Citation :

R. Ratheesh, M. Saranya Nair, N.V.S. Sree Rathna Lakshmi, Blessina Preethi R, "Spatial Attention-Enhanced Bidirectional Transformer Network for Cardiovascular Disease Classification," International Journal of Electronics and Communication Engineering, vol. 13, no. 4, pp. 35-51, 2026. Crossref, https://doi.org/10.14445/23488549/IJECE-V13I4P103

Abstract

Most people were affected by this Cardiovascular Disease (CVD), which is caused by atherosclerosis and some infections. The early detection of CVD has a higher chance of recovering the person from this disease. In tradition, biosensors such as lab–on–a–chip technology were used to detect the CVD. CVD does not accurately detect the disease, and it is more expensive. Even though nanomaterials like nanotubes and nanowires offer special physical and chemical properties, they also have certain limitations. Diagnosing the disease based on just one biometer is not reliable, and it is hard to identify the conditions apart from using a single indicator. In this system, an optimized spatial attention Bidirectional Transformer Network is utilized to detect Cardiovascular Disease. The clinical data is pre-processed by using Missing value imputation and ECG signals by One-hot-encoding algorithms. The pre-processed ECG signals are denoised by using a Narrowband filter (NBF). The features of the pre-processed clinical data are extracted by a Dense-assisted Global Attention-Based Autoencoder (DGA-AE), and features of denoised ECG signals are extracted by using Multiwavelet Transform-Based Feature Decomposition (MT-FD). The data are merged and optimized by the Bidirectional transformer and the POA (Puma Optimization Algorithm) algorithm. The testing of the datasets achieved a high accuracy. In contrast, the ECG dataset from Ptb-XL gives an accuracy of 95.34%, and the second dataset, Cardiovascular Disease detection, gives an accuracy of 97.21%, respectively. The overall performance demonstrated that the proposed model exceeds the baseline models, and it effectively improved the early detection of cardiovascular diseases with high accuracy.

Keywords

Cardiovascular Disease Detection, Bidirectional Transformer Network, Missing Value Imputation, One-Hot Encoding, Multiwavelet Transform-Based Feature Decomposition, Puma Optimization.

References

1. Abdullah Alqahtani et al., “Cardiovascular Disease Detection using Ensemble Learning,” Computational Intelligence and Neuroscience, vol. 2022, pp. 1-9, 2022.
   [CrossRef] [Google Scholar] [Publisher Link]
2. Yuansheng Gao, Architecture of the Blood Vessels, Biology of Vascular Smooth Muscle: Vasoconstriction and Dilatation, pp. 3-17, Springer, 2022.
   [CrossRef] [Google Scholar] [Publisher Link]
3. Jay P. Rabadia et al., Cardiovascular System, its Functions and Disorders, Cardioprotective Plants, pp. 1-34, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
4. Christiana Wuche, “The Cardiovascular System and Associated Disorders,” British Journal of Nursing, vol. 31, no. 17, pp. 886-892, 2022.
   [CrossRef] [Google Scholar] [Publisher Link]
5. Muhammad Hamid et al., “Fine Tuned CatBoost Machine Learning Approach for Early Detection of Cardiovascular Disease through Predictive Modeling,” Scientific Reports, vol. 15, pp. 1-15, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
6. Mohammed B. Abubaker, and Bilal Babayiğit, “Detection of Cardiovascular Diseases in ECG Images Using Machine Learning and Deep Learning Methods,” IEEE Transactions on Artificial Intelligence, vol. 4, no. 2, pp. 373-382, 2022.
   [CrossRef] [Google Scholar] [Publisher Link]
7. Vivek Pandey, Umesh Kumar Lilhore, and Ranjan Walia, “A Systematic Review on Cardiovascular Disease Detection and Classification,” Biomedical Signal Processing and Control, vol. 102, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
8. Mohammad Moshawrab et al., “Reviewing Multimodal Machine Learning and Its Use in Cardiovascular Diseases Detection,” Electronics, vol. 12, no. 7, pp. 1-30, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
9. Adedayo Ogunpola et al., “Machine Learning-Based Predictive Models for Detection of Cardiovascular Diseases,” Diagnostics, vol. 14, no. 2, pp. 1-19, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
10. Pedro A. Moreno-Sánchez et al., “ECG-based Data-driven Solutions for Diagnosis and Prognosis of Cardiovascular Diseases: A Systematic Review,” Computers in Biology and Medicine, vol. 172, pp. 1-20, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
11. Jiachuan Long et al., “A Comprehensive Review of Signal Processing and Machine Learning Technologies for UHF PD Detection and Diagnosis (II): Pattern Recognition Approaches,” IEEE Access, vol. 12, pp. 29850-29890, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
12. Tahseen Ullah et al., “Machine Learning-based Cardiovascular Disease Detection using Optimal Feature Selection,” IEEE Access, vol. 12, pp. 16431-16446, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
13. Awad Bin Naeem et al., “Heart Disease Detection Using Feature Extraction and Artificial Neural Networks: A Sensor-Based Approach,” IEEE Access, vol. 12, pp. 37349-37362, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
14. Omneya Attallah, “CerCan·Net: Cervical Cancer Classification Model Via Multi-layer Feature Ensembles of Lightweight CNNs and Transfer Learning,” Expert Systems with Applications, vol. 229, pp. 1-40, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
15. Yoon Sang Cho, and Seoung Bum Kim, “Supervised Contrastive Learning for Multisensor Signals Classification in Automobile Engine Manufacturing,” IEEE Transactions on Industrial Informatics, vol. 20, no. 5, pp. 7764-7776, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
16. Lin Liu et al., “Camera-Based Dual-Wavelength Defocused Speckle Imaging for Multi-Point Seismocardiographic Motion Measurement,” IEEE Journal of Biomedical and Health Informatics, pp. 1-13, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
17. D. M. G. Preethichandra et al., “Wireless Body Area Networks and Their Applications—A Review,” IEEE Access, vol. 11, pp. 9202-9220, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
18. Nadiah A. Baghdadi et al., “Advanced Machine Learning Techniques for Cardiovascular Disease Early Detection and Diagnosis,” Journal of Big Data, vol. 10, pp. 1-29, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
19. Serhat Kiliçarslan, “PSO + GWO: A Hybrid Particle Swarm Optimization and Grey Wolf Optimization based Algorithm for Fine-Tuning Hyper-Parameters of Convolutional Neural Networks for Cardiovascular Disease Detection,” Journal of Ambient Intelligence and Humanized Computing, vol. 14, pp. 87-97, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
20. E. I. Elsedimy, Sara M. M. AboHashish, and Fahad Algarni, “New Cardiovascular Disease Prediction Approach using Support Vector Machine and Quantum-behaved Particle Swarm Optimization,” Multimedia Tools and Applications, vol. 83, pp. 23901-23928, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
21. Xi Wei et al., “Risk Assessment of Cardiovascular Disease based on SOLSSA-CatBoost Model,” Expert Systems with Applications, vol. 219, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
22. A. Yashudas et al., “DEEP-CARDIO: Recommendation System for Cardiovascular Disease Prediction Using IoT Network,” IEEE Sensors Journal, vol. 24, no. 9, pp. 14539-14547, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
23. Subasish Mohapatra et al., “A Stacking Classifiers Model for Detecting Heart Irregularities and Predicting Cardiovascular Disease,” Healthcare Analytics, vol. 3, pp. 1-10, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
24. Kellen Sumwiza et al., “Enhanced Cardiovascular Disease Prediction Model using Random Forest Algorithm,” Informatics in Medicine Unlocked, vol. 41, pp. 1-9, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
25. Ghulam Muhammad et al., “Enhancing Prognosis Accuracy for Ischemic Cardiovascular Disease Using K Nearest Neighbor Algorithm: A Robust Approach,” IEEE Access, vol. 11, pp. 97879-97895, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
26. Ali Garavand et al., “Towards Diagnostic Aided Systems in Coronary Artery Disease Detection: A Comprehensive Multiview Survey of the State of the Art,” International Journal of Intelligent Systems, vol. 2023, pp. 1-19, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
27. Muhammad Ali Muzammil et al., “Artificial Intelligence-enhanced Electrocardiography for Accurate Diagnosis and Management of Cardiovascular Diseases,” Journal of Electrocardiology, vol. 83, pp. 30-40, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
28. PTB-XL, A Large Publicly Available Electrocardiography Dataset, PhysioNet, 2022. [Online]. Available: https://physionet.org/content/ptb-xl/1.0.3/
29. Cardiovascular Disease Dataset, Kaggle. [Online]. Available: https://www.kaggle.com/datasets/sulianova/cardiovascular-disease-dataset