Implementation of CNN-SVM with Index Pattern-Based Feature Selection on PPG Signals for Cuffless Hypertension Detection

Dafina Nazhifah, Wiharto Wiharto, Fajar Muslim

Abstract

Hypertension is one of the leading causes of death worldwide and often goes undetected due to its minimal symptoms. Early detection is crucial, and one non-invasive method involves the use of photoplethysmogram (PPG) signals. However, PPG signals contain a large number of features, which can lead to information redundancy and decreased model performance. This study proposes a hypertension detection system based on a CNN-SVM combination, preceded by feature selection using position-based indices (odd, even, specific multiples) to reduce data dimensionality and accelerate computation. The PPG signal dataset was obtained from 216 patients at UNS Hospital. After preprocessing and feature selection, feature extraction was performed using a Convolutional Neural Network (CNN), followed by classification using a Support Vector Machine (SVM). The model was evaluated under three classification scenarios: binary classification (normal vs. prehypertensive-hypertension and normal-prehypertension vs. hypertension) and three-class classification (normal, prehypertension, hypertension). The best classification accuracy achieved was 93.10% for the normal vs. prehypertension-hypertension scenario, 88.38% for normal-prehypertension vs. hypertension, and 82.79% for the three-class classification. This approach demonstrates that the combination of CNN-SVM with simple feature selection can improve both accuracy and efficiency in PPG-based hypertension detection.

Keywords

Hypertension Detection; Photoplethysmogram (PPG); CNN-SVM; Index-Based Selection; Cuffless Monitoring

Full Text:

PDF

References

1 Gupta, K., Bajaj, V., & Ansari, I. A. (2023). A support system for automatic classification of hypertension using BCG signals. Expert Systems with Applications, 214, 119058. https://doi.org/https://doi.org/10.1016/j.eswa.2022.119058

2 Martinez-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/https://doi.org/10.1016/j.compbiomed.2022.105479

3 El-Hajj, C., & Kyriacou, P. A. (2020). A review of machine learning techniques in photoplethysmography for the non-invasive cuff-less measurement of blood pressure. Biomedical Signal Processing and Control, 58, 101870. https://doi.org/https://doi.org/10.1016/j.bspc.2020.101870

4 Koparır, H. M., & Arslan, Ö. (2024). Cuffless blood pressure estimation from photoplethysmography using deep convolutional neural network and transfer learning. Biomedical Signal Processing and Control, 93, 106194. https://doi.org/https://doi.org/10.1016/j.bspc.2024.106194

5 Chowdhury, A., Das, D., Eldaly, A. B. M., Cheung, R. C. C., & Chowdhury, M. H. (2024). Photoplethysmogram-based heart rate and blood pressure estimation with hypertension classification. IPEM-Translation, 9, 100024. https://doi.org/https://doi.org/10.1016/j.ipemt.2024.100024

6 Castaneda, D., & Ghamari, M. (n.d.). A review on wearable photoplethysmography sensors and their potential future applications in health care.

7 El-Dahshan, E.-S. A., Bassiouni, M. M., Khare, S. K., Tan, R.-S., & Rajendra Acharya, U. (2024). ExHyptNet: An explainable diagnosis of hypertension using EfficientNet with PPG signals. Expert Systems with Applications, 239, 122388. https://doi.org/https://doi.org/10.1016/j.eswa.2023.122388

8 Kuzmanov, I., Bogdanova, A. M., Kostoska, M., & Ackovska, N. (2022). Fast Cuffless Blood Pressure Classification with ECG and PPG signals using CNN-LSTM Models in Emergency Medicine. 2022 45th Jubilee International Convention on Information, Communication and Electronic Technology (MIPRO), 362–367. https://doi.org/10.23919/MIPRO55190.2022.9803582

9 Rong, M., & Li, K. (2021). A multi-type features fusion neural network for blood pressure prediction based on photoplethysmography. Biomedical Signal Processing and Control, 68, 102772. https://doi.org/https://doi.org/10.1016/j.bspc.2021.102772

10 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. Computer Methods and Programs in Biomedicine, 240, 107716. https://doi.org/https://doi.org/10.1016/j.cmpb.2023.107716

11 Sinaki, F. Y., Ward, R., Abbott, D., Allen, J., Fletcher, R. R., Menon, C., & Elgendi, M. (2022). Ethnic disparities in publicly-available pulse oximetry databases. Communications Medicine, 2(1), 59. https://doi.org/10.1038/s43856-022-00121-8

12 Botros, J., Mourad-Chehade, F., & Laplanche, D. (2022). CNN and SVM-Based Models for the Detection of Heart Failure Using Electrocardiogram Signals. Sensors, 22(23). https://doi.org/10.3390/s22239190

13 Nuryani, N., Akshya, M. F., & Wiyono, N. (2023). Sistem Pengukuran Detak Jantung Menggunakan Arduino Dan Android Berbasis Fotopletismogram. Indonesian Journal of Applied Physics, 13(1), 147–157.

14 Rastegar, S., Gholam Hosseini, H., & Lowe, A. (2023). Hybrid CNN-SVR Blood Pressure Estimation Model Using ECG and PPG Signals. Sensors, 23(3). https://doi.org/10.3390/s23031259

15 Cervantes, J., Garcia-Lamont, F., Rodríguez-Mazahua, L., & Lopez, A. (2020). A comprehensive survey on support vector machine classification: Applications, challenges and trends. Neurocomputing, 408, 189–215. https://doi.org/https://doi.org/10.1016/j.neucom.2019.10.118

16 Sontakke, S. A., Lohokare, J., Dani, R., & Shivagaje, P. (2019). Classification of Cardiotocography Signals Using Machine Learning. In K. Arai, S. Kapoor, & R. Bhatia (Eds.), Intelligent Systems and Applications (pp. 439–450). Springer International Publishing.

17 Gupta, K., Bajaj, V., Ansari, I. A., & Rajendra Acharya, U. (2022). Hyp-Net: Automated detection of hypertension using deep convolutional neural network and Gabor transform techniques with ballistocardiogram signals. Biocybernetics and Biomedical Engineering, 42(3), 784–796. https://doi.org/https://doi.org/10.1016/j.bbe.2022.06.001

18 Hicks, S. A., Strümke, I., Thambawita, V., Hammou, M., Riegler, M. A., Halvorsen, P., & Parasa, S. (2022). On evaluation metrics for medical applications of artificial intelligence. Scientific Reports, 12(1), 5979. https://doi.org/10.1038/s41598-022-09954-8

19 Nuryani, N., Utomo, T. P., Prabowo, N. A., Aripriharta, Yazid, M., & Yunianto, M. (2024). Advancing Non-Cuff Hypertension Detection: Leveraging 1D Convolutional Neural Network and Time Domain Physiological Signals. International Journal of Online and Biomedical Engineering (IJOE), 20(05), 78–100. https://doi.org/10.3991/ijoe.v20i05.45547

20 Liang, Y., Chen, Z., Ward, R., & Elgendi, M. (2018). Photoplethysmography and Deep Learning: Enhancing Hypertension Risk Stratification. Biosensors, 8(4). https://doi.org/10.3390/bios8040101

DOI: https://doi.org/10.13057/ijap.v15i2.102421

Refbacks

  • There are currently no refbacks.