Chronic Kidney Disease (CKD) - Diagnosis using Machine Learning Methodology - Classifications

Aug 5, 2026

Early diagnosis of kidney disease and pre-kidney conditions is essential to help patients manage progression and potentially avoid or delay severe outcomes that reduce quality of life. Chronic Kidney Disease (CKD) can lead to fluid retention, high blood pressure, and swelling in legs and arms. This study develops a machine learning model for CKD diagnosis using preprocessing that handles missing values via mean, deletion, and median approaches. SVM and KNN are evaluated with accuracy, F1-score, recall, and precision, and results show performance improvements depending on the imputation strategy.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages8

Reading Time20 min

AccessFree to download

Abstract

Introduction

Related Works

Research Article Chronic Kidney Disease (CKD)Diagnosis using Machine Learning Methodology Classifications Ahmed Sami Jaddoa Business Informatics College University of Information Technology and Communications Baghdad, Iraq [ahmed.sami@uoitc.edu.iq](ahmed.sami@uoitc.edu.iq) A R T I C L E I N F O Article History Received: 01/07/2024 Accepted: 05/08/2024 Published:04/10/2024 This is an open-access article under the CC BY 4.0 license: [http://creativecommo](http://creativecommo)[ns.org/licenses/by/4.0/](ns.org/licenses/by/4.0/) ABSTRACT Early diagnosis of kidney as well as pre-kidney disease is crucial for patients because it allows them to take control of their condition and could potentially avoid or delay more significant consequences that could lower their quality of life. The chance of developing a major disease might be decreased with its assistance. Almost every part of the body could be impacted by chronic kidney disease (CKD) . Fluid retention in the lungs, high blood pressure, and swelling of the legs and arms are all potential side effects. This study proposes a model that makes use of machine learning (ML) algorithms for diagnosing kidney disease. The preprocessing dataset, which contains missing values and is preprocessed with the use of mean, delete, and median approaches before data scaling, is the foundation of the suggested model. To achieve the highest classification accuracy, the preprocessing stage receives the results of missing values. Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) are the two classification algorithms used to classify whether kidney disease is present or absent. Classify the dataset into testing and training (40% and 60%, respectively) . The accuracy, F1-score, recall, and precision have been utilized for evaluating the suggested model. The kidney disease data-set has been used to test the outcomes ofthe suggested model. Without preprocessing any missing values in the dataset, the algorithms SVM and K-NN obtained maximum accuracy (95% and %89) . Through deleting missing values from the dataset, the algorithms SVM and K-NN obtained maximum accuracy (%96 and %93) . K-NN and SVM algorithms reached a maximum accuracy of %98 when using a mean technique; when using a median method, such algorithms attained an accuracy ranging from %95 to %98 . Keywords: CKD, KNN, SVM, Mean, Median, Preprocessing, Machine Learning; 1. INTRODUCTION CKD can be defined as a disability of kidneys to perform their normal function of blood filtering as well as other functions. The disease has been considered as a severe form of kidney failure in which the kidneys are incapable of filtering blood, resulting in a significant buildup of fluid in the body. This causes the body's levels of potassium and calcium salts to rise dangerously. The presence of elevated concentrations of such salts causes the body to experience a number of additional ailments [1]. Permanent dialysis or kidney transplants are frequently required for CKD. High risk of CKD is associated with a family history of kidney disease. Nearly one in three patients who are diagnosed with diabetes also have CKD, according to the available literature. Evidence from the literature suggests that CKD treatment and diagnosis early on could lead to the enhancement of a patient's quality of life. Prediction algorithms in ML could be cleverly applied to predict the development of CKD and offer an early treatment strategy [1] . A computer software that performs a computation and inferring of task-related information and determines properties of matching pattern is referred to as ML. This technology may be one of the potential tools for the diagnosis of CKD because it could produce accurate and affordable disease diagnoses. With information technology advancement, it has taken on a new form as a medical instrument, and the rapid growth of electronic health records expanded its potential applications. ML has previously been appli

FAQs

Why is early CKD diagnosis important?

Early diagnosis helps patients control their condition and can reduce the likelihood of developing major diseases, improving quality of life.

Which machine learning algorithms are used for CKD diagnosis?

The study uses Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) to classify whether kidney disease is present or absent.

How does the paper handle missing values in the dataset?

It preprocesses missing values using mean imputation, deletion, and median approaches before data scaling, and compares classification performance across these strategies.

Aug 5, 2026

Upload by Theodore