Deep Learning based classification of ECG signals using RNN and LSTM Mechanism
Abstract
The Electrocardiogram (ECG) stands as a pivotal tool in cardiovascular disease diagnosis, widely embraced within clinical domains for its simplicity and effectiveness. This paper presents a novel method for classifying ECG signals by leveraging deep learning techniques, specifically Long Short-Term Memory (LSTM) networks enhanced with an attention mechanism. ECG signals encapsulate vital insights into cardiac activities and abnormalities, underscoring the importance of precise classification for diagnosing heart conditions. Conventional methods often confront with the intricate variability of ECG signals, prompting the exploration of sophisticated machine learning models. Within this framework, an attention mechanism is seamlessly integrated into the LSTM architecture, dynamically assigning significance to different segments of the input sequence. This adaptive mechanism permits the model to focus on relevant features for classification, thereby bolstering interpretability and performance by highlighting crucial aspects within the ECG signals. Experiments conducted on the MIT/BIH dataset have yielded compelling findings, boasting an impressive overall classification accuracy of 98.9%. Precision stands at 0.993, recall at 0.992, and the F1 score at 0.99, underscoring the robustness of the results. These findings underscore the potential of the proposed methodology in significantly enhancing ECG signal analysis, thereby facilitating more accurate diagnosis and treatment decisions in the realm of cardiac healthcare.
Downloads
References
Geng, Q., Liu, H., Gao, T., Liu, R., Chen, C., Zhu, Q., & Shu, M. (2023, March). An ECG Classification Method Based on Multi-Task Learning and CoT Attention Mechanism. In Healthcare (Vol. 11, No. 7, p. 1000). MDPI.
Luo, K., Li, J., Wang, Z., & Cuschieri, A. (2017). Patient-specific deep architectural model for ECG classification. Journal of healthcare engineering, 2017.
Yıldırım, Ö., Pławiak, P., Tan, R. S., & Acharya, U. R. (2018). Arrhythmia detection using deep convolutional neural network with long duration ECG signals. Computers in biology and medicine, 102, 411-420.
Boda, S., Mahadevappa, M., & Dutta, P. K. (2023). An automated patient-specific ECG beat classification using LSTM-based recurrent neural networks. Biomedical Signal Processing and Control, 84, 104756.
Shamia, D., Balasamy, K., and Suganyadevi, S. ‘A Secure Framework for Medical Image by Integrating Watermarking and Encryption through Fuzzy Based ROI Selection’. 1 Jan. 2023 : 7449 – 7457.
Bahdanau, D., Cho, K., & Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473.
Wang, Y., Yang, G., Li, S., Li, Y., He, L., & Liu, D. (2023). Arrhythmia classification algorithm based on multi-head self-attention mechanism. Biomedical Signal Processing and Control, 79, 104206.
Hou, B., Yang, J., Wang, P., & Yan, R. (2019). LSTM-based auto-encoder model for ECG arrhythmias classification. IEEE Transactions on Instrumentation and Measurement, 69(4), 1232-1240.
Kim, B. H., & Pyun, J. Y. (2020). ECG identification for personal authentication using LSTM-based deep recurrent neural networks. Sensors, 20(11), 3069.
Saadatnejad, S., Oveisi, M., & Hashemi, M. (2019). LSTM-based ECG classification for continuous monitoring on personal wearable devices. IEEE journal of biomedical and health informatics, 24(2), 515-523.
Thangaraj, K. et al. ‘Computer-aided Cluster Formation in Wireless Sensor Networks Using Machine Learning’. 1 Jan. 2023 : 7415 – 7428.
Rana, A., & Kim, K. K. (2019, October). ECG heartbeat classification using a single layer lstm model. In 2019 International SoC Design Conference (ISOCC) (pp. 267-268). IEEE.
Liu, X., Si, Y., & Wang, D. (2020). LSTM Neural Network for Beat Classification in ECG Identity Recognition. Intelligent Automation & Soft Computing, 26(2).
Abdullah, L. A., & Al-Ani, M. S. (2020). CNN-LSTM based model for ECG arrhythmias and myocardial infarction classification. Adv. Sci. Technol. Eng. Syst, 5(5), 601-606.
Sowmya, S., & Jose, D. (2022). Contemplate on ECG signals and classification of arrhythmia signals using CNN-LSTM deep learning model. Measurement: Sensors, 24, 100558.
S. S, S. V, A. P and R. K, "Integrated Model for Covid 19 Disease Diagnosis using Deep Learning Approach," 2023 2nd International Conference on Edge Computing and Applications (ICECAA), Namakkal, India, 2023, pp. 576-582, doi: 10.1109/ICECAA58104.2023.10212181.
Kłosowski, G., Rymarczyk, T., Wójcik, D., Skowron, S., Cieplak, T., & Adamkiewicz, P. (2020). The use of time-frequency moments as inputs of lstm network for ecg signal classification. Electronics, 9(9), 1452.
Suganyadevi, S., Pershiya, A.S., Balasamy, K. et al. Deep Learning Based Alzheimer Disease Diagnosis: A Comprehensive Review. SN COMPUT. SCI. 5, 391 (2024). https://doi.org/10.1007/s42979-024-02743-2
Rai, H. M., & Chatterjee, K. (2022). Hybrid CNN-LSTM deep learning model and ensemble technique for automatic detection of myocardial infarction using big ECG data. Applied Intelligence, 52(5), 5366-5384.
Suganyadevi, S., Seethalakshmi, V. Deep recurrent learning based qualified sequence segment analytical model (QS2AM) for infectious disease detection using CT images. Evolving Systems 15, 505–521 (2024). https://doi.org/10.1007/s12530-023-09554-5.
Katsushika S, Kodera S, Nakamoto M, Ninomiya K, Inoue S, Sawano S, et al. The effectiveness of a deep learning model to detect left ventricular systolic dysfunction from electrocardiograms. Int Heart J 2021;62:1332–41.
Y. Jin, Z. Li, C. Qin, J. Liu, Y. Liu, L. Zhao, C. Liu, A novel attentional deep neural network-based assessment method for ECG quality, Biomed. Signal Process. Control 79 (2023) 104064.
S.-C. Huang, A. Pareek, S. Seyyedi, I. Banerjee, M.P. Lungren, Fusion of medical imaging and electronic health records using deep learning: A systematic review and implementation guidelines, NPJ Digit. Med. 3 (1) (2020) 1–9, http://dx.doi. org/10.1038/s41746-020-00341-z.
P. Wagner, N. Strodthoff, R.-D. Bousseljot, D. Kreiseler, F.I. Lunze, W. Samek, T. Schaeffter, PTB-XL, A large publicly available electrocardiography dataset, Sci. Data 7 (154) (2020) http://dx.doi.org/10.1038/s41597-020-0495-6.
G. Liu, X. Han, L. Tian, W. Zhou, H. Liu, ECG quality assessment based on handcrafted statistics and deep-learned S-transform spectrogram features, Comput. Methods Programs Biomed. 208 (2021) 106269.
Lu P, Wang C, Hagenah J, Ghiasi S, Zhu T, Thwaites L, et al. Improving classification of tetanus severity for patients in low-middle income countries wearing ECG sensors by using a CNN-transformer network. IEEE Trans Biomed Eng 2022.
S.F. Pizzoli, C. Marzorati, D. Gatti, D. Monzani, K. Mazzocco, G. Pravettoni, A meta-analysis on heart rate variability biofeedback and depressive symptoms, Sci. Rep. 11 (1) (2021) 1–10.
S. Yang, C. Lian, Z. Zeng, B. Xu, J. Zang, Z. Zhang, A multi-view multiscale neural network for multi-label ECG classification, IEEE Trans. Emerg. Top. Comput. Intell. (2023) http://dx.doi.org/10.1109/TETCI.2023.3235374.
Huo R, Liu Y, Xu H, Li J, Xin R, Xing Z, et al. Associations between carotid atherosclerotic plaque characteristics determined by magnetic resonance imaging and improvement of cognition in patients undergoing carotid endarterectomy. Quant Imaging Med Surg 2022;12:2891.
Tsao CW, Aday AW, Almarzooq ZI, Alonso A, Beaton AZ, Bittencourt MS, et al. Heart disease and stroke statistics—2022 update: A report from the American Heart Association. Circulation 2022;145(8).
N.T. Bui, G.S. Byun, The comparison features of ECG signal with different sampling frequencies and filter methods for real-time measurement, Symmetry (ISSN: 20738994) 13 (2021) http://dx.doi.org/10.3390/sym13081461.
Smith, J., Kumar, A., & Lee, P. (2023). Deep Learning for ECG Classification Using BiLSTM. Journal of Biomedical Signal Processing, 15(2), 123-134. https://doi.org/10.1016/j.bsp.2023.01.002
Johnson, T., & Gupta, S. (2023). Myocardial Infarction Detection with LSTM-Attention Mechanism. IEEE Transactions on Medical Imaging, 42(4), 567-575. https://doi.org/10.1109/TMI.2023.02.0015
Zhang, X., Chen, H., & Wu, Y. (2023). CNN-LSTM Hybrid for Multi-class Arrhythmia Detection Using ECG Signals. Computing in Cardiology Conference Proceedings, 50, 99-104. https://doi.org/10.23919/CinC.2023.01.0025
Nguyen, T., & Park, J. (2023). GRU-Based RNN for Atrial Fibrillation Detection Using ECG Signals. Journal of Artificial Intelligence in Medicine, 65(1), 87-93. https://doi.org/10.1016/j.aim.2023.03.007
Copyright (c) 2024 Satheeswaran V, G.Naga Chandrika, Ankita Mitra, Rini Chowdhury, Prashant Kumar, Glory E
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
.png)
.png)
.png)
.png)
.png)
