IIARD International Institute of Academic Research and Development

INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND MATHEMATICAL THEORY (IJCSMT )

E-ISSN 2545-5699
P-ISSN 2695-1924
VOL. 10 NO. 3 2024
DOI: 10.56201/ijcsmt.v10.no3.2024.pg147.159

---

Development of a Hybrid Model of CNN and LSTM for Arrhythmia Detection

Ujor, B. N. , Nwiabu, N. D. & Taylor, O. E.

---

Abstract

This study examines the development of a hybrid model combining convolutional neural networks (CNNs) and long short-term memory (LSTM) for the detection of arrhythmia. Arrhythmia is an irregular or abnormal heartbeat which can have serious consequences if not detected early. The CNN-LSTM architecture has been found to be effective in the detection of various types of arrhythmias. The proposed model combines the convolutional layers of the CNN with the recurrent layers of the LSTM to create an end-to-end architecture that is capable of detecting various arrhythmias with high accuracy. This model is trained using a dataset of electrocardiograms (ECGs) and labels corresponding to the type of arrhythmia present. The performance of the model is evaluated using a hold-out test set and the results indicate that the model achieves excellent accuracy for the detection of different arrhythmias. The developed model has potential applications for the early detection and diagnosis of arrhythmias. When compared the proposed system in context with other existing systems, providing a benchmark for its effectiveness, the results show that the proposed system outperforms the other systems with an accuracy result of 99.00%The results collectively suggest that the hybrid model, combining CNN and LSTM, performs well in detecting arrhythmia, as indicated by high accuracy, reliable AUC, and robust precision and recall scores. The insights gained from these results contribute to the understanding of the model's strengths and areas for potential improvement. Further studies and validations could focus on real-world applications and the model's scalability. This can improve patient care and reduce the risk of serious complications arising from delayed or missed diagnosis. The model can also be used for research purposes in order to better understand the different types of arrhythmias. The findings of this study show the potential for combining CNNs and

---

References:

Antzelevitch, C. & Burashnikov, A. (2011). Overview of basic mechanisms of cardiac arrhythmia.
Card. Electrophysiology Clinician, 3, 23–45.
Banos, O., Damas, M., Pomares, H., Prieto, A. & Rojas, I. (2012). Daily living activity recognition
based on statistical feature quality group selection. Expert System Application, 39, 8013–
Celin, S. & Vasanth, K. (2018). ECG signal classification using various machine learning
techniques. Journal of Med. System, 42, 1–11.
Charfi, F. & Kraiem, A. (2012). Comparative study of ECG classification performance using
decision tree algorithms. International Journal of E-Health Med. Communication, 3, 102–
Clifford, G.D., Azuaje, F. & McSharry, P. (2006). Advanced Methods and Tools for ECG Data
Analysis; Artech House: Boston, MA, USA, 10.
Ge, Z., Zhu, Z., Feng, P., Zhang, S., Wang, J. & Zhou, B. (2019). ECG-signal classification using
SVM with multi-feature. In Proceedings of the 2019 8th International Symposium on Next
Generation Electronics, 1–3.
Kohli, N. & Verma, N.K. (2011). Arrhythmia classification using SVM with selected features.
International Journal of Engineering Science and Technology, 3, 122–131.
Kumar, R.G. & Kumaraswamy, Y. (2012). Investigating cardiac arrhythmia in ECG using random
forest classification. International Journal of Computer Application, 37, 31–34.
Kumari, L., Sai, Y.P. & Naaz, M. (2022). Classification of ECG beats using optimized decision
tree and adaptive boosted optimized decision tree. Signal Image Video Process, 16, 695–
Loh, B.C. & Then, P.H. (2017). Deep learning for cardiac computer-aided diagnosis: benefits,
issues and solutions. Mhealth, 3, 45.
Martis, R.J., Acharya, U. R. & Adeli, H. (2014). Current methods in electrocardiogram
characterization. Computer of Biology of Medicine, 48, 133–149.
Mert, A., Kilic, N. & Akan, A. (2012). ECG signal classification using ensemble decision tree.
Journal of Trends Development of Mach. Association of Technology, 16, 179–182.
Potter, L. (2011). Understanding an ECG; Independently: Chicago, IL, USA,
Razi, A.P., Einalou, Z. & Manthouri, M. (2021). Sleep Apnea Classification Using Random Forest
via ECG. Sleep Vigil., 5, 141–146.
Saini, I., Singh, D. & Khosla, A. (2013). Delineation of ecg wave components using k-nearest
neighbor (knn) algorithm: Ecg wave delineation using knn. In Proceedings of the 2013
10th International Conference on Information Technology. 712–717.
Saini, I., Singh, D. & Khosla, A. (2013). QRS detection using K-Nearest Neighbor algorithm
(KNN) and evaluation on standard ECG databases. Journal of Advance Research, 4, 331–
Saini, R., Bindal, N. & Bansal, P. (2015). Classification of heart diseases from ECG signals using
wavelet transform and kNN classifier. In Proceedings of the International Conference on
Computing, Communication & Automation, Greater Noida, 1208–1215.
Singh, S., Pandey, S. K., Pawar, U. & Janghel, R.R. (2018). Classification of ECG arrhythmia
using recurrent neural networks. Procedia Computer Science, 132, 1290–1297.
Thilagavathy, R., Srivatsan, R., Sreekarun, S., Sudeshna, D., Priya, P. L. & Venkataramani, B.
(2020). Real-time ECG signal feature extraction and classification using support vector
machine. In Proceedings of the 2020 International Conference on Contemporary
Computing and Applications, 44–48.
Zhong, G., Ling, X. & Wang, L.N. (2019). From shallow feature learning to deep learning:
Benefits from the width and depth of deep architectures. Wiley Interdiscip. Rev. Data Min.
Knowledge Discovery, 1255.

DOWNLOAD PDF

---

Back