Comparative analysis of prediction algorithms for diabetes

Abstract

Machine learning is a widely growing field which helps in better learning from data and its analysis without any human intervention. It is being popularly used in the field of healthcare for analyzing and detecting serious and complex conditions. Diabetes is one such condition that heavily affects the entire system. In this paper, application of intelligent machine learning algorithms like logistic regression, naïve Bayes, support vector machine, decision tree, k-nearest neighbors, neural network, and random decision forest are used along with feature extraction. The accuracy of each algorithm, with and without feature extraction, leads to a comparative study of these predictive models. Therefore, a list of algorithms that works better with feature extraction and another that works better without it is obtained. These results can be used further for better prediction and diagnosis of diabetes.