CADDet: A Machine Learning Framework for Coronary Artery Disease Prediction Using Heart Sound Signals
Article Sidebar
Main Article Content
Abstract
Coronary artery disease (CAD) continues at the forefront of mortality sources across the globe. Its early detection using heart sound signals seems promising for integration into Wearable Body Area Networks (WBANs). On the other hand, WBAN-based CAD detection systems face challenges such as noise, motion artefacts, and poor signal quality, which in turn reduce diagnostic performance. Literature surveys indicate that most current models struggle due to insufficient feature extraction, fragile classification, and poor generalisation, leading to the outlined dilemma. We propose a robust classification algorithm that combines MFCC feature extraction with Random Forests to achieve high detection accuracy, addressing these problems and filling the research gap. For our research, we used the Heartbeat Sounds datasets from Kaggle, which encompass recordings from both clinical and non-clinical environments (Sets A and B). We derived 13 MFCC features per recording and employed an 80-20 stratified train-test split to balance the evaluation. The Random Forest classifier, powered by 100 decision trees, has achieved astonishing effectiveness, with 95% overall accuracy, 0.97 F1 Score for healthy cases, and 0.86 F1 Score for pathological cases. Our results exceed those of five recent baseline papers by a wide margin in precision, recall, and overall classification accuracy. Thus, they support the validity of the method we proposed for CAD detection using real heart sound data.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
How to Cite
References
Dai, Y., Liu, P., Hou, W., Kadier, K., Mu, Z., Lu, Z., Chen, P., Ma, X., & Dai, J. (2024). Deep-learning fusion framework for automated detection of coronary artery disease using raw heart sound signals. Heliyon, 10(4), e16623. DOI: https://doi.org/10.1016/j.heliyon.2024.e35631
H. Li, X. Wang, C. Liu, Q. Zeng, Y. Zheng, X. Chu, C. Karmakar, A fusion framework based on multi-domain features and deep learning features of phonocardiogram for coronary artery disease detection, Comput. Biol. Med. 120 (2020) 103733,
DOI: https://doi.org/10.1016/j.compbiomed.2020.103733
T. Liu, P. Li, Y. Liu, H. Zhang, Y. Li, Y. Jiao, X. Wang, Detection of coronary artery disease using multi-domain feature fusion of multi-channel heart sound signals, Entropy 23 (6) (2021) 642, DOI: https://doi.org/10.3390/e23060642
A.Ainiwaer, W.Q. Hou, Q. Qi, K. Kadier, L. Qin, R. Rehemuding, Y.T. Ma, Deep learning of heart-sound signals for efficient prediction of obstructive coronary artery disease, Heliyon 10 (1) (2024) e23354, DOI: https://doi.org/10.1016/j.heliyon.2023.e23354
J. Fan, S. Tang, H. Duan, X. Bi, B. Xiao, W. Li, X. Gao, Le-lwtnet: a learnable lifting wavelet convolutional neural network for heart sound abnormality detection, IEEE Trans. Instrum. Meas. 72 (2023) 1–14, DOI: https://doi.org/10.1109/TIM.2023.3246513
X. Cheng, Y. Sun, W. Zhang, Y. Wang, X. Cao, Y. Wang, Application of deep learning in multitemporal remote sensing image classification, Rem. Sens. 15 (15) (2023) 3859, DOI: https://doi.org/10.3390/rs15153859
J. Zhang, H. Liu, K. Yang, X. Hu, R. Liu, R. Stiefelhagen, CMX: cross-modal fusion for RGB-X semantic segmentation with transformers, IEEE Trans. Intell. Transport. Syst. (2023), DOI: https://doi.org/10.1109/TITS.2023.3300537
J. Liu, H. Wang, Z. Yang, J. Quan, L. Liu, J. Tian, Deep learning-based computer-aided heart sound analysis in children with left-to-right shunt congenital heart disease, Int. J. Cardiol. 348 (2022) 58–64, DOI: https://doi.org/10.1016/j.ijcard.2021.12.012
W. Chen, Z. Zhou, J. Bao, C. Wang, H. Chen, C. Xu, H. Wu, classifying heart-sound signals based on CNN trained on MelSpectrum and log-MelSpectrum features, Bioengineering 10 (6) (2023) 645, DOI: https://doi.org/10.3390/bioengineering10060645
A.Yadav, A. Singh, M.K. Dutta, C.M. Travieso, Machine learning-based classification of cardiac diseases from PCG recorded heart sounds, Neural Comput. Appl. 32 (24) (2020) 17843–17856, DOI: https://doi.org/10.1007/s00521-019-04547-5
S. Aziz, M.U. Khan, M. Alhaisoni, T. Akram, M. Altaf, Phonocardiogram signal processing for automatic diagnosis of congenital heart disorders through fusion of temporal and cepstral features, Sensors 20 (13) (2020) 3790, DOI: https://doi.org/10.3390/s20133790
M.A. Soto-Murillo, J.I. Galvan-Tejada, C.E. Galvan-Tejada, J.M. Celaya-Padilla, H. Luna-Garcia, R. Magallanes-Quintanar, H. Gamboa-Rosales, Automatic evaluation of heart condition according to the sounds emitted and implementing six classification methods, in: Healthcare, vol. 9, MDPI, 2021, March, p. 317, DOI: https://doi.org/10.3390/healthcare9030317
X. Bao, Y. Xu, E.N. Kamavuako, The effect of signal duration on the classification of heart sounds: a deep learning approach, Sensors 22 (6) (2022) 2261, DOI: https://doi.org/10.3390/s22062261
S.E. Schmidt, C. Holst-Hansen, J. Hansen, E. Toft, J.J. Struijk, Acoustic features for the identification of coronary artery disease, IEEE Trans. Biomed. Eng. 62 (11) (2015) 2611–2619, DOI: https://doi.org/10.1109/TBME.2015.2432129. The works remain significant, see the declaration
Kaggle Dataset for Heart Sound Signals [https://www.kaggle.com/datasets/kinguistics/heartbeat-sounds]