Machine Learning Framework for Chronic Kidney Disease Prediction

Article

No Article found

CROSSREF PEER REVIEWED GOOGLE SCHOLAR PLAGIARISM CHECK

ISSN License

Machine Learning Framework for Chronic Kidney Disease Prediction

Author: Ms.Ponkohila.J , Assistant Professor, Department of Computer Technology and Data Science , Sri Krishna Arts and Science College

Published On: 2026-08-02

DOI: https://doi.org/10.70127/irjedt.vol.9.issue08.47

Download PDF Review Report Indexing this Article

Abstract

Chronic Kidney Disease (CKD) represents a significant global health threat, affecting approximately 753 million people as of 2016. Because symptoms are often non-specific or absent until the final stages, early detection is critical to preventing kidney failure and improving survival rates. This document outlines a proposed machine learning workflow designed to predict CKD status using clinical data.The system leverages Ant Colony Optimization (ACO) for feature selection and Support Vector Machine (SVM) for classification. By reducing the number of required clinical attributes from 24 down to the 12 most relevant features, the model achieves an overall accuracy of 96.7% . This framework addresses common challenges in clinical data analysis, such as missing values and redundant features, providing a high-accuracy tool for early-stage diagnosis and disease management.

Keywords

Article Information