Synergizing CNN, DBN-Net, Transfer Learning, and DES: An Efficient Hybrid Framework Over Cardiovascular Disease Prediction
Keywords:
Precision medicine, Cardio-vascular prediction (CVD), DRA mechanism, Dense connectivity, Residual learning, Attention mechanisms, Ensemble, Accuracy, Computing TimeAbstract
Cardiovascular diseases (CVDs) continue to be a significant global health challenge, necessitating more accuracy and an early prediction to mitigate their impact. Cardiovascular disease (CVD) remains a global public health concern, accounting for nearly 18 million deaths annually. Timely diagnosis and intervention are paramount for improving CVD outcomes. Machine learning (ML) has emerged as a powerful tool for CVD prediction, but existing ML models often struggle with accuracy and interpretability. This study proposes a novel hybrid framework that integrates convolutional neural networks (CNNs), deep belief networks (DBN-Nets), transfer learning, and dynamic ensemble selection (DES) for CVD prediction. The proposed framework initially leverages CNNs to extract high-level features from electrocardiogram (ECG) signals. Subsequently, DBN-Nets are employed to learn a hierarchical representation of the extracted features, enhancing the model's ability to capture complex patterns in the data. To further augment the model's performance, transfer learning is implemented by fine-tuning a pre-trained DBN-Net on the CVD prediction task. Finally, DES is utilized to select the most informative features, reducing the dimensionality of the data and improving the model's interpretability. Experimental results on a benchmark ECG dataset (PhysioNet ECG Database) demonstrate that the proposed hybrid framework outperforms state-of-the-art methods in terms of accuracy, sensitivity, specificity, and F1-score.This study contributes to the ongoing pursuit of precision medicine and proactive disease management, which enhances survival of many patients with advance prescription alerting.
Downloads
References
Nianhao Xiao, Zou Yuanchen et al, DRNN: Deep Residual Neural Network for Heart Disease Prediction, November 2020, Journal of Physics, DOI: 10.1088/1742-6596/1682/1/012065.
Chen, W.-F., Ou, H.-Y. et al, C.-T, Development of Novel Residual-Dense-Attention (RDA) U-Net Network Architecture for Hepatocellular Carcinoma Segmentation. Diagnostics 2022, 12, 1916, https://doi.org/10.3390/diagnostics12081916.
Madhumita Pal et al, Risk prediction of cardiovascular disease using machine learning classifiers, Open Med (Wars), 2022; 17(1): 1100–1113, doi: 10.1515/med-2022-0508.
Xin Qian,Yu Li et al, A Cardiovascular Disease Prediction Model Based on Routine Physical Examination Indicators Using Machine Learning Methods: A Cohort Study, Front. Cardiovasc. Med., 2022, Sec. Atherosclerosis and Vascular Medicine, Volume 9, https://doi.org/10.3389/ fcvm.2022.854287.
Yazdani, A., Varathan, K.D. et al, A novel approach for heart disease prediction using strength scores with significant predictors, BMC Med Inform Decis Mak 21, 194 (2021), https://doi.org/10.1186/s12911-021-01527-5.
Yang, L., Wu, H., Jin, X. et al., Study of cardiovascular disease prediction model based on random forest in eastern China. Sci Rep 10, 5245 (2020), https://doi.org/10.1038/s41598-020-62133-5.
Rajkumar Gangappa Nadakinamani, A. Reyana,et al, Clinical Data Analysis for Prediction of Cardiovascular Disease Using Machine Learning Techniques, Computational Intelligence and Neuroscience, vol. 2022, Article ID 2973324, 13 pages, 2022, https://doi.org/10.1155/2022/ 2973324.
S, Malathi et al., Prediction of cardiovascular disease using deep learning algorithms to prevent COVID 19, Taylor & Francis, 0952-813X, doi: 10.1080/0952813X.2021.1966842.
M. Swathy, K. Saruladha et al, A comparative study of classification and prediction of Cardio-Vascular Diseases (CVD) using Machine Learning and Deep Learning techniques, ICT Express,Volume 8, Issue 1,2022,Pages 109-116,ISSN 2405-9595, https://doi.org/ 10.1016/j.icte.2021.08.021.
Farshad Farzadfar et al, Cardiovascular disease risk prediction models: challenges and perspectives, September, 2019, DOI:https://doi.org/10.1016/S2214-109X(19)30365-1.
Bhatt, C.M.; Patel, P. et al, Effective Heart Disease Prediction Using Machine Learning Techniques. Algorithms 2023, 16, 88. https://doi.org/10.3390/a16020088.
Zheming Tong, Xin Chen et al, Dense Residual LSTM-Attention Network for Boiler Steam Temperature Prediction with Uncertainty Analysis, ACS Omega 2022 7 (13), 11422-11429, DOI: 10.1021/acsomega.2c00615.
Tao, H.; Guo, W. et al, RDASNet: Image Denoising via a Residual Dense Attention Similarity Network. Sensors 2023, 23, 1486, https://doi.org/10.3390/s23031486.
Soham Chattopadhyay, Arijit Dey et al, DRDA-Net: Dense residual dual-shuffle attention network for breast cancer classification using histopathological images, Computers in Biology and Medicine, Volume 145,2022, ISSN 0010-4825,https://doi.org/10.1016/j.compbiomed.2022.105437.
Ding Qin, Xiaodong Gu et al, Single-image super-resolution with multilevel residual attention network, October 2020, Neural Computing and Applications 32(19), DOI: 10.1007/s00521-020-04896-6.
Arooj, S., Rehman, S.u et al, A Deep Convolutional Neural Network for the Early Detection of Heart Disease, Biomedicines 2022, 10, 2796, https://doi.org/10.3390/ biomedicines10112796.
Dhaka, V.S., Meena, S.V. et al., A Survey of Deep Convolutional Neural Networks Applied for Prediction of Plant Leaf Diseases, Sensors 2021, 21, 4749, https://doi.org/10.3390/s21144749.
Peng Lu, Saidi Guo et al, on Improved Depth Belief Network-Based Prediction of Cardiovascular Diseases, Journal of Healthcare Engineering, vol. 2018, Article ID 8954878, 9 pages, 2018. https://doi.org/10.1155/ 2018/8954878.
Rohit Bharti, Aditya Khamparia et al, Prediction of Heart Disease Using a Combination of Machine Learning and Deep Learning, Computational Intelligence and Neuroscience, vol. 2021, Article ID 8387680, 11 pages, 2021, https://doi.org/ 10.1155/2021/8387680.
Wang, Y.-C.; Wang, C.-C. et al, Identification of a High-Risk Group of New-Onset Cardiovascular Disease in Occupational Drivers by Analyzing Heart Rate Variability, Int. J. Environ. Res. Public Health 2021, 18, 11486, https://doi.org/ 10.3390/ijerph182111486.
Elena Di Bernardino, Clémentine Prieur et al, Estimation of Multivariate Conditional Tail Expectation using Kendall's Process, October 2014, Journal of Nonparametric Statistics, DOI: 10.1080/10485252.2014.889137.
The Multi-Ethnic Study of Atherosclerosis (MESA), https://www.mesa-nhlbi.org/MESA _508TextOnly.htm.
Hrushikesava Raju et al (2022), An IoT Vision for Dietary Monitoring System and for Health Recommendations. In: Ranganathan, G., Fernando, X., Shi, F. (eds) Inventive Communication and Computational Technologies. Lecture Notes in Networks and Systems, vol 311. Springer, https://doi.org/ 10.1007/ 978-981-16-5529-6_65
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
