Home > Published Issues > 2023 > Volume 14, No. 2, 2023 >
JAIT 2023 Vol.14(2): 384-391
doi: 10.12720/jait.14.2.384-391

Chronic Kidney Disease Prediction Using Machine Learning

Chamandeep Kaur 1, M. Sunil Kumar 2, Afsana Anjum 1, M. B. Binda 3, Maheswara Reddy Mallu 4, and Mohammed Saleh Al Ansari 5,*
1. Department of Computer Science & Information Technology, Jazan University, Jizan, Saudi Arabia; Email: cgourmeat@jazanu.edu.sa (C.K.), aisrar@jazanu.edu.sa (A.A.)
2. School of Computing, Department of CSE, Mohan Babu University & Sree Vidyanikethan Engineering College Tirupati, AP, India; Email: sunilmalchi1@gmail.com (M.S.K.)
3. Traffic Signal Division, Keltron Communication Complex, Thiruvananthapuram, Kerala, India
4. Department of Biotechnology, Koneru Lakshmaiah Education Foundation, Vaddeswaram-522302, Guntur, Andhra Pradesh, India; Email: mahesh_bt@kluniversity.in (M.R.M.)
5. Department of Chemical Engineering, University of Bahrain, Bahrain
*Correspondence: malansari.uob@gmail.com (M.S.A.A.)

Manuscript received September 19, 2022; revised October 12, 2022; accepted December 21, 2022; published April 26, 2023.

Abstract—The occurrence of Chronic Renal Disease (CRD), is also referred to as Chronic Kidney Disease (CKD). It depicts a medical condition that harms the kidneys and has an impact on a person’s overall health. End-stage renal disease and the patient’s eventual mortality can result from improper disease diagnosis and treatment. In the field of medical science, Machine Learning (ML) techniques have become a valuable tool and play a significant role in disease prediction. The development and validation of a predictive model for the prognosis of chronic renal disease is the aim of the proposed study. A dataset on chronic kidney disease with 400 samples was taken from the UCI Machine Learning Repository. Three machine learning classifiers—Logistic Regression (LR), Decision Tree (DT), and Support Vector Machine (SVM)—were used for analysis, and the bagging ensemble method was used to enhance the model’s performance. The machine learning classifiers were trained using the clusters of the dataset for chronic renal disease. The Kidney Disease Collection is then compiled using non-linear features and categories. The decision tree produces the best results, with an accuracy of 95%. Finally, we achieve the greatest accuracy of 97% by using the bagging ensemble approach.
 
Keywords—chronic renal disease, classification algorithms, random forest classifier, machine learning

Cite: Chamandeep Kaur, M. Sunil Kumar, Afsana Anjum, M. B. Binda, Maheswara Reddy Mallu, and Mohammed Saleh Al Ansari, "Chronic Kidney Disease Prediction Using Machine Learning," Journal of Advances in Information Technology, Vol. 14, No. 2, pp. 384-391, 2023.

Copyright © 2023 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.