATLAB, while SVM (scikit-learn) model training and testing were conducted in Google Colab. Comparison of three kernel variants—linear, quadratic, and cubic—showed that the cubic kernel was the most superior with an accuracy of 96.4%, followed by quadratic at 94.9% and linear at 91.3%. Overall, the model achieved 93.9% accuracy in distinguishing six blood pressure categories (Hypotension, Normal, Prehypertension, Stage 1 Hypertension, Stage 2 Hypertension, Crisis). Visualization of the results (scatter plot, confusion matrix, parallel coordinates) revealed that systolic pressure, diastolic pressure, age, weight, and respiration rate were the most influential parameters. These findings underscore the potential application of SVM in portable devices for early detection and real-time monitoring of hypertension.

##plugins.themes.academic_pro.article.details##

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

How to Cite
Sirait, G. V., Roshan, A., Sitanggang, D., & Rizal, R. A. (2025). Classification of Hypertension Using Support Vector Machine Based on Data Photoplethysmography and Blood Pressure Estimator. JURNAL TEKNOLOGI DAN ILMU KOMPUTER PRIMA (JUTIKOMP), 8(2), 162–172. https://doi.org/10.34012/jutikomp.v8i2.7658

References

  1. Arulselvi, R., Jeyakumar, V., Vidya, N. G., Krishna Kumar, G. M., & Lakshmi, M. (2024, December). Remote blood pressure measurement through facial PPG signals. In TENCON 2024 – 2024 IEEE Region 10 Conference (TENCON) (pp. 1143–1146). IEEE. https://doi.org/10.1109/TENCON61640.2024.10903082
  2. Dehghanojamahalleh, S., & Kaya, M. (2019). Sex-related differences in photoplethysmography signals measured from finger and toe. IEEE Journal of Translational Engineering in Health and Medicine, 7. https://doi.org/10.1109/JTEHM.2019.2938506
  3. Dwaish, H., & Miften, F. S. (2025, March). Enhancing blood pressure estimation accuracy using photoplethysmography and machine learning. In IET Conference Proceedings (Vol. 2024, No. 34, pp. 250–255). IET. https://doi.org/10.1049/icp.2025.0091
  4. Dwaish, M. F. S. (2024). Least squares SVM for accurate BP classification. In IET Conference Proceedings. IET. https://doi.org/10.1049/icp.2025.0091
  5. Fuadah, Y. N., & Lim, K. M. (2022). Classification of blood pressure levels based on photoplethysmogram and electrocardiogram signals with a concatenated convolutional neural network. Diagnostics, 12(11), 2886. https://doi.org/10.3390/diagnostics12112886
  6. Jeyakumar. (2024). SVM-based classification for remote photoplethysmography. In IEEE TENCON 2024. IEEE. https://doi.org/10.1109/TENCON55214.2024.10903082
  7. Kim, B. J., Lee, S. H., Lee, M. Y., Lee, S. J., & Choi, H. I. (2023). Comparison of office blood pressure, automated unattended office blood pressure, home blood pressure, and 24-hour ambulatory blood pressure measurements. Journal of Korean Medical Science, 38(48), e406. https://doi.org/10.3346/jkms.2023.38.e406
  8. M., M., N. P. M., & Cigi, J. J. (2024). Comparison of PPG signal analysis methods for hypertension detection. In IEEE EMBC 2024. IEEE. https://doi.org/10.1109/EMBC51015.2024.10782610
  9. M., P., J., J., & Nabeel, C. M. (2024). Machine learning approaches for blood pressure classification from photoplethysmogram: A comparative analysis. In IEEE EMBC 2024. IEEE. https://doi.org/10.1109/EMBC51015.2024.10782610
  10. Martínez, D. C., Villegas, D. F., Sarmiento, J. D., & Bayona, J. F. (2025, April). Evaluating the discriminative power of cardiovascular and PPG-derived biomarkers for blood pressure classification: A machine learning approach. In 2025 Global Medical Engineering Physics Exchanges/Pan American Health Care Exchanges (GMEPE/PAHCE) (pp. 1–1). IEEE. https://doi.org/10.1109/GMEPE/PAHCE65777.2025.11002828
  11. Martínez-Ríos, E., Montesinos, L., & Alfaro-Ponce, M. (2022). A machine learning approach for hypertension detection based on photoplethysmography and clinical data. Computers in Biology and Medicine, 145, 105479. https://doi.org/10.1016/j.compbiomed.2022.105479
  12. Mejía-Mejía, E., Budidha, K., Kyriacou, P. A., & Mamouei, M. (2022, September). Comparison of pulse rate variability and morphological features of photoplethysmograms in estimation of blood pressure. Biomedical Signal Processing and Control, 78, 103968. https://doi.org/10.1016/j.bspc.2022.103968
  13. Raj, P. S. (2023). SVM-based multi-class classification of blood pressure levels using PPG signals. Bioengineering Research Journal. https://doi.org/10.3390/bioengineering10040278
  14. S., & Bafandeh, B. M. (2021). Application of K-nearest neighbor (KNN) for economic forecasting under data imbalance conditions. International Journal of Engineering Research and Applications. https://doi.org/10.9790/9622-1101022430
  15. Singh, A. (2023). Real-time SVM-based blood pressure monitoring system. Artificial Intelligence in Medicine. https://doi.org/10.1016/j.artmed.2023.102471
  16. Sorelli, M., Stoyneva, Z., Mizeva, I., & Bocchi, L. (2017, May). Spatial heterogeneity in the time and frequency properties of skin perfusion. Physiological Measurement, 38(5), 860–876. https://doi.org/10.1088/1361-6579/aa5909
  17. Tjahjadi, H., & Ramli, K. (2020, February). Noninvasive blood pressure classification based on photoplethysmography using K-nearest neighbors algorithm: A feasibility study. Information (Switzerland), 11(2), 93. https://doi.org/10.3390/info11020093
  18. Villegas, D. F. (2025). Facial PPG for blood pressure estimation. In IEEE GMEC 2025. IEEE. https://doi.org/10.1109/GMEC59095.2025.11002828
  19. Wang, D., Yang, X., Liu, X., Fang, S., Ma, L., & Li, L. (2020, June). Photoplethysmography-based stratification of blood pressure using multi-information fusion artificial neural network. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (pp. 1113–1119). IEEE. https://doi.org/10.1109/CVPRW50498.2020.00146
  20. Yunifar, R. I., et al. (2021, March). Heart rate measurement using optical sensor based on self-mixing interferometry and photoplethysmography (PPG). Journal of Physics: Conference Series, 1505(1), 012072. https://doi.org/10.1088/1742-6596/1505/1/012072

Similar Articles

1 2 3 > >> 

You may also start an advanced similarity search for this article.