Open AccessImplementing Classification Algorithms for Predicting Chronic Diabetes Diseases
Author(s) -
M. Kavitha,
S. Subbaiah
Publication year - 2019
Publication title -
international journal of engineering and advanced technology
Language(s) - English
Resource type - Journals
ISSN - 2249-8958
DOI - 10.35940/ijeat.f1328.0986s319
Subject(s) - naive bayes classifier , decision tree , logistic regression , machine learning , diabetes mellitus , artificial intelligence , computer science , algorithm , disease , decision tree learning , c4.5 algorithm , statistical classification , random forest , classifier (uml) , medicine , support vector machine , endocrinology
Now a day Chronic Diabetes Disease is increasing due to many reasons like changes in life style, food habit. It causes an increase in blood sugar levels. If Diabetes Disease remains untreated or unidentified, many different types of complications may be occurred. The doctors have the problem to identify these kinds of diseases easily. The machine learning algorithms helps the doctor to solve these types of problems. In this paper, we implemented three algorithms namely logistic regression, Naive Bayes and Decision tree algorithms to predict diabetes at an early stage. Experiments are performed on Pima Indians Diabetes Dataset, which is from UCI machine learning repository. The performance of all the three algorithms is evaluated using measures on Accuracy. Results obtained showed logistic regression displays 75.3%, Decision tree displays 77.9% and Naive Bayes classifier displays the accuracy value is 76.6%.