Analysis of Electrocardiogram Dynamic Features for Arrhythmia Classification

Yusril Ramadhan; Satria Mandala

doi:10.15575/join.v8i2.1106

Authors

Yusril Ramadhan School of Computing, Telkom University; Human Centric (HUMIC) Engineering, Telkom University, Indonesia
Satria Mandala School of Computing, Telkom University; Human Centric (HUMIC) Engineering, Telkom University, Indonesia

DOI:

https://doi.org/10.15575/join.v8i2.1106

Keywords:

electrocardiogram, Feature Extraction, Arrhythmia, Dynamic Feature

Abstract

Arrhythmia is a deviation from the normal heart rate pattern. Arrhythmias are usually harmless, but they can cause heart problems. Some types of arrhythmias include Atrial Fibrillation (AF), Premature Atrial Contractions (PAC), and Premature Ventricular Contractions (PVC). Many studies have been conducted to identify the dynamic characteristics of electrocardiogram (ECG) irregular waves in the detection of arrhythmias. However, the accuracy obtained in these studies is less than optimal. This study aims to solve the problem by evaluating three main features of arrhythmias using ECG signals: RR interval, PR interval, and QRS complex. Experiments were conducted rigorously on these three features. The accuracy achieved was 98.21%, with a specificity of 98.65% and a sensitivity of 97.37%.

Author Biography

Yusril Ramadhan, School of Computing, Telkom University; Human Centric (HUMIC) Engineering, Telkom University

References

KEMENTERIAN KESEHATAN, R.I. Penyakit jantung penyebab utama kematian, kemenkes perkuat layanan primer, 9 2022.

CHEN, C., HUA, Z., ZHANG, R., LIU, G., AND WEN, W. Automated arrhythmia classification based on a combination

network of cnn and lstm. Biomedical Signal Processing and Control 57 (2020). Cited by : 88.

DUAN, J., WANG, Q., ZHANG, B., LIU, C., LI, C., AND WANG, L. Accurate detection of atrial fibrillation events with r-r intervals from ecg signals. PLoS ONE 17, 8 August (2022). Cited by: 0; All Open Access, Gold Open Access, Green Open Access.

BASHAR, S. K., HAN, D., ZIENEDDIN, F., DING, E., FITZGIB- BONS, T. P., WALKEY, A. J., MCMANUS, D. D., JAVIDI, B., AND CHON, K. H. Novel density poincar ?e plot based machine learning method to detect atrial fibrillation from premature atrial/ventricular contractions. IEEE Transactions on Biomedical Engineering 68, 2 (2021), 448–460.

ALAGARSAMY, M., VEDAM, J. M. J., SHANMUGAM, N., ESWARAN, P. M., SANKARAIYER, G., AND SURIYAN, K.

Performing the classification of pulsation cardiac beats auto- matically by using cnn with various dimensions of kernels.

International Journal of Reconfigurable and Embedded Systems 11, 3 (2022), 249 – 257. Cited by: 0; All Open Access, Gold Open Access, Green Open Access.

T. Wang, C. Lu, Y. Sun, M. Yang, C. Liu, and C. Ou, “Automatic ECG Classification Using Continuous Wavelet Transform and Convolutional Neural Network,” Entropy, vol. 23, no. 1, p. 119, Jan. 2021, doi: 10.3390/e23010119.

MUJEEB RAHMAN, K., AND MONICA SUBASHINI, M. Ecg signal processing and analysis for accurate features extraction.

DUAN, J., WANG, Q., ZHANG, B., LIU, C., LI, C., AND WANG, L. Accurate detection of atrial fibrillation events with r-r intervals from ecg signals. PLoS ONE 17, 8 August (2022). Cited by: 0; All Open Access, Gold Open Access, Green Open Access.

SHRIKANTH RAO, S., AND MARTIS, R. J. Machine learning based decision support system for atrial fibrillation detection

using electrocardiogram. p. 263 – 266. Cited by: 4.

DEV SHARMA, L., SUNKARIA, R. K., AND KUMAR, A. Bundle branch block detection using statistical features of qrs-complex

and k-nearest neighbors. In 2017 Conference on Information and Communication Technology (CICT) (2017), pp. 1–4.

SOLIKHAH, M., NURYANI, N., AND DARMANTO, D. Deteksi aritmia pada elektrokardiogram dengan metode jaringan syaraf

tiruan kelas jamak menggunakan fitur interval rr, lebar qrs, dan gradien gelombang r. Jurnal Fisika dan Aplikasinya 11 (01 2015), 36.

HAN, C., QUE, W., WANG, S., ZHANG, J., ZHAO, J., AND SHI, L. Qrs complexes and t waves localization in multi-

lead ecg signals based on deep learning and electrophysiology knowledge. Expert Systems with Applications 199 (2022). Cited

by: 2.

CAI, W., AND HU, D. Qrs complex detection using novel deep learning neural networks. IEEE Access 8 (2020), 97082 – 97089. Cited by: 37; All Open Access, Gold Open Access.

J YANG, J., LI, J., LAN, K., WEI, A., WANG, H., HUANG, S., AND FONG, S. Multi-label attribute selection of arrhythmia for

electrocardiogram signals with fusion learning. Bioengineering 9, 7 (2022). Cited by: 0; All Open Access, Gold Open Access, Green Open Access.

DAN RIZAL MAULANA DAN DAHNIAL SYAUQY, A. P. Implementasi sistem pendeteksi premature ventricular contraction (pvc) aritmia menggunakan metode svm. Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer 5, 2 (2021), 542–548.

HUDA SEPRIANDI IBRAHIM, JONDRI, U. N. W. Analisis deep learning untuk mengenaliqrs kompleks pada sinyal ecg dengan

metode cnn, 8 2018.

ROSS-HOWE, S., AND TIZHOOSH, H. Atrial fibrillation detection using deep features and convolutional networks. Cited by:

; All Open Access, Green Open Access..

Goldberger, A., Amaral, L., Glass, L., Hausdorff, J., Ivanov, P. C., Mark, R., ... & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation [Online]. 101 (23), pp. e215–e220. M.

Merino-Monge, J. A. Castro-García, C. Lebrato-Vázquez, I. M. Gómez-González, and A. J. Molina-Cantero, “Heartbeat detector from ECG and PPG signals based on wavelet transform and upper envelopes,” Phys. Eng. Sci. Med., vol. 46, no. 2, pp. 597–608, 2023, doi: 10.1007/s13246-023-01235- 6.

YIN, L., F., ZHANG, Q., AND MA, X. Arrhythmia classification based on multi-domain feature extraction. Journal of Physics: Conference Series 1237, 2 (jun 2019). 022062.

HONG, J., LI, H.-J., YANG, C.-C., HAN, C.-L., AND HSIEH, J.-C. A clinical study on atrial fibrillation, premature ventricular contraction, and premature atrial contraction screening based on an ecg deep learning model. Applied Soft Computing 126 (2022).

L. Montenegro, M. Abreu, A. Fred, and J. M. Machado, “Human-Assisted vs. Deep Learning Feature Extraction: An Evaluation of ECG Features Extraction Methods for Arrhythmia Classification Using Machine Learning,” Applied Sciences (Switzerland), vol. 12, no. 15, pp. 1–15, 2022.21.