An Optimized Cluster Convolution based Hybrid Hierarchical Deep Learner for Chronic Kidney Disease (CKD)

An Optimized Cluster Convolution based Hybrid Hierarchical Deep Learner for Chronic Kidney Disease (CKD)
  IJETT-book-cover           
  
© 2022 by IJETT Journal
Volume-70 Issue-11
Year of Publication : 2022
Authors : P. Usha, N. Kavitha
DOI : 10.14445/22315381/IJETT-V70I11P216

How to Cite?

P. Usha, N. Kavitha, "An Optimized Cluster Convolution based Hybrid Hierarchical Deep Learner for Chronic Kidney Disease (CKD)," International Journal of Engineering Trends and Technology, vol. 70, no. 11, pp. 154-162, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I11P216

Abstract
Chronic Kidney Disease (CKD) remains a universal health issue. Learning the attributes relevant to CKD patients might help improve the early prediction of CKD. However, the outliers in the CKD database may affect the prediction accuracy. To solve this issue, a Moth Flame (MF)-based DBSCAN with Pearson Correlation (MFDBSCAN-PC) algorithm was suggested that adjusts the DBSCAN variables during clustering of the CKD-related attributes and creates the cleansed database without outliers. Also, various machine learning classifiers were performed for CKD prediction. But, the complex and implicit temporal relationships between local and global attributes were not learned, influencing the learning of the timeseries CKD database. Therefore, this article proposes a Deep Clustering-based outlier removal and Convolutional Neural network with a Hierarchical Bi-directional Long Short-Term Memory (DC-CNN-HBLSTM) model to process the time-series database for CKD prediction. Primarily, the CKD information-rich dataset is pre-processed using data imputation to fill up any blanks in the rows. Then, MF optimization performs to select the optimal DBSCAN variables and attributes simultaneously. Based on the best variables, the DBSCAN is employed as a new clustering layer in the CNN structure to cluster the data points and remove the outliers from the database, resulting in a newly cleaned database. After that, the HBLSTM classifier is trained by learning the temporal correlation between the local and global attributes to create a trained model. Further, the trained classification model is used to classify the test instances into healthy and CKD patients. Finally, the experimental results realize the DC-CNN-HBLSTM model achieves 96.21% accuracy compared to the SVM, recursive ANN, and ELM classifiers, which achieved 88.69%, 90.57%, and 92.9% accuracy for the CKD database.

Keywords
Attribute selection, Chronic kidney disease, Clustering, CNN, DBSCAN, Hierarchical bidirectional LSTM, Moth flame optimization, Outliers removal.

Reference
[1] K. J. Foreman, N. Marquez, A. Dolgert, K. Fukutaki, N. Fullman, M. McGaughey, and C. J. Murray, "Forecasting Life Expectancy, Years of Life Lost, and All-Cause and Cause-Specific Mortality for 250 Causes of Death: Reference and Alternative Scenarios for 2016–40 for 195 Countries And Territories," The Lancet, vol. 392, no. 10159, pp. 2052-2090, 2018. Crossref, https://doi.org/10.1016/S0140-6736(18)31694-5.
[2] R. Vanholder, L. Annemans, A. K. Bello, B. Bikbov, D. Gallego, R. T. Gansevoort, and F. Wieringa, "Fighting the Unbearable Lightness of Neglecting Kidney Health: The Decade of the Kidney," Clinical Kidney Journal, vol. 14, no. 7, pp. 1719-1730, 2021. Crossref, https://doi.org/10.1093/ckj/sfab070
[3] C. S. D. Moraes Júnior, N. M. D. S. Fernandes, and F. A. B. Colugnati, "Multidisciplinary Treatment for Patients with Chronic Kidney Disease in Pre-Dialysis Minimizes Costs: A Four-Year Retrospective Cohort Analysis," Brazilian Journal of Nephrology, vol. 43, pp. 330-339, 2021. Crossref, https://doi.org/10.1590/2175-8239-JBN-2020-0226.
[4] P. Suriyong, C. Ruengorn, C. Shayakul, P. Anantachoti, and P. Kanjanarat, “Prevalence of chronic kidney disease stages 3–5 in low-and middle-income countries in Asia: a systematic review and meta-analysis,” PloS One, vol. 17, no. 2, pp. 1-18, 2022. Crossref, https://doi.org/10.1371/journal.pone.0264393
[5] S. A. Amshi, A. B. Bababe, M. Saquib, and A. Adamu, A. "Chronic Kidney Disease Associated with Consumption of Vegetables Cultivated on Contaminated Soil in Gashua, Yobe State–Nigeria," SSRG International Journal of Pharmacy and Biomedical Engineering, vol. 7, no. 1, pp. 1-5, 2020. Crossref, https://doi.org/10.14445/23942576/IJPBE-V7I1P101
[6] M. Evans, R. D. Lewis, A. R. Morgan, M. B. Whyte, W. Hanif, S. C. Bain, and W. D. Strain, "A Narrative Review of Chronic Kidney Disease in Clinical Practice: Current Challenges and Future Perspectives," Advances in Therapy, vol. 39, no. 1, pp. 33-43, 2022.
[7] A. C. Simoes e Silva, A. S. Miranda, N. P. Rocha, and A. L. Teixeira, "Neuropsychiatric Disorders in Chronic Kidney Disease," Frontiers in Pharmacol, vol. 10, pp. 1-11, 2019. Crossref, https://doi.org/10.3389/fphar.2019.00932.
[8] C. J. Sperati, S. Soman, V. Agrawal, Y. Liu, K. Abdel-Kader, C. J. Diamantidis, M.M. Estrella, K. Cavanaugh, L. Plantinga, J. Schell, J. Simon, J.A. Vassalotti, M.J. Choi, B.G. Jaar and R.C. Greer, "Primary Care Physicians' Perceptions of Barriers and Facilitators to Management of Chronic Kidney Disease: A Mixed Methods Study," PloS One, vol. 14, no. 8, pp. 1-19, 2019. Crossref, https://doi.org/10.1371/journal.pone.0221325
[9] S. Shanmitha, N. Rathina Moorthy, and S. Suruthi, "Cancer Detection Technique in Data Mining," SSRG International Journal of Computer Science and Engineering, Special Issue ICETSST, pp. 40-42, 2018
[10] E. H. A. Rady, and A. S. Anwar, "Prediction of Kidney Disease Stages Using Data Mining Algorithms," Informatics in Medicine Unlocked, vol. 15, pp. 1-7, 2019. Crossref, https://doi.org/10.1016/j.imu.2019.100178
[11] H. S. Shad, Z. Jamal, S. M. Ahmed, S. Momen, and N. Mansoor, "Early Prediction of Chronic Kidney Disease using Data Mining Techniques," in Proceedings of Computational Methods in Systems and Software, Springer, Cham, pp. 947-957, 2021. Crossref, https://doi.org/10.1007/978-3-030-90321-3_79
[12] G. M. Ifraz, M. H. Rashid, T. Tazin, S. Bourouis, and M. M. Khan, "Comparative Analysis for Prediction of Kidney Disease Using Intelligent Machine Learning Methods," Computational and Mathematical Methods in Medicine, vol. 2021, pp. 1-10, 2021. Crossref, https://doi.org/10.1155/2021/6141470
[13] Y. Zhang, "DBSCAN Clustering Algorithm Based on Big Data is Applied in Network Information Security Detection," Security and Communication Networks, vol. 2022, pp. 1-8, 2022. Crossref, https://doi.org/10.1155/2022/9951609
[14] P. Usha, and N. Kavitha, "Optimized Uncertainty Handling Feature Selection using Moth Flame Based DBSCAN Clustering for Diabetic Related Chronic Kidney," Journal of Theoretical and Applied Information Technology, vol. 100, no. 10, pp. 3328-3336, 2022.
[15] I. A. Pasadana, D. Hartama, M. Zarlis, A. S. Sianipar, A. Munandar, S. Baeha, and A. R. M. Alam "Chronic Kidney Disease Prediction by using Different Decision Tree Techniques," in Journal of Physics: Conference Series, IOP Publishing, vol. 1255, no. 1. pp. 1-6, 2019. Crossref, https://doi.org/10.1088/1742-6596/1255/1/012024
[16] A. Ogunleye, and Q. G. Wang, "XGBoost Model for Chronic Kidney Disease Diagnosis," IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 17, no. 6, pp. 2131-2140, 2019. Crossref, https://doi.org/10.1109/TCBB.2019.2911071
[17] J. Qin, L. Chen, Y. Liu, C. Liu, C. Feng, and B. Chen, "A Machine Learning Methodology for Diagnosing Chronic Kidney Disease," IEEE Access, vol. 8, pp. 20991-21002, 2019. Crossref, https://doi.org/10.1109/ACCESS.2019.2963053
[18] A. Khamparia, G. Saini, B. Pandey, S. Tiwari, D. Gupta, and A. Khanna, "KDSAE: Chronic Kidney Disease Classification with Multimedia Data Learning Using Deep Stacked Autoencoder Network," Multimedia Tools Application, vol. 79, no. 47, pp. 35425-35440, 2020. Crossref, https://doi.org/10.1007/s11042-019-07839-z
[19] M. C. Shanker, M. Vadivel, "Hybrid Transfer Learning of Mammogram Images for Screening of Micro-Calcifications," SSRG International Journal of Electrical and Electronics Engineering, vol. 9, no. 8, pp. 40-47, 2022. Crossref, https://doi.org/10.14445/23488379/IJEEE-V9I8P105
[20] S. M. M. Elkholy, A. Rezk, and A. A. E. F. Saleh, "Early Prediction of Chronic Kidney Disease Using Deep Belief Network," IEEE Access, vol. 9, pp. 135542-135549, 2021. Crossref, https://doi.org/10.1109/ACCESS.2021.3114306
[21] H. Ilyas, S. Ali, M. Ponum, O. Hasan, M. T. Mahmood, M. Iftikhar, and M. H. Malik, "Chronic Kidney Disease Diagnosis using Decision Tree Algorithms," BMC Nephrology, vol. 22, no. 1, pp. 1-11, 2021. Crossref, https://doi.org/10.1186/s12882-021-02474-z
[22] H. Peng, H. Zhu, C. W. A. Ieong, T. Tao, T. Y. Tsai, and Z. Liu, "A Two‐Stage Neural Network Prediction of Chronic Kidney Disease," IET Systems Biology, vol. 15, no. 5, pp. 163-171, 2021. Crossref, https://doi.org/10.1049/syb2.12031
[23] M. Rashed-Al-Mahfuz, A. Haque, A. Azad, S. A. Alyami, J. M. Quinn, and M. A. Moni, "Clinically Applicable Machine Learning Approaches to Identify Attributes of Chronic Kidney Disease (CKD) for Use in Low-Cost Diagnostic Screening," IEEE Journal of Translational Engineering in Health and Medicine, vol. 9, pp. 1-11, 2021. Crossref, https://doi.org/ 10.1109/JTEHM.2021.3073629.
[24] L. Antony, S. Azam, E. Ignatious, R. Quadir, A. R. Beeravolu, M. Jonkman, and F. De Boer, "A Comprehensive Unsupervised Framework for Chronic Kidney Disease Prediction," IEEE Access, vol. 9, pp. 126481-126501, 2021. Crossref, https://doi.org/10.1109/ACCESS.2021.3109168.
[25] V. Singh, V. K. Asari, and R. Rajasekaran, "A Deep Neural Network for Early Detection and Prediction of Chronic Kidney Disease," Diagnostic, vol. 12, no.1, pp. 1-22, 2022. Crossref, https://doi.org/10.3390/diagnostics12010116
[26] F. Ma, T. Sun, L. Liu, and H. Jing, "Detection and Diagnosis of Chronic Kidney Disease Using Deep Learning-Based Heterogeneous Modified Artificial Neural Network," Future Generation Computer Systems, vol. 111, pp. 17-26, 2020. Crossref, https://doi.org/10.1016/j.future.2020.04.036