Time-Frequency Feature Integration with Deep Neural Networks for Robust Bundle Branch Block Classification
Received: 12 August 2025 | Revised: 1 September 2025, 12 September 2025, and 25 September 2025 | Accepted: 6 October 2025 | Online: 8 December 2025
Corresponding author: M. B. Prakash
Abstract
Bundle Branch Block (BBB) is a conduction disorder where electrical impulses are delayed or blocked in the heart’s Right or Left BBBs (RBBB or LBBB), causing abnormal ventricular depolarization, seen as a widened QRS complex on an Electrocardiogram (ECG). It can be without symptoms or associated with conditions such as cardiovascular disease or high blood pressure. This research aims to design an inter-patient heartbeat classification approach capable of reliably differentiating between LBBB, RBBB, and Normal heart rhythms. This study presents a comparative analysis of various ECG classification models, focusing on the integration of advanced pre-processing techniques with Deep Learning (DL) architectures using the MIT-BIH Arrhythmia database. The proposed work introduces three Convolution Neural Networks and Long Short Term Memory (CNN-LSTM)-based models: Standard CNN-LSTM, Discrete Wavelet Transform (DWT) enhanced CNN-LSTM, and Hilbert Transform-Wigner Ville Distribution (HT-WVD) enhanced CNN-LSTM. Among these, the latter delivers the best classification accuracy of 99.6%, along with a superior sensitivity of 98.83%, specificity of 99.43%, and an F1- Score of 98.98%. The DWT with CNN-LSTM and the Standard CNN-LSTM models also demonstrate high performance, confirming the effectiveness of the hybrid time-frequency domain pre-processing for capturing intricate ECG patterns, especially as RBBB and LBBB. The results show that combining signal processing with DL techniques can lead to accurate and trustworthy ECG interpretation.
Keywords:
bundle branch block, deep learning, discrete wavelet transform, Hilbert transform-Wigner Ville distributionDownloads
References
S. I. Khan and R. B. Pachori, "Automated Bundle Branch Block Detection Using Multivariate Fourier–Bessel Series Expansion-Based Empirical Wavelet Transform," IEEE Transactions on Artificial Intelligence, vol. 5, no. 11, pp. 5643–5654, Nov. 2024. DOI: https://doi.org/10.1109/TAI.2024.3420259
Y. Zhang, J. Yu, Y. Zhang, C. Liu, and J. Li, "A Convolutional Neural Network for Identifying Premature Ventricular Contraction Beat and Right Bundle Branch Block Beat," in 2018 International Conference on Sensor Networks and Signal Processing (SNSP), Jul. 2018, pp. 158–162. DOI: https://doi.org/10.1109/SNSP.2018.00037
Ö. Eravcı and N. Özkurt, "Arrhythmia Detection with Custom Designed Wavelet-based Convolutional Autoencoder," in 2023 International Conference on Innovations in Intelligent Systems and Applications (INISTA), Sep. 2023, pp. 1–5. DOI: https://doi.org/10.1109/INISTA59065.2023.10310328
R. Navya, B. Santhosh Krishna, R. Anurag, and S. Satheeshkumar, "Cardiac Arrhythmia - Prediction and Classification using Support Vector Machine," in 2023 International Conference on System, Computation, Automation and Networking (ICSCAN), Aug. 2023, pp. 1–4. DOI: https://doi.org/10.1109/ICSCAN58655.2023.10394774
R. Allami, A. Stranieri, V. Balasubramanian, and H. F. Jelinek, "A genetic algorithm-neural network wrapper approach for bundle branch block detection," in 2016 Computing in Cardiology Conference (CinC), Vancouver, BC, Canada, Sep. 2016, pp. 461–464, [Online]. Available: https://ieeexplore.ieee.org/document/7868779. DOI: https://doi.org/10.22489/CinC.2016.132-174
A. Jaiswal and S. Dandapat, "Leveraging Convolutional Autoencoders for Bundle Branch Block Detection in Electrocardiograms," in 2024 International Conference on Signal Processing and Communications (SPCOM), Jul. 2024, pp. 1–5. DOI: https://doi.org/10.1109/SPCOM60851.2024.10631605
D. Khuat Van, T. Anh Tran, T.-H. Thi Nguyen, and M. Tuan Nguyen, "Deep Learning Based Cardiac Arrhythmia Detection Using Wavelet Transform," in 2024 International Conference on Advanced Technologies for Communications (ATC), Jul. 2024, pp. 744–749. DOI: https://doi.org/10.1109/ATC63255.2024.10908155
S. Ajili, R. Cheour, M. Abid, M. Abid, and R. Hotte, "Automated System Classification of ECG Heartbeat based on Support Vector Machine and Convolutional Neural Network," in 2024 IEEE 7th International Conference on Advanced Technologies, Signal and Image Processing (ATSIP), Jul. 2024, vol. 1, pp. 576–581. DOI: https://doi.org/10.1109/ATSIP62566.2024.10638983
B. Al-Naami, H. Fraihat, H. A. Owida, K. Al-Hamad, R. De Fazio, and P. Visconti, "Automated Detection of Left Bundle Branch Block from ECG Signal Utilizing the Maximal Overlap Discrete Wavelet Transform with ANFIS," Computers, vol. 11, no. 6, Jun. 2022, Art. no. 93. DOI: https://doi.org/10.3390/computers11060093
Y. Jin, Z. Li, Y. Tian, X. Wei, and C. Liu, "A self-supervised framework for computer-aided arrhythmia diagnosis," Applied Soft Computing, vol. 164, Oct. 2024, Art. no. 112024. DOI: https://doi.org/10.1016/j.asoc.2024.112024
A. Sadeghi, A. Rezaee, and F. Hajati, "Diagnosing Left Bundle Branch Block in 12-lead Electrocardiogram using Self-Attention Convolutional Neural Networks." medRxiv, Jun. 29, 2023, Art. no. 2023.06.25.23291867. DOI: https://doi.org/10.1101/2023.06.25.23291867
J. J. Kolliyil and M. C. Brindise, "Automated detection of arrhythmias using a novel interpretable feature set extracted from 12-lead electrocardiogram," Computers in Biology and Medicine, vol. 189, May 2025, Art. no. 109957. DOI: https://doi.org/10.1016/j.compbiomed.2025.109957
S. Mishra et al., "ECG Paper Record Digitization and Diagnosis Using Deep Learning," Journal of Medical and Biological Engineering, vol. 41, no. 4, pp. 422–432, Aug. 2021. DOI: https://doi.org/10.1007/s40846-021-00632-0
S. S. Ilić, "Detection of the left bundle branch block in continuous wavelet transform of ECG signal," Elektronika ir elektrotechnika., no. 2, pp. 33–36, 2007.
B. Macas, J. Garrigós, J. J. Martínez, J. M. Ferrández, and M. P. Bonomini, "An explainable machine learning system for left bundle branch block detection and classification," Integrated Computer-Aided Engineering, vol. 31, no. 1, pp. 43–58, Feb. 2024. DOI: https://doi.org/10.3233/ICA-230719
P. S. Kammath, V. V. Gopal, and J. Kuriakose, "Detection of Bundle Branch Blocks using Machine Learning Techniques," Indonesian Journal of Electrical Engineering and Informatics, vol. 10, no. 3, pp. 559–566, Aug. 2022. DOI: https://doi.org/10.52549/ijeei.v10i3.3852
H. Huang, J. Liu, Q. Zhu, R. Wang, and G. Hu, "Detection of inter-patient left and right bundle branch block heartbeats in ECG using ensemble classifiers," BioMedical Engineering OnLine, vol. 13, no. 1, Jun. 2014, Art. no. 72. DOI: https://doi.org/10.1186/1475-925X-13-72
Y. Kaya, "Detection of Bundle Branch Block using Higher Order Statistics and Temporal Features," The International Arab Journal of Information Technology, vol. 18, no. 3, May 2021. DOI: https://doi.org/10.34028/iajit/18/3/3
Y. Cheng, D. Li, D. Wang, Y. Chen, and L. Wang, "Multi-label arrhythmia classification using 12-lead ECG based on lead feature guide network," Engineering Applications of Artificial Intelligence, vol. 129, Mar. 2024, Art. no. 107599. DOI: https://doi.org/10.1016/j.engappai.2023.107599
T. Ikeda, "Right Bundle Branch Block: Current Considerations," Current Cardiology Reviews, vol. 17, no. 1, pp. 24–30. DOI: https://doi.org/10.2174/1573403X16666200708111553
J. Kim, J.-W. Lee, and K. Kim, "Classification of cardiac arrhythmias using deep learning," International Journal of Engineering & Technology, vol. 7, no. 3.3, Jun. 2018, Art. no. 401. DOI: https://doi.org/10.14419/ijet.v7i2.33.14195
Y. Kutlu and D. Kuntalp, "Feature extraction for ECG heartbeats using higher order statistics of WPD coefficients," Computer Methods and Programs in Biomedicine, vol. 105, no. 3, pp. 257–267, Mar. 2012. DOI: https://doi.org/10.1016/j.cmpb.2011.10.002
Q. Mastoi et al., "Novel DERMA Fusion Technique for ECG Heartbeat Classification," Life, vol. 12, no. 6, Jun. 2022, Art. no. 842. DOI: https://doi.org/10.3390/life12060842
Ö. Yildirim, "A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification," Computers in Biology and Medicine, vol. 96, pp. 189–202, May 2018. DOI: https://doi.org/10.1016/j.compbiomed.2018.03.016
X. Yang, X. Zhang, M. Yang, and L. Zhang, "12-Lead ECG arrhythmia classification using cascaded convolutional neural network and expert feature," Journal of Electrocardiology, vol. 67, pp. 56–62, Jul. 2021. DOI: https://doi.org/10.1016/j.jelectrocard.2021.04.016
A. Pratima, K. Gopalakrishna, and S. N. Prasad, "A Comparative Analysis of Advanced Deep Learning Techniques for Accurate Cardiac Arrhythmia Classification," Engineering, Technology & Applied Science Research, vol. 15, no. 4, pp. 25008–25013, Aug. 2025. DOI: https://doi.org/10.48084/etasr.11333
K. Viswateja, D. Supriya, K. B. Jahnavi, and V. Aruna, "Optimizing the Early Detection of Heart Disease with Improved Feature Selection Using Machine Learning Model," in 2024 International Conference on Computing, Sciences and Communications (ICCSC), Jul. 2024, pp. 1–6. DOI: https://doi.org/10.1109/ICCSC62048.2024.10830387
S. Sriram, P. Vyshnavi, V. Nivethitha, M. Thangavel, and S. Ravikumar, "Arrhythmia Classification using Supervised Machine Learning Algorithms," in 2024 International Conference on Electronic Systems and Intelligent Computing (ICESIC), Aug. 2024, pp. 185–190. DOI: https://doi.org/10.1109/ICESIC61777.2024.10846101
P. Sharma and S. K. Dinkar, "An intelligent deep neural network with Opposition based Laplacian Equilibrium Optimizer to improve feature extraction using ECG signals," Biomedical Signal Processing and Control, vol. 87, Jan. 2024, Art. no. 105415. DOI: https://doi.org/10.1016/j.bspc.2023.105415
H. Ullah et al., "An Automatic Premature Ventricular Contraction Recognition System Based on Imbalanced Dataset and Pre-Trained Residual Network Using Transfer Learning on ECG Signal," Diagnostics, vol. 13, no. 1, Jan. 2023, Art. no. 87. DOI: https://doi.org/10.3390/diagnostics13010087
J. An, R. Gregg, B. Bailey, Y.-H. Zhang, and D. J. Dzikowicz, "Left Bundle Branch Block Detection in 12-Lead ECG Using End-to-End Deep Learning with Explainability," presented at the 2024 Computing in Cardiology Conference, Dec. 2024. DOI: https://doi.org/10.22489/CinC.2024.067
J. Hu et al., "Deep Multi-instance Networks for Bundle Branch Block Detection from Multi-lead ECG," in 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Jul. 2020, pp. 353–356. DOI: https://doi.org/10.1109/EMBC44109.2020.9175909
M. Kolhar and A. M. Al Rajeh, "Deep learning hybrid model ECG classification using AlexNet and parallel dual branch fusion network model," Scientific Reports, vol. 14, no. 1, Nov. 2024, Art. no. 26919. DOI: https://doi.org/10.1038/s41598-024-78028-8
N. Perera and C. Daluwatte, "Detecting Strict Left Bundle Branch Block From 12-Lead Electrocardiogram Using Support Vector Machine Classification and Derivative Analysis," in Computing in Cardiology 2018, Dec. 2018, vol. 45, pp. 1-40. DOI: https://doi.org/10.22489/CinC.2018.030
A. Odugoudar and J. S. Walia, "ECG Classification System for Arrhythmia Detection Using Convolutional Neural Networks." arXiv, Jun. 12, 2024.
A. Isin and S. Ozdalili, "Cardiac arrhythmia detection using deep learning," Procedia Computer Science, vol. 120, pp. 268–275, Jan. 2017. DOI: https://doi.org/10.1016/j.procs.2017.11.238
S.-T. Pan and C.-H. Wu, "A novel model based on CNN for improving computation efficiency on arrhythmia detection by combining HMM," Biomedical Signal Processing and Control, vol. 106, Aug. 2025, Art. no. 107704. DOI: https://doi.org/10.1016/j.bspc.2025.107704
B. Hou, J. Yang, P. Wang, and R. Yan, "LSTM-Based Auto-Encoder Model for ECG Arrhythmias Classification," IEEE Transactions on Instrumentation and Measurement, vol. 69, no. 4, pp. 1232–1240, Apr. 2020. DOI: https://doi.org/10.1109/TIM.2019.2910342
Downloads
How to Cite
License
Copyright (c) 2025 M. B. Prakash, H. M. Harish
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License 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) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
