A METHOD TO IMPROVE THE ACCURACY OF DEEP LEARNING MODELS IN CARDIOVASCULAR DISEASE CLASSIFICATION  USING ELECTROCARDIOGRAM SIGNALS

Nguyễn Thu Hường; Đinh Công Tùng; Mai Đức Vinh

doi:10.34238/tnu-jst.12910

A METHOD TO IMPROVE THE ACCURACY OF DEEP LEARNING MODELS IN CARDIOVASCULAR DISEASE CLASSIFICATION USING ELECTROCARDIOGRAM SIGNALS

About this article

Received: 29/05/25 Revised: 30/06/25 Published: 30/06/25

Authors

1. Nguyen Thu Huong, University of Transport and Communications
2. Dinh Cong Tung , University of Transport and Communications
3. Mai Duc Vinh, University of Transport and Communications

Abstract

This paper proposes an improved method to enhance the accuracy of classifying cardiovascular diseases based on electrocardiogram signals by applying a deep learning model composed of multiple integrated components. Specifically, the model architecture is built upon a one-dimensional convolutional neural network to extract local features from raw electrocardiogram signals, effectively capturing significant patterns in the input data. Subsequently, a long short-term memory network is employed to exploit the temporal dependencies within the signal, enabling the model to understand contextual relationships and dynamic changes in features over time. To further improve the model's ability to focus on the most relevant information for classification, a multihead attention mechanism is integrated after the long short-term memory layer. This attention mechanism allows the model to learn the relative importance of different segments within the signal sequence more effectively. Experimental results demonstrate that the combination of one-dimensional convolutional neural network, long short-term memory, and multihead attention yields high performance, achieving an accuracy of over 97% in classifying four types of heart diseases. The proposed method shows promising potential for the application of artificial intelligence in the automated diagnosis of cardiovascular conditions.

Keywords

Electrocardiogram; One-dimensional convolutional neural network; Long short-term memory; Multihead attention; Cardiovascular diseases

Full Text:

PDF

References

[1] G. Sivapalan, K. K. Nundy, S. Dev, B. Cardiff, and D. John, “ANNet: A lightweight neural network for ECG anomaly detection in IoT edge sensors,” IEEE Trans. Biomed. Circuits Syst., vol. 16, no. 1, pp. 24–35, Jan. 2022, doi: 10.1109/TBCAS.2021.3137646.

[2] J. Qin, F. Gao, Z. Wang, D. C. Wong, Z. Zhao, S. D. Relton, and H. Fang, “A novel temporal generative adversarial network for electrocardiography anomaly detection,” Artif. Intell. Med., vol. 136, Jan. 2023, Art. no. 102489, doi: 10.1016/j.artmed.2023.102489.

[3] L. Mohebbanaaz, V. R. Kumar, and Y. P. Sai, “A new transfer learning approach to detect cardiac arrhythmia from ECG,” Signal Image Video Process., vol. 16, no. 7, pp. 1945–1953, Jul. 2022, doi: 10.1007/s11760-022-02155-w.

[4] A. Alamr and A. Artoli, “Unsupervised transformer-based anomaly detection in ECG signals,” Algorithms, vol. 16, no. 3, Mar. 2023, Art. no. 152, doi: 10.3390/a16030152.

[5] X. Zhang, Z. Huo, and Q. Wu, “An ensemble of deep learning-based multi-model for ECG heartbeats arrhythmia classification,” IEEE Access, vol. 9, pp. 101746–101759, Jul. 2021, doi: 10.1109/ACCESS.2021.3096610.

[6] H. Khan, N. Javaid, T. Bashir, M. Akbar, N. Alrajeh, and S. Aslam, “Heart disease prediction using novel ensemble and blending based cardiovascular disease detection networks: EnsCVDD-Net and BlCVDD-Net,” IEEE Access, vol. 12, pp. 109230–109254, Jul. 2024, doi: 10.1109/ACCESS.2024.3421241.

[7] J. Chen, S. Huang, Y. Zhang, et al., “Congenital heart disease detection by pediatric electrocardiogram based deep learning integrated with human concepts,” Nat. Commun., vol. 15, Jan. 2024, doi: 10.1038/s41467-024-44930-y.

[8] H. Li and P. Boulanger, “Structural anomalies detection from electrocardiogram (ECG) with spectrogram and handcrafted features,” Sensors, vol. 22, no. 7, Mar. 2022, Art. no. 2467, doi: 10.3390/s22072467.

[9] U. R. Acharya, H. Fujita, O. S. Lih, Y. Hagiwara, J. H. Tan, and M. Adam, “Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network,” Inf. Sci., vol. 405, pp. 81–90, Sep. 2017, doi: 10.1016/j.ins.2017.04.012.

[10] P. Rajpurkar, A. Y. Hannun, M. Haghpanahi, C. Bourn, and A. Y. Ng, “Cardiologist-level arrhythmia detection with convolutional neural networks,” arXiv preprint, arXiv:1707.01836, Jul. 2017.

[11] O. Yildirim, U. B. Baloglu, R. S. Tan, and U. R. Acharya, “A deep convolutional neural network model for automated identification of abnormal heart rhythms using ECG signals,” Appl. Soft Comput., vol. 84, Oct. 2019, Art. no. 105619, doi: 10.1016/j.asoc.2019.105619.

[12] B. Tutuko, A. Darmawahyuni, S. Nurmaini, A. E. Tondas, M. N. Rachmatullah, et al., “DAE-ConvBiLSTM: End-to-end learning single-lead electrocardiogram signal for heart abnormalities detection,” PLoS ONE, vol. 17, no. 12, Dec. 2022, Art. no. e0277932, doi: 10.1371/journal.pone.0277932.

[13] T. M. Ingolfsson, H. A. A. Madsen, A. Laursen, and P. Popovski, “ECG-TCN: Wearable Cardiac Arrhythmia Detection with a Temporal Convolutional Network,” IEEE Transactions on Biomedical Circuits and Systems, vol. 17, no. 2, pp. 225–238, Apr. 2023, doi: 10.1109/TBCAS.2023.3240431.

[14] R. Cheng, S. Li, Z. Zhang, J. Chen, and X. Hu, “MSW-Transformer: Multi-Scale Shifted Windows Transformer Networks for 12-Lead ECG Classification,” arXiv preprint arXiv:2311.13583, 2023. [Online]. Available: https://arxiv.org/abs/2311.13583. [Accessed Feb. 15, 2025].

[15] D. Li, J. Zhang, Q. Zhang, and X. Wei, “Classification of ECG signals based on 1D convolution neural network,” in Proc. 2017 IEEE 19th Int. Conf. e-Health Netw., Appl. Serv. (Healthcom), Dalian, China, Oct. 2017, pp. 1–6, doi: 10.1109/HealthCom.2017.8210842.

[16] T. D. Pham, “Time–frequency time–space LSTM for robust classification of physiological signals,” Sci. Rep., vol. 11, Mar. 2021, doi: 10.1038/s41598-021-86390-1.

[17] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” Adv. Neural Inf. Process. Syst., vol. 30, pp. 5998–6008, Dec. 2017.

[18] T. Kwon, H. Lee, J. Kim, and B. Lee, “Transformer-based stacked multi-head attention model for EEG signal denoising,” Brain Informatics, vol. 10, no. 1, pp. 1–13, 2023.

[19] S. Roy, A. Kiral-Kornek, and D. M. Harrer, “Deep learning enabling technology for epileptic seizure detection using EEG,” in Proc. IEEE EMBC, 2019, pp. 1–4.

[20] Z. Zhao, Q. Zhang, H. Liu, L. Peng, and Y. Li, “Epileptic Seizure Detection Based on Multi-Head Attention Mechanism and CNN-LSTM Network,” IEEE Access, vol. 10, pp. 19424–19435, 2022.

[21] J. Zheng, J. Zhang, S. Danioko, et al., “A 12-lead electrocardiogram database for arrhythmia research covering more than 10,000 patients,” Sci. Data, vol. 7, Feb. 2020, doi: 10.1038/s41597-020-0386-x.

[22] C. W. Cleverdon, “Factors Determining the Performance of Indexing Systems,” Aslib Cranfield Research Project, 1966.

[23] C. J. V. Rijsbergen, Information Retrieval, 2nd ed. Butterworth-Heinemann, 1979.

DOI: https://doi.org/10.34238/tnu-jst.12910

Refbacks

There are currently no refbacks.



Remember me