Sistem Pendeteksi Premature Ventricular Contraction Berbasis K-Nearest Neighbors Menggunakan Elektrokardiograf Portabel
Abstract
Premature Ventricular Contraction (PVC) merupakan jenis aritmia yang ditandai dengan kompleks QRS yang melebar lebih dari 120 ms tanpa disertai gelombang P. Penelitian ini bertujuan mengembangkan sistem portabel untuk merekam sinyal EKG dan menerapkan algoritma K-Nearest Neighbors (KNN) guna mendeteksi PVC. Sistem dirancang menggunakan sensor ADS1293 dan mikrokontroler ESP32 yang mengirimkan data EKG ke aplikasi mobile untuk dianalisis. Hasil pengujian menunjukkan sinyal EKG yang terekam memiliki kualitas baik dan heart rate yang sesuai dengan alat referensi. Model KNN yang dilatih menggunakan data MIT-BIH menghasilkan akurasi 92,85% dan F1-score 0,93. Sistem juga berhasil diterapkan pada aplikasi mobile untuk memvisualisasikan hasil deteksi. Meskipun belum divalidasi secara klinis, sistem ini telah berfungsi sesuai tujuan dan dapat dikembangkan lebih lanjut untuk klasifikasi secara real-time. Kata kunci— Elektrokardiogram (EKG), Aritmia, Premature Ventricular Contraction (PVC), K-Nearest Neigbors (KNN)
References
N. T. Sarshar and M. Mirzaei, “Premature
Ventricular Contraction Recognition Based on a
Deep Learning Approach,” J Healthc Eng, vol. 2022,
, doi: 10.1155/2022/1450723.
A. R. Pratama, R. Maulana, and D. Syauqy,
“Implementasi Sistem Pendeteksi Premature
Ventricular Contraction (PVC) Aritmia
menggunakan Metode SVM,” 2021. [Online].
Available: http://j-ptiik.ub.ac.id
N. Alexandra Yosephine, “INFORMASI (Jurnal
Informatika dan Sistem Informasi) Penggunaan
Artificial Neural Network pada Sinyal
Elektrokardiogram untuk Mendeteksi Penyakit
Jantung Aritmia Supraventrikular.”
C. X. You and C. F. Liu, “Premature Ventricular
Contractions and Cardiomyopathy,” Nov. 01, 2019,
Lippincott Williams and Wilkins. doi:
1097/CRD.0000000000000262.
H. Ullah et al., “An Automatic Premature Ventricular
Contraction Recognition System Based on
Imbalanced Dataset and Pre-Trained Residual
Network Using Transfer Learning on ECG Signal,”
Diagnostics, vol. 13, no. 1, Jan. 2023, doi:
3390/diagnostics13010087.
J. Yu, X. Wang, X. Chen, and J. Guo, “Searching for
premature ventricular contraction from
electrocardiogram by using one-dimensional
convolutional neural network,” Electronics
(Switzerland), vol. 9, no. 11, pp. 1–18, Nov. 2020,
doi: 10.3390/electronics9111790.
Y. Jung and H. Kim, “Detection of PVC by using a
wavelet-based statistical ECG monitoring
procedure,” Biomed Signal Process Control, vol. 36,
pp. 176–182, Jul. 2017, doi:
1016/j.bspc.2017.03.023.
M. H. Mazidi, M. Eshghi, and M. R. Raoufy,
“Premature Ventricular Contraction (PVC) Detection
System Based on Tunable Q-Factor Wavelet
Transform,” J Biomed Phys Eng, vol. 12, no. 1, pp.
–74, 2022, doi: 10.31661/jbpe.v0i0.1235.
R. He et al., “A novel method for the detection of Rpeaks in ECG based on K-Nearest Neighbors and
Particle Swarm Optimization,” EURASIP J Adv
Signal Process, vol. 2017, no. 1, Dec. 2017, doi:
1186/s13634-017-0519-3.
R. J. Martis, U. R. Acharya, and H. Adeli, “Current
methods in electrocardiogram characterization,” May
, 2014, Elsevier Ltd. doi:
1016/j.compbiomed.2014.02.012.
Sara S. Abdeldayem and Thirimachos Bourlai,
Automatically Detecting Arrhythmia-related
Irregular Patterns using the Temporal and SpectroTemporal Textures of ECG Signals. IEEE, 2018.
H. A. Abu Alfeilat et al., “Effects of Distance
Measure Choice on K-Nearest Neighbor Classifier
Performance: A Review,” Dec. 01, 2019, Mary Ann
Liebert Inc. doi: 10.1089/big.2018.0175.
T. L. Daniel and Chantal D. Larose, “k-Nearest
Neighbor Algorithm,” in Discovering Knowledge in
Data: An Introduction to Data Mining, Second
Edition, John Wiley & Sons, Inc, 2014, ch. 7.
Ö. F. Ertuğrul and M. E. Tağluk, “A novel version of
k nearest neighbor: Dependent nearest neighbor,”
Applied Soft Computing Journal, vol. 55, pp. 480–
, Jun. 2017, doi: 10.1016/j.asoc.2017.02.020.
P. Patial, “Different Techniques of Baseline
Wandering Removal-A Review,” 2013. [Online].
Available: www.erpublications.com
L. Xie, Z. Li, Y. Zhou, Y. He, and J. Zhu,
“Computational diagnostic techniques for
electrocardiogram signal analysis,” Nov. 01, 2020,
MDPI AG. doi: 10.3390/s20216318.
D. Makowski et al., “NeuroKit2: A Python toolbox
for neurophysiological signal processing,” Behav Res
Methods, vol. 53, no. 4, pp. 1689–1696, Aug. 2021,
doi: 10.3758/s13428-020-01516-y
