Early Diagnosis and Prognosis of Chronic Kidney Disease Using Classification Methods

Authors

  • A. Abarna, G. Bhuvaneswari

DOI:

https://doi.org/10.17762/msea.v71i4.766

Abstract

Chronic kidney disease (CKD), a condition that affects people all over the world and has a high mortality rate, is a major cause of other ailments. Patients sometimes fail to notice the illness since there are no visible incidental symptoms in the early stages of CKD. Patients can seek beneficial treatment to slow the progression of CKD by being informed about it early. Due to their quick and accurate affirmation execution, AI models can successfully help clinical achieve this goal. In this evaluation, we suggest a methodology for diagnosing CKD called Logistic Relapse. We examine suggested calculations including NAVIE BAYES, DECISION TREE, KSTAR, LOGISITIC and SUPPORT VECTOR MACHINE to obtain the most notable precision. There are a huge number of lacking qualities in the AI store. Since patients may miss a few examinations for a variety of reasons, clinical conditions are where missing attributes are typically discovered. We suggested a fused model that uses perceptron to combine determined backslide and sporadic woodlands by separating the errors made by the established models. Therefore, we proposed that this line of reasoning would be appropriate to more perplexing clinical evidence for condition identification.

Downloads

Published

2022-09-09

How to Cite

A. Abarna, G. Bhuvaneswari. (2022). Early Diagnosis and Prognosis of Chronic Kidney Disease Using Classification Methods. Mathematical Statistician and Engineering Applications, 71(4), 2153–2163. https://doi.org/10.17762/msea.v71i4.766

Issue

Section

Articles