Open AccessDetecting Kidney Disease using Naïve Bayes and Decision Tree in Machine Learning
Author(s) -
Sakshi Kapoor*,
Rabina Verma,
S. N. Panda
Publication year - 2019
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.a4377.119119
Subject(s) - c4.5 algorithm , naive bayes classifier , decision tree , kidney disease , computer science , machine learning , feature selection , artificial intelligence , diabetes mellitus , disease , medicine , classifier (uml) , intensive care medicine , data mining , support vector machine , endocrinology
Chronic Kidney Disease (CKD) mostly influence patients suffered from difficulties due to diabetes or high blood pressure and make them unable to carry out their daily activities. In a survey , it has been revealed that one in 12 persons living in two biggest cities of India diagnosed of CKD features that put them at high risk for unfavourable outcomes. In this article, we have analyzed as well as anticipated chronic kidney disease by discovering the hidden pattern of the relationship using feature selection and Machine Learning classification approach like naive Bayes classifier and decision tree(J48). The dataset on which these approaches are applied is taken from UC Irvine repository. Based on certain feature, the approaches will predict whether a person is diagnosed with a CKD or Not CKD. While performing comparative analysis, it has been observed that J48 decision tree gives high accuracy rate in prediction. J48 classifier proves to be efficient and more effective in detecting kidney diseases.