Diabetes Analysis Using Different Machine Algorithms

Abstract

Machine learning is the application of artificial intelligence which is used to train the machine so that it can analyse different parameters to predict output. In medical field the most important thing is the correct diagnosis of disease at early stage. Traditionally it was done by medical professionals. Nowadays, it can be done by using different machine learning algorithms. Diabetes is a very common disease that can remain lifelong if it is not diagnosed at early stage. At its worse stage people cannot control their blood levels through medicines and diet and they need to take dose of insulin daily which get more and more regular once it gets started. Diabetes can act as a complication in other different health conditions. However, one can cure it by seeking medical help at early stage when they have a chance of having diabetes. The purpose of this research is to find the accuracy of the result whether the person is likely to have diabetes or not based on different parameters. In this paper we are using Naive Bayes Algorithm, Random Forest, Logical Regression. The dataset used for the training is Pima Indian diabetic set from UCI repository of machine learning datasets.