ECG Lead Selection for Disease Diagnostics Using CNN-Transformer
Keywords:
Electrocardiography, Cardiovascular Diseases, Deep Learning, PTB-XL Dataset, ECG Lead OptimizationAbstract
Electrocardiography (ECG) is crucial for diagnosing cardiovascular diseases (CVDs), which cause millions of deaths each year. This study addresses the challenge of CVD diagnosis in rural areas, where there is a shortage of skilled healthcare professionals and medical equipment. This study proposes a novel method to systematically compare different ECG leads using Deep Learning techniques, specifically a 1D CNN Transformer, to detect anomalies from minimal disturbances. The analysis was conducted using the PTB-XL dataset and further validated with Holter ECG-based records from the St. Petersburg INCART database. Minimal pre-processing was applied, limited to baseline wander removal, to maintain the intrinsic information of each lead. The results indicate that utilizing all leads significantly improves the F1 score, although lead II, V1, and V2 also provide comparable results in the INCART database. This study demonstrates that fewer leads can be effectively used to diagnose diseases, facilitating the creation of low-cost ECG machines suitable for deployment in rural areas. The code is publicly available at https://github.com/nabeelraza-7/ecg-lead-selection.
References
J. Natarajan, A., Chang, Y., Mariani, S., Rahman, A., Boverman, G., Vij, S., & Rubin, “A wide and deep transformer neural network for 12-lead ECG classification,” IEEE Access, pp. 1–4, 2020.
M. A. U. Rajendra Acharya, Hamido Fujita, Shu Lih Oh, Yuki Hagiwara, Jen Hong Tan, “Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals,” Inf. Sci. (Ny)., vol. 415–416, pp. 190–198, 2017, doi: https://doi.org/10.1016/j.ins.2017.06.027.
F. A.-M. Majid Sepahvand, “A novel method for reducing arrhythmia classification from 12-lead ECG signals to single-lead ECG with minimal loss of accuracy through teacher-student knowledge distillation,” Inf. Sci. (Ny)., vol. 593, pp. 64–77, 2022, doi: https://doi.org/10.1016/j.ins.2022.01.030.
J. X. Shenda Hong, Meng Wu, Yuxi Zhou,Qingyun Wang, Junyuan Shang, Hongyan Li1, “ENCASE: an ENsemble ClASsifiEr for ECG Classification Using Expert Features and Deep Neural Networks,” Comput. Cardiol. (2010)., vol. 44, 2017, [Online]. Available: https://www.cinc.org/archives/2017/pdf/178-245.pdf
B. Z. Runchuan Li, Xingjin Zhang, “Interpretability Analysis of Heartbeat Classification Based on Heartbeat Activity’s Global Sequence Features and BiLSTM-Attention Neural Network,” IEEE Access, 2019, doi: 10.1109/ACCESS.2019.2933473.
W. W. Jian Guan, Wenbo Wang, Pengming Feng, Xinxin Wang, “Low-dimensional Denoising Embedding Transformer for ECG Classification,” arXiv:2103.17099, 2021, doi: https://doi.org/10.48550/arXiv.2103.17099.
S. H. W. Yen Chun Chang, “AF Detection by Exploiting the Spectral and Temporal Characteristics of ECG Signals with the LSTM Model,” Comput. Cardiol. (2010)., 2018, [Online]. Available: https://scholar.nycu.edu.tw/en/publications/af-detection-by-exploiting-the-spectral-and-temporal-characterist
L. Z. Xiuzhu Yang, Xinyue Zhang, Mengyao Yang, “12-Lead ECG arrhythmia classification using cascaded convolutional neural network and expert feature,” J. Electrocardiol., vol. 67, pp. 56–62, 2021, doi: https://doi.org/10.1016/j.jelectrocard.2021.04.016.
T. B. S. & A. L. P. R. Antônio H. Ribeiro, Manoel Horta Ribeiro, Gabriela M. M. Paixão, Derick M. Oliveira, Paulo R. Gomes, Jéssica A. Canazart, Milton P. S. Ferreira, Carl R. Andersson, Peter W. Macfarlane, Wagner Meira Jr., “Automatic diagnosis of the 12-lead ECG using a deep neural network,” Nat. Commun., 2020, doi: https://doi.org/10.1038/s41467-020-15432-4.
W. W. Ahmed Mostayed, Junye Luo, Xingliang Shu, “Classification of 12-Lead ECG Signals with Bi-directional LSTM Network,” arXiv:1811.02090, 2018, doi: https://doi.org/10.48550/arXiv.1811.02090.
K. P. Sandra Śmigiel, “ECG Signal Classification Using Deep Learning Techniques Based on the PTB-XL Dataset,” Entropy, vol. 23, no. 9, p. 1121, 2021, doi: https://doi.org/10.3390/e23091121.
Z. H. Genlang Chen, “A cascaded classifier for multi-lead ECG based on feature fusion,” Comput Methods Programs Biomed, 2019, doi: 10.1016/j.cmpb.2019.06.021.
T. I. & M. G. Serkan Kiranyaz, “Personalized Monitoring and Advance Warning System for Cardiac Arrhythmias,” Sci. Reports Vol., 2017, doi: https://doi.org/10.1038/s41598-017-09544-z.
A. P. Neha Shukla, “[Retracted] ECG-ViT: A Transformer-Based ECG Classifier for Energy-Constraint Wearable Devices,” J. Sensors, 2022, doi: https://doi.org/10.1155/2022/2449956.
S. Y. Yunan Wu, Feng Yang, Ying Liu, Xuefan Zha, “A Comparison of 1-D and 2-D Deep Convolutional Neural Networks in ECG Classification,” arXiv:1810.07088, 2018, doi: https://doi.org/10.48550/arXiv.1810.07088.
N. S. Patrick Wagner, “PTB-XL, a large publicly available electrocardiography dataset,” Sci. Data, 2020, [Online]. Available: https://physionet.org/content/ptb-xl/1.0.3/
L. A. A. A. L. Goldberger, “PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals,” Circulation, vol. 101, 2000, doi: 10.1161/01.cir.101.23.e215.
R. S. T. Shubhojeet Chatterjee, “Review of noise removal techniques in ECG signals,” IET Signal Process., vol. 14, no. 9, p. 12, 2020, doi: 10.1049/iet-spr.2020.0104.
C.-C. C. & F. R. Tsui, “Comparing different wavelet transforms on removing electrocardiogram baseline wanders and special trends,” BMC Med. Inform. Decis. Mak., vol. 20, 2020, doi: https://doi.org/10.1186/s12911-020-01349-x.
T. M. A. Matloob Khushi, Kamran Shaukat, “A Comparative Performance Analysis of Data Resampling Methods on Imbalance Medical Data,” IEEE Access, 2021, doi: 10.1109/ACCESS.2021.3102399.
T. M. Alam et al., “A Machine Learning Approach for Identification of Malignant Mesothelioma Etiological Factors in an Imbalanced Dataset,” Comput. J., vol. 65, no. 7, pp. 1740–1751, Jul. 2022, doi: 10.1093/COMJNL/BXAB015.
M. K. Xiaoyan Yang, “Biomarker CA125 Feature Engineering and Class Imbalance Learning Improves Ovarian Cancer Prediction,” IEEE Asia-Pacific Conf. Comput. Sci. Data Eng., 2020, [Online]. Available: https://www.computer.org/csdl/proceedings-article/csde/2020/09411607/1taFbRdyYUw
Z. Wang, W. Yan, and T. Oates, “Time series classification from scratch with deep neural networks: A strong baseline,” IEEE Int. Jt. Conf. Neural Netw., vol. 2017-May, pp. 1578–1585, Jun. 2016, doi: 10.1109/IJCNN.2017.7966039.
L. I. & P.-A. M. Hassan Ismail Fawaz, Germain Forestier, Jonathan Weber, “Deep learning for time series classification: a review,” Data Min. Knowl. Discov., vol. 33, pp. 917–963, 2019, doi: https://doi.org/10.1007/s10618-019-00619-1.
I. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, “Attention is all you need,” Adv. Neural Inf. Process. Syst., p. 30, 2017.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 50sea
This work is licensed under a Creative Commons Attribution 4.0 International License.
