Prediction of Chronic Kidney Disease Using C4.5 Algorithm
M. Praveena1, N. Bhavana2
1M. Praveena, Assistant Professor, Department of Computer Science and Engineering, Koneru Lakshmaiah Educational Foundation, Vaddeswaram (Andhra Pradesh), India.
2N. Bhavana, Student, Department of Computer Science and Engineering, Koneru Lakshmaiah Educational Foundation, Vaddeswaram (Andhra Pradesh), India.
Manuscript received on 23 April 2019 | Revised Manuscript received on 05 May 2019 | Manuscript Published on 17 May 2019 | PP: 166-168 | Volume-7 Issue-6S4 April 2019 | Retrieval Number: F10320476S419/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Chronic Kidney Disease (CKD) is a major medical problem and can be cured if treated it in the early stages. Usually, people are not aware that medical tests we take for different purposes could contain valuable information concerning kidney diseases. Consequently, attributes of various medical tests are investigated to distinguish which attributes may contain helpful information about the disease. The objective of this paper is to make use of such attributes. The information says that it helps us to measure the severity of the problem, the predicted survival of the patient after the illness, the pattern of the disease and work for curing the disease. Hence we considered a data-set with different attributes that can be found in general medical tests, machine learning is applied by developing a decision tree using the C4.5 algorithm and predicted whether the person is normal or suffering from kidney problem. This proposed model will be developed using Java language and is implemented in Net-Beans platform.
Keywords: Chronic Kidney Disease (CKD), Decision Tree, C4.5 Algorithm, Machine Learning.
Scope of the Article: Regression and Prediction