Efficient Predictive Modelling of Cardiovascular Disease using Deep Learning Approaches
DOI:
https://doi.org/10.52783/jns.v14.1771Keywords:
Cardiovascular disease, Prediction, ML-GCN model, MFCC, Deep learning, GCN, Heartbeat Sounds, Multi-label image Recognition, Transformer, CNN.Abstract
In order to improve the identification and diagnosis of cardiovascular diseases (CVDs), this study provides a fresh suggested model that uses Graph Convolutional Networks (GCNs) for the multi-label classification of phonocardiographic data. The complex temporal and spectral properties included in heartbeat sounds are often too complex for traditional machine learning frameworks to fully capture. Mel-Frequency Cepstral Coefficients (MFCC) and MEL-spectrograms, two sophisticated feature extraction techniques, work together in our suggested model to improve the representation of important audio aspects that are essential for cardiovascular diagnoses. Through the utilization of GCNs' intrinsic relational structure, the model enhances the propagation of superior information among associated nodes, which in turn improves the categorization of various cardiovascular conditions. Moreover, dynamic customization of node feature representations is made possible by the design, which enhances the resilience of real-world pulse recordings against noise and fluctuation. The results highlight the usefulness of the suggested model in clinical settings, opening the door for further research into hybrid modelling methods and the incorporation of advanced brain architectures with the goal of improving cardiovascular health assessment and intervention plans.
Downloads
Metrics
References
F. Li, Z. Zhang, L. Wang, and W. Liu, ‘Heart sound classification based on improved mel-frequency spectral coefficients and deep residual learning’, Front. Physiol., vol. 13, p. 1084420, 2022.
W. Chen, Q. Sun, X. Chen, G. Xie, H. Wu, and C. Xu, ‘Deep learning methods for heart sounds classification: A systematic review’, Entropy, vol. 23, no. 6, pp. 1–18, 2021, doi: 10.3390/e23060667.
T. M. A. Monisha Sharean and G. Johncy, ‘Deep learning models on Heart Disease Estimation - A review’, J. Artif. Intell. Capsul. Networks, vol. 4, no. 2, pp. 122–130, 2022, doi: 10.36548/jaicn.2022.2.004.
A. F. Quiceno-Manrique, J. I. Godino-Llorente, M. Blanco-Velasco, and G. Castellanos-Dominguez, ‘Selection of dynamic features based on time–frequency representations for heart murmur detection from phonocardiographic signals’, Ann. Biomed. Eng., vol. 38, pp. 118–137, 2010.
M. A. Faghy et al., ‘Cardiovascular disease prevention and management in the COVID-19 era and beyond: an international perspective’, Prog. Cardiovasc. Dis., vol. 76, pp. 102–111, 2023.
C. Liu et al., ‘Liu, C., Springer, D., Li, Q., Moody, B., Juan, R. A., Chorro, F. J., et al. (2016). An open access database for the evaluation of heart sound algorithms. Physiol. Meas. 37, 2181–2213. doi:10.1088/0967-3334/37/12/2181’, Physiol. Meas., vol. 37, no. 12, p. 2181, 2016.
D. R. Deepa, V. B. Sadu, C. G. Prashant, and D. A. Sivasamy, ‘Early prediction of cardiovascular disease using machine learning: Unveiling risk factors from health records’, AIP Adv., vol. 14, no. 3, 2024, doi: 10.1063/5.0191990.
A. Harimi et al., ‘Classification of heart sounds using chaogram transform and deep convolutional neural network transfer learning’, Sensors, vol. 22, no. 24, p. 9569, 2022.
I. Maglogiannis, E. Loukis, E. Zafiropoulos, and A. Stasis, ‘Support vectors machine-based identification of heart valve diseases using heart sounds’, Comput. Methods Programs Biomed., vol. 95, no. 1, pp. 47–61, 2009.
G. E. Hinton and R. R. Salakhutdinov, ‘Reducing the dimensionality of data with neural networks’, Science (80-. )., vol. 313, no. 5786, pp. 504–507, 2006.
N. Mei, H. Wang, Y. Zhang, F. Liu, X. Jiang, and S. Wei, ‘Classification of heart sounds based on quality assessment and wavelet scattering transform’, Comput. Biol. Med., vol. 137, p. 104814, 2021.
F. Li, Z. Zhang, L. Wang, and W. Liu, ‘Heart sound classification based on improved mel-frequency spectral coefficients and deep residual learning’, Front. Physiol., vol. 13, no. December, pp. 1–16, 2022, doi: 10.3389/fphys.2022.1084420.
H. Lin, K. Chen, Y. Xue, S. Zhong, L. Chen, and M. Ye, ‘Coronary heart disease prediction method fusing domain-adaptive transfer learning with graph convolutional networks (GCN)’, Sci. Rep., vol. 13, no. 1, pp. 1–14, 2023, doi: 10.1038/s41598-023-33124-z.
P. Hamet and J. Tremblay, ‘Artificial intelligence in medicine’, metabolism, vol. 69, pp. S36–S40, 2017.
K. W. Johnson et al., ‘Artificial intelligence in cardiology’, J. Am. Coll. Cardiol., vol. 71, no. 23, pp. 2668–2679, 2018.
T. Zhang, Y. Lin, W. He, F. Yuan, Y. Zeng, and S. Zhang, ‘GCN-GENE: a novel method for prediction of coronary heart disease-related genes’, Comput. Biol. Med., vol. 150, p. 105918, 2022.
G. Battineni, G. G. Sagaro, N. Chinatalapudi, and F. Amenta, ‘Applications of machine learning predictive models in the chronic disease diagnosis’, J. Pers. Med., vol. 10, no. 2, 2020, doi: 10.3390/jpm10020021.
J. Zhang, X. Hu, Z. Jiang, B. Song, W. Quan, and Z. Chen, ‘Predicting Disease-related RNA Associations based on Graph Convolutional Attention Network’, Proc. - 2019 IEEE Int. Conf. Bioinforma. Biomed. BIBM 2019, pp. 177–182, 2019, doi: 10.1109/BIBM47256.2019.8983191.
H. Li et al., ‘A fusion framework based on multi-domain features and deep learning features of phonocardiogram for coronary artery disease detection’, Comput. Biol. Med., vol. 120, p. 103733, 2020.
A. Castro, A. Moukadem, S. Schmidt, A. Dieterlen, and M. T. Coimbra, ‘Analysis of the electromechanical activity of the heart from synchronized ECG and PCG signals of subjects under stress’, in International Conference on Bio-inspired Systems and Signal Processing, SCITEPRESS, 2015, pp. 49–56.
H. Liang, S. Lukkarinen, and I. Hartimo, ‘Heart sound segmentation algorithm based on heart sound envelogram’, in Computers in Cardiology 1997, IEEE, 1997, pp. 105–108.
S. Choi and Z. Jiang, ‘Comparison of envelope extraction algorithms for cardiac sound signal segmentation’, Expert Syst. Appl., vol. 34, no. 2, pp. 1056–1069, 2008.
B. S. Emmanuel, ‘A review of signal processing techniques for heart sound analysis in clinical diagnosis’, J. Med. Eng. Technol., vol. 36, no. 6, pp. 303–307, 2012.
R. F. Ibarra, M. A. Alonso, S. Villarreal, and C. I. Nieblas, ‘A parametric model for heart sounds’, in 2015 49th Asilomar Conference on Signals, Systems and Computers, IEEE, 2015, pp. 765–769.
M. B. Er, ‘Heart sounds classification using convolutional neural network with 1D-local binary pattern and 1D-local ternary pattern features’, Appl. Acoust., vol. 180, p. 108152, 2021.
Z. Ren et al., ‘Deep attention-based neural networks for explainable heart sound classification’, Mach. Learn. with Appl., vol. 9, p. 100322, 2022.
K. Iqtidar, U. Qamar, S. Aziz, and M. U. Khan, ‘Phonocardiogram signal analysis for classification of Coronary Artery Diseases using MFCC and 1D adaptive local ternary patterns’, Comput. Biol. Med., vol. 138, p. 104926, 2021.
S. Lahmiri and S. Bekiros, ‘Complexity measures of high oscillations in phonocardiogram as biomarkers to distinguish between normal heart sound and pathological murmur’, Chaos, Solitons & Fractals, vol. 154, p. 111610, 2022.
T. N. Kipf and M. Welling, ‘Semi-supervised classification with graph convolutional networks’, arXiv Prepr. arXiv1609.02907, 2016.
A. L. Maas, A. Y. Hannun, and A. Y. Ng, ‘Rectifier nonlinearities improve neural network acoustic models’, in Proc. icml, Atlanta, GA, 2013, p. 3.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
