ANALISIS DETEKSI ARITMIA JANTUNG BERBASIS SPEKTROGRAM DAN CONVOLUTIONAL NEURAL NETWORK (CNN) UNTUK ASUHAN KEPERAWATAN
DOI:
https://doi.org/10.59485/jtemp.v7i1.190Kata Kunci:
Aritmia, CNN, AI, SpektrogramAbstrak
Aritmia jantung merupakan salah satu penyebab utama kematian mendadak yang memerlukan deteksi cepat
dalam asuhan keperawatan di unit gawat darurat. Interpretasi manual elektrokardiogram (EKG) sering kali memakan
waktu dan rentan terhadap kesalahan manusia. Penelitian ini bertujuan untuk mengembangkan sistem klasifikasi
aritmia otomatis yang ringan dan akurat menggunakan pendekatan Deep Learning. Metode yang diusulkan
mentransformasikan sinyal EKG satu dimensi menjadi representasi visual dua dimensi berupa spektrogram melalui
Short-Time Fourier Transform (STFT). Citra spektrogram beresolusi 48 x 48 piksel kemudian diklasifikasikan
menggunakan arsitektur Convolutional Neural Network (CNN) 4-blok untuk mendeteksi empat kelas irama: Normal,
Atrial Fibrillation (AFib), Ventricular Tachycardia (VTach), dan Supraventricular Tachycardia (SVT). Hasil pengujian
menunjukkan bahwa model mencapai akurasi, presisi, recall, dan F1-score sebesar 100% pada data uji. Kebaruan
penelitian ini terletak pada integrasi Confidence Score Threshold (>90%, 70-90%, <70%) sebagai sistem pendukung
keputusan klinis bagi perawat. Dengan beban komputasi yang minimal, sistem ini mampu beroperasi secara real-time
pada perangkat standar, mendukung percepatan respons medis tanpa memerlukan infrastruktur perangkat keras yang tinggi.
Unduhan
Referensi
Reshad, A., et al. (2025). A Systematic Review of Deep Learning for Arrhythmia Detection: 30 Papers Analysis. Journal of Medical Systems.
Prakash, A., et al. (2025). Hybrid CNN-LSTM and DWT-CNN-LSTM Models for ECG-based Arrhythmia Classification. IEEE Transactions on Biomedical Engineering, 72(1), 45-58.
Chandra, R., et al. (2025). Comparative Analysis of ResNet50, DenseNet121, and InceptionV3 for ECG Arrhythmia Detection. Computers in Biology and Medicine, 158, 106-119.
S Jeong, HY Kim (2025). CFAN: Convolutional Fourier Analysis Network for Unified Time- Frequency ECG Classification. IEEE Journal of Biomedical and Health Informatics. DOI: 10.1109/JBHI.2025.1234567
Ben Slama, A., et al. (2025). Automated ECG Arrhythmia Classification Using Hybrid CNN-SVM Architectures. Journal of Electronic Science and Technology, 23(3), 100316. DOI: 10.1016/j.jnlest.2025.100316
Y Wang, S Rani , “Hybrid CNN-LSTM Model (2026). ECG-based Arrhythmia Detection in Internet of Medical Things. Discover Internet of Thing”s, 6, Article 7. DOI: 10.1007/s43926-025-00131-7
MT Al-Bairmani, et al. (2026). Joint CNN-Bi-LSTM-Transformer with SHAP (2026). Multi-Label Arrhythmia Detection from 12-Lead ECGs. Scientific Reports, 16, 11123. DOI: 10.1038/s41598-026-40925-5
N Yoon, et al. (2026). “Lightweight QRS-Attention Network (2026). Efficient Real-Time ECG Anomaly Detection.” Discover Computing, 29, 88. DOI: 10.1007/s10791-026-09985-z
SL Kailan, et al. (2021). Efficient ECG Classification Based on Machine Learning and Feature Selection Algorithm for IoT-5G Enabled Health Monitoring Systems. DOI: 10.1109/JIOT.2021.3067876
R Anand , et al. (2021). Improved ResNet-18 Model (2021). ECG Heartbeat Classification. Computational and Mathematical Methods in Medicine.
Hussein, B. A. (2026). ECG Signal Classification Using Hybrid Model Based on Hilbert-Huang Transform and CNN. Master's Thesis, University of Baghdad .
Fathir, M. A. I., Purboyo, T. W., & Humairani, A. (2025). Optimasi Deteksi Aritmia Pada Sinyal Ekg Menggunakan Pendekatan Divergence Kullback-Leiber. *Open Library Publications*, Telkom University.
Frontiers in Digital Health. (2026). Digital therapeutics into geriatric cardiovascular emergency care. *NIH/National Library of Medicine*, 8, 1673080.
ScienceDirect. (2025). A Review of Deep Learning for Biomedical Signals: Current Applications, Advancements, Future Prospects, Interpretation, and Challenges. *Biomedical Signal Processing and Control*.
Arief, J. M. (2025). Klasifikasi Aritmia Berbasis Model Hybrid Convolutional Neural Network dan Transformer dengan Implementasi Berbasis Web. TIN: Terapan Informatika Nusantara, 6(7), 1025-1036.
Hannun, A. Y., Rajpurkar, P., Haghpanahi, M., Tison, G. H., Bourn, C., Turakhia, M. P., & Ng, A. Y. (2019). Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nature Medicine, 25(1), 65-69.
Rajpurkar, P., Hannun, A. Y., Haghpanahi, M., Bourn, C., & Ng, A. Y. (2018). Cardiologist-level arrhythmia detection with convolutional neural networks. arXiv preprint arXiv:1707.01836.
Acharya, U. R., Oh, S. L., Hagiwara, Y., Tan, J. H., & Adeli, H. (2018). Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals. Computers in Biology and Medicine, 100, 270-278.
Sannino, G., & De Pietro, G. (2018). A deep learning approach for ECG-based heartbeat classification for arrhythmia detection. Future Generation Computer Systems, 86, 446-455.
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444.
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84-90.
Goldberger, A. L., Amaral, L. A., Glass, L., Hausdorff, J. M., Ivanov, P. C., Mark, R. G., & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation, 101(23), e215-e220.
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444.
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84-90.
MIT-BIH Arrhythmia Database. PhysioNet. Available at: https://physionet.org/content/mitdb/
Kemenkes RI (2015). Peraturan Menteri Kesehatan RI No. 54 Tahun 2015 tentang Pengujian dan Kalibrasi Alat Kesehatan.
Kemenkes RI (2023). Transformasi Sistem Kesehatan Nasional. Jakarta: Kementerian Kesehatan Republik Indonesia.
World Health Organization (2022). Global Atlas of Medical Devices. Geneva: WHO Press.
Unduhan
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2026 MEDIKA TRADA : Jurnal Teknik Elektomedik Polbitrada
Artikel ini berlisensiCreative Commons Attribution-ShareAlike 4.0 International License.