Deep learning driven electrocardiogram classification ‎with optimized convolutional neural network for ‎accurate arrhythmia detection and explainable clinical

Authors

  • Kamala Priya Anthani

    Research Scholar, Department of Computer Science and Engineering, GITAM School of Technology, GITAM (Deemed to be ‎ University), Visakhapatnam, Andhra Pradesh, India

  • Bhavani Madireddy

    Associate Professor, Department of Computer Science and Engineering, GITAM School of Technology, GITAM (Deemed to be ‎ University),Visakhapatnam, Andhra Pradesh, India

How to Cite

Anthani, K. P., & Madireddy, B. . (2025). Deep learning driven electrocardiogram classification ‎with optimized convolutional neural network for ‎accurate arrhythmia detection and explainable clinical. International Journal of Basic and Applied Sciences, 14(1), 251-263. https://doi.org/10.14419/sbrrvz11

Received date: April 14, 2025

Accepted date: May 8, 2025

Published date: May 11, 2025

DOI:

https://doi.org/10.14419/sbrrvz11

Keywords:

ECG Classification; Deep Learning; Convolutional Neural Network; Arrhythmia Detection; Explainable AI; Real-Time Monitoring; Cross-Dataset ‎Validation

Abstract

Since cardiovascular diseases are the top cause globally, there is a critical need to develop dependable automated electrocardiogram ‎‎(ECG) classification systems that can detect arrhythmias early. Existing deep learning models for ECG classification demonstrate potential ‎for enhanced accuracy but encounter obstacles related to class imbalance, limited generalization across different datasets, computational inef,‎ and interpretability issues. The paper presents an enhanced CNN-based ECG classification framework which merges multi-scale ‎feature extraction with sophisticated preprocessing methods and explainability tools to resolve prevalent model limitations. The model combines wavelet-based noise reduction with hybrid approaches to class balance through synthetic data creation and domain adaptation, which ‎results in improved detection of uncommon arrhythmias. The use of Grad-CAM and SHAP-based visualizations enhances clinical interpretability by providing clear insights into model predictions. Real-time execution optimization with minimal computational overhead enables ‎this model to function appropriately for wearable cardiac monitoring applications. The experimental findings show that the proposed CNN ‎model reached 98.86% test accuracy, which surpasses the performance of current deep learning models. The model maintains computational ‎efficiency as it achieves better generalization and interpretability. This research advances AI-driven cardiac diagnostics by connecting AI-based ECG classification with real-world clinical applications to enable reliable and interpretable arrhythmia detection systems that can be ‎deployed in practice‎. 

References

  1. P. Gupta, R. Kumar, and S. Roy, “Application of autoregressive modeling for baseline drift removal in ECG signals,” Biomed. Signal Process. Con-trol, vol. 76, pp. 103687, 2023. https://doi.org/10.1016/j.bspc.2022.103687.
  2. S. Banerjee and S. Mitra, “ECG arrhythmia classification using hidden Markov models,” Pattern Recognit. Lett., vol. 162, pp. 45–52, 2022. https://doi.org/10.1016/j.patrec.2022.01.010.
  3. M. S. Ahmed, S. Haider, and M. Shafi, “ECG signal classification using combined method of wavelet transform and SMOTE with machine learn-ing techniques,” in Proceedings of the 2020 IEEE 23rd International Conference on Information Fusion (FUSION), Rustenburg, South Africa, 6–9 July 2020, pp. 1–6.
  4. C. Shen, X. Zhao, X. Wu, H. Cao, C. Wang, J. Tang, and J. Liu, “Multiaperture visual velocity measurement method based on biomimetic com-pound-eye for UAVs,” IEEE Internet Things J., vol. 11, pp. 11165–11174, 2024. https://doi.org/10.1109/JIOT.2023.3324966.
  5. S. Elouaham, A. Dliou, W. Jenkal, M. Louzazni, H. Zougagh, and S. Dlimi, “Empirical wavelet transform based ECG signal filtering method,” J. Electr. Comput. Eng., vol. 2024, pp. 9050909, 2024. https://doi.org/10.1155/2024/9050909.
  6. X. Liu, J. Tang, C. Shen, C. Wang, D. Zhao, X. Guo, J. Li, and J. Liu, “Brain-like position measurement method based on improved optical flow algorithm,” ISA Trans., vol. 143, pp. 221–230, 2023. https://doi.org/10.1016/j.isatra.2023.02.015.
  7. J. Xu, L. Zhang, and T. Zhao, “ECG-TransCovNet: A hybrid CNN-Transformer architecture for large-scale ECG arrhythmia classification,” IET Cyber-Phys. Syst. Theory Appl., vol. 2, pp. 98–108, 2023. https://doi.org/10.1049/cps2.12004.
  8. L. V. Rajani Kumari and Y. Chalapathi Rao, “ECG beat classification using proposed pattern adaptive wavelet-based hybrid classifiers,” Signal Image Video Process., vol. 17, pp. 2827–2835, 2023. https://doi.org/10.1007/s11760-023-02501-6.
  9. M. Ramkumar, C. Ganesh Babu, K. Vinoth Kumar, D. Hepsiba, A. Manjunathan, and R. Sarath Kumar, “ECG cardiac arrhythmias classification using DWT, ICA and MLP neural networks,” J. Phys. Conf. Ser., vol. 1831, pp. 012015, 2021. https://doi.org/10.1088/1742-6596/1831/1/012015.
  10. L. Shan, Y. Li, H. Jiang, P. Zhou, J. Niu, R. Liu, Y. Wei, J. Peng, H. Yu, X. Sha, et al., “Abnormal ECG detection based on an adversarial autoen-coder,” Front. Physiol., vol. 13, pp. 961724, 2022. https://doi.org/10.3389/fphys.2022.961724.
  11. B. Babusiak, S. Borik, and M. Smondrk, “Two-electrode ECG for ambulatory monitoring with minimal hardware complexity,” Sensors, vol. 20, no. 8, pp. 2386, Apr. 2020. https://doi.org/10.3390/s20082386.
  12. S. Liu, J. Shao, T. Kong, and R. Malekian, “ECG arrhythmia classification using high order spectrum and 2D graph Fourier transform,” Appl. Sci., vol. 10, no. 14, pp. 4741, Jul. 2020. https://doi.org/10.3390/app10144741.
  13. M. S. Islam, K. F. Hasan, S. Sultana, S. Uddin, P. Lió, J. M. W. Quinn, et al., “HARDC: A novel ECG-based heartbeat classification method to detect arrhythmia using hierarchical attention-based dual structured RNN with dilated CNN,” Neural Netw., vol. 162, pp. 271–287, May 2023. https://doi.org/10.1016/j.neunet.2023.01.007.
  14. S. Zhang, C. Lian, B. Xu, Y. Su, and A. Alhudhaif, “12-lead ECG signal classification for detecting ECG arrhythmia via an information bottle-neck-based multi-scale network,” Inf. Sci., vol. 662, Mar. 2024. https://doi.org/10.1016/j.ins.2024.120239.
  15. H. Narotamo, M. Dias, R. Santos, A. V. Carreiro, H. Gamboa, and M. Silveira, “Deep learning for ECG classification: A comparative study of 1D and 2D representations and multimodal fusion approaches,” Biomed. Signal Process. Control, vol. 93, Jul. 2024. https://doi.org/10.1016/j.bspc.2024.106141.
  16. S.-F. Li, M.-L. Huang, and Y.-S. Wu, “Combining the Taguchi method and convolutional neural networks for arrhythmia classification by using ECG images with single heartbeats,” Mathematics, vol. 11, no. 13, pp. 2841, Jun. 2023. https://doi.org/10.3390/math11132841.
  17. Eleyan and E. Alboghbaish, “Electrocardiogram signals classification using deep-learning-based incorporated convolutional neural network and long short-term memory framework,” Computers, vol. 13, no. 2, pp. 55, Feb. 2024. https://doi.org/10.3390/computers13020055.
  18. F. Khan, X. Yu, Z. Yuan, and A. U. Rehman, “ECG classification using 1-D convolutional deep residual neural network,” PLoS One, vol. 18, no. 4, Apr. 2023. https://doi.org/10.1371/journal.pone.0284176.
  19. X. Zhang, J. Li, Z. Cai, L. Zhao, and C. Liu, “Deep learning-based signal quality assessment for wearable ECGs,” IEEE Instrum. Meas. Mag., vol. 25, no. 5, pp. 41–52, Aug. 2022. https://doi.org/10.1109/MIM.2022.9832823.
  20. Farooq, M. Seyedmahmoudian, and A. Stojcevski, “A wearable wireless sensor system using machine learning classification to detect arrhythmia,” IEEE Sensors J., vol. 21, no. 9, pp. 11109–11116, May 2021. https://doi.org/10.1109/JSEN.2021.3062395.
  21. S. Akbar, A. Raza, T. Al Shloul, A. Ahmad, A. Saeed, Y. Y. Ghadi, et al., “PAtbP-EnC: Identifying anti-tubercular peptides using multi-feature representation and genetic algorithm-based deep ensemble model,” IEEE Access, vol. 11, pp. 137099–137114, 2023. https://doi.org/10.1109/ACCESS.2023.3286729.
  22. S. Bhattacharyya, S. Majumder, P. Debnath, and M. Chanda, “Arrhythmic heartbeat classification using ensemble of random forest and support vector machine algorithm,” IEEE Trans. Artif. Intell., vol. 2, no. 3, pp. 260–268, Jun. 2021. https://doi.org/10.1109/TAI.2021.3083689.
  23. C. Zou, A. Müller, U. Wolfgang, D. Rückert, P. Müller, M. Becker, et al., “Heartbeat classification by random forest with a novel context feature: A segment label,” IEEE J. Translational Eng. Health Med., vol. 10, pp. 1–8, 2022. https://doi.org/10.1109/JTEHM.2022.3202749.
  24. Y. Ping, C. Chen, L. Wu, Y. Wang, and M. Shu, “CNN-LSTM and shortcut connection-based automatic atrial fibrillation detection,” J. Phys. Conf. Ser., vol. 913, pp. 012004, 2020. https://doi.org/10.1088/1742-6596/913/1/012004.
  25. G. Bortolan, I. Christov, and I. Simova, “Rule-based approach and deep learning networks for automatic ECG categorization,” in Proceedings of the 2020 Computing in Cardiology (CinC), Rimini, Italy, Sep. 2020, pp. 1–4. https://doi.org/10.22489/CinC.2020.116.
  26. Demonbreun and G. M. Mirsky, “Automated classification of electrocardiograms using wavelet analysis and deep learning,” in Proceedings of the 2020 Computing in Cardiology (CinC), Rimini, Italy, Sep. 2020, pp. 1–4. https://doi.org/10.22489/CinC.2020.138.
  27. K. Cornely, A. Carrillo, and G. M. Mirsky, “Reduced-lead ECG classification using wavelet analysis and deep learning,” in Proceedings of the 2021 Computing in Cardiology (CinC), Brno, Czech Republic, Sep. 2021, pp. 1–4. https://doi.org/10.23919/CinC53138.2021.9662813.
  28. J. Chen, T. Chen, and B. Xiao, “SE-ECGNet: Multi-scale SE-Net for multi-lead ECG data,” in Proceedings of the 2020 Computing in Cardiology (CinC), Rimini, Italy, Sep. 2020, pp. 1–4. https://doi.org/10.22489/CinC.2020.085.
  29. T. Golany, K. Radinsky, and D. Freedman, “Simgans: Simulator-based generative adversarial networks for ECG synthesis to improve deep ECG classification,” in Proceedings of the International Conference on Machine Learning (PMLR), Chennai, India, Nov. 2020, pp. 3597–3606.
  30. M. M. Hussain, U. Rafi, A. Imran, M. U. Rehman, and S. K. Abbas, “Risk factors associated with cardiovascular disorders,” Pak. BioMed. J., vol. 2024, pp. 03–10, 2024. https://doi.org/10.54393/pbmj.v7i02.1034.
  31. T. Fan, et al., “A new deep convolutional neural network incorporating attentional mechanisms for ECG emotion recognition,” Comput. Biol. Med., vol. 159, pp. 106938, 2023. https://doi.org/10.1016/j.compbiomed.2023.106938.
  32. S. Zhang and D. Metaxas, “On the challenges and perspectives of foundation models for medical image analysis,” Med. Image Anal., vol. 2023, pp. 102996, 2023. https://doi.org/10.1016/j.media.2023.102996.
  33. Y. H. Bhosale and K. S. Patnaik, “Bio-medical imaging (X-ray, CT, ultrasound, ECG), genome sequences applications of deep neural network and machine learning in diagnosis, detection, classification, and segmentation of COVID-19: A meta-analysis & systematic review,” Multimed. Tools Appl., vol. 82, no. 25, pp. 39157–39210, 2023. https://doi.org/10.1007/s11042-023-15029-1.
  34. Song, R. Zhou, and F. Ahmed, “Multi-modal machine learning in engineering design: A review and future directions,” J. Comput. Inf. Sci. Eng., vol. 24, no. 1, pp. 010801, 2024. https://doi.org/10.1115/1.4063911.
  35. X. Xu, et al., “A comprehensive review on synergy of multi-modal data and AI technologies in medical diagnosis,” Bioengineering, vol. 11, no. 3, pp. 219, 2024. https://doi.org/10.3390/bioengineering11030219.
  36. K. A. Shastry and A. Shastry, “An integrated deep learning and natural language processing approach for continuous remote monitoring in digital health,” Decis. Analytics J., vol. 8, pp. 100301, 2023. https://doi.org/10.1016/j.dajour.2023.100301.
  37. M. Osama, et al., “Internet of medical things and healthcare 4.0: Trends, requirements, challenges, and research directions,” Sensors, vol. 23, no. 17, pp. 7435, 2023. https://doi.org/10.3390/s23177435.
  38. Venkaiahppalaswamy, P. P. Reddy, and S. Batha, “Hybrid deep learning approaches for the detection of diabetic retinopathy using optimized wavelet-based model,” Biomed. Signal Process. Control, vol. 79, pp. 104146, 2023. https://doi.org/10.1016/j.bspc.2022.104146.
  39. N. T. Pham, et al., “Hybrid data augmentation and deep attention-based dilated convolutional-recurrent neural networks for speech emotion recog-nition,” Expert Syst. Appl., vol. 230, pp. 120608, 2023. https://doi.org/10.1016/j.eswa.2023.120608.
  40. R. S. Ram, J. Akilandeswari, and M. V. Kumar, “HybDeepNet: A hybrid deep learning model for detecting cardiac arrhythmia from ECG signals,” Inform. Technol. Control, vol. 52, no. 2, pp. 433–444, 2023. https://doi.org/10.5755/j01.itc.52.2.32993.
  41. S. Khan and V. Kumar, “A novel hybrid GRU-CNN and residual bias (RB) based RB-GRU-CNN models for prediction of PTB diagnostic ECG time series data,” Biomed. Signal Process. Control, vol. 94, pp. 106262, 2024. https://doi.org/10.1016/j.bspc.2024.106262.
  42. Q. Xiao, et al., “Deep learning-based ECG arrhythmia classification: A systematic review,” Appl. Sci., vol. 13, no. 8, pp. 4964, 2023. https://doi.org/10.3390/app13084964.
  43. W. Chorney and H. Wang, “Towards federated transfer learning in electrocardiogram signal analysis,” Computers in Biology and Medicine, vol. 170, p. 107984, Jan. 2024, https://doi.org/10.1016/j.compbiomed.2024.107984.
  44. P. K. Sekharamantry, M. S. Rao, Y. Srinivas, and A. Uriti, “PSR-LeafNet: a deep learning framework for identifying medicinal plant leaves using support vector machines,” Big Data and Cognitive Computing, vol. 8, no. 12, p. 176, Dec. 2024. https://doi.org/10.3390/bdcc8120176.

Downloads

How to Cite

Anthani, K. P., & Madireddy, B. . (2025). Deep learning driven electrocardiogram classification ‎with optimized convolutional neural network for ‎accurate arrhythmia detection and explainable clinical. International Journal of Basic and Applied Sciences, 14(1), 251-263. https://doi.org/10.14419/sbrrvz11

Received date: April 14, 2025

Accepted date: May 8, 2025

Published date: May 11, 2025