Prediction of Chronic Kidney Disease using SVM and CNN
Article Sidebar
Main Article Content
Abstract
Chronic kidney disease is one of the deadliest diseases today and it is vital to have a good diagnosis as soon as possible. In medical treatment, machine learning has been reported to be effective. A doctor can diagnose the disease early by using machine learning classifier algorithms. This study investigated the chronic disease prognosis of this concept. Disease data was taken from the University of California, Irvine. Other measurement algorithms used in this study include C5.0, Chi-square automatic interaction detector, line extraction, SVM line with L1 and L2 flap, and neural network random tree. The database was also submitted to a feature selection program that merited the database. Scores are computer generated for each category segment using the following methods: Full Version, (ii) Link-Based Feature Selection, (iii) Folder Feature Selection, (iv) Minimal Collapse and Selected Optional Retrospective Features, (v) integrated small oversampling method with very small reduction features and selected bias on the selected operator, and (vi) how to do multiple samples combined with full functions. In the full multi-sample processing process, the findings show that L2-loaded LSVM has a very high accuracy of 96.86 percent. The graph shows the results of different methods, as well as precision, precision, recall, F-score, area under the curve, and GINI coefficient. The minimum absolute reduction and selection regression operation selected features using the synthetic minority oversampling approach produced the best results after using the synthetic minority oversampling method with full features. The support vector machine achieved a high accuracy of 96.46 percent in the process of making very large samples with very small turndowns and selected operator features. Machine learning methods used with convolutional neural networks and SVM classifier models on the same database, with 96.7 percent of high-definition support machine models and networks are used.
Article Details
References
G. R. Vasquez-Morales, S. M. Martinez-Monterrubio, P. Moreno-Gier, and J. A. Recio- Garcia, Interpretive Predictability of Renal Disease in Colombian People Using Networks of Emotional and Cognitive Networks.
Z. Chen, X. Zhang, and Z. Zhang. "Clinical risk assessment of patients with chronic kidney disease by using clinical data and multivariate models. Int. Urol Nephrol., vol. 48, no. 12, pp. 2069-2075, Jun 2016.
Y Amirgaliyev, S. Shamiluulu, and A. Serek, "Analysis of chronic kidney disease dataset by applying machine learning methods," in Proc. IEEE 12th Int. Conf. Appl Inf. Commun. Technol (AFCT), Oct.2018, pp. 1-4.
L. Kilvia De Almeida, L. Lessa, A. Peixoto, R. Gomes, and J Celestino, “Kidney failure detection using machine learning techniques," in Poe St Int. Workshop ADVANCES ICT Infrastructures Services, 2020, pp. 1-8.
W. Gunarathne, K. D. M Perera, and K. A. DC P Kahandawaarachchi. Performance evaluation on machine learning classification techniques for disease classification and forecasting through data analytics for chronic kidney disease (CKD)," in Proc. IEEE 17th Int. Conf. Blond Bioeng (BIBE), Oct. 2017, pp. 291-296.
H. Polat, H. D. Mehr, and A. Cetin, "Huseyin polat & homay danari mehrl & aydin cetin. J. Med. Syst., vol. 41, no. 4, pp. 1-11, Apr 2017, doi: 10.1007/s10916-017-0703-x.
M. Almasoud and T. E. Ward, "Detection of chronic kidney disease using machine learning algorithms with least number of predictors. Int. J. Adv. Comput. Sci. Appl., vol. 10, no. 8, pp. 89- 95, 2019.
S. Vijayaranil and S. Dhayanand. "Kidney disease prediction using SVM and ANN algorithms, Int. J. Comput. Bus. Res., vol. 6, no. 2, pp. 1-12, Mar. 2015.
F. Ma, T Sun, L. Liu, and H. Jing. Detection and diagnosis of chronic kidney disease using deep learning-based heterogeneous modified artifi cial neural network, Future Gener. Comput. Syst., vol. 111. pp. 17-26. Oct. 2020.
A. U Haq, I. P. Li, J. Khan, M. H. Memon, S. Nazir, S. Ahmad, G. A. Khan, and A. Aliss. Intelligent machine learning approach for effective recognition of diabetes in E-healthcare using clinical data," Sensors, vol. 20, no. 9. p. 2649, May 2020.
UH. Amin, J. Li, Z. Ali, M. H. Memon, M. Abbas, and S. Nazir, Recognition of the Parkinson's disease using a hybrid feature selection. approach, J. Iell. Fuzzy Syst, Jul. 2020.
Dodge, Samuel, and Lina Karam. "Understanding how image quality affects deep neural networks.", Quality Multimedia Experience (QoMEX), Eighth 2016 International Conference for TEEE, 2016.
Dejean-Servieres. Mathieu, et al. "Study of the Impact of Standard Image Compression Techniques on Performance of Image Classification with a Convolutional Neural Network, Diss. INSA Rennes Univ Rennes; IETR; Institut Pascal, 2017.
A. Krizhevsky, et al., "ImageNet classification with deep convolutional neural networks," in Advances in neural information processing systems, 2012, pp. 1097-1105.
D. H. Hubel and T. N. Wiesel, "Receptive fields, binocular interaction and functional architecture in the cat's visual cortex," The Journal of physiology, vol. 160, pp. 106-154, 1962.
K. Fukushima and S. Miyake, "Neocognitron: A self-organizing neural network model for a mechanism of visual pattern recognition," in Competition and cooperation in neural nets, ed: Springer, 1982, pp. 267-285.
Y. LeCun, et al., "Handwritten digit recognition with a back propagation network," in Advances in neural information processing systems, 1990, pp. 396-404.
Y. LeCun, et al., "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, pp. 2278-2324, 1998.
R. Hecht-Nielsen, "Theory of the backpropagation neural network," in Neural networks for perception, ed: Elsevier, 1992, pp. 65-93.