Big Data and Machine Learning Based Early Chronic Kidney Disease Prediction

Authors

  • Asra Fatima Assistant Professor, Department of Computer Science and Engineering Faculty of Engineering and Technology, KBN University, Gulbarga, Karnataka, India
  • Shireen Fatima Assistant Professor, Department of Computer Science and Engineering Faculty of Engineering and Technology, KBN University, Gulbarga, Karnataka, India
  • Ayesha Kiran Assistant Professor, Department of Computer Science and Engineering Faculty of Engineering and Technology, KBN University, Gulbarga, Karnataka, India

DOI:

https://doi.org/10.61808/jsrt88

Keywords:

Random forest, Decision tree, XGBoot, KNN

Abstract

A chronic kidney disease, sometimes called a chronic renal disease, is characterized by a gradual decline in kidney purpose or abnormal kidney purpose which continues for months or even years. Patients with a domestic past of chronic kidney disease (CKD), high BP, or other kidney-related conditions are often the first to have chronic kidney disease (CKD) identified during screenings. Consequently, effective illness prevention and therapy rely on early prediction. Methods from the field of machine learning, including XGBoost, KNN, Decision Tree, and Random Forest, are being considered for use in this CKD project. The final product uses the fewest characteristics possible to determine whether the patient has chronic kidney disease (CKD).

Published

06-03-2024

How to Cite

Asra Fatima, Shireen Fatima, & Ayesha Kiran. (2024). Big Data and Machine Learning Based Early Chronic Kidney Disease Prediction. Journal of Scientific Research and Technology, 2(3), 22–28. https://doi.org/10.61808/jsrt88

Issue

Section

Articles