Journal of RNA and Genomics

Reach Us +44 1250400002

Research Article - Journal of RNA and Genomics (2021) Volume 16, Issue 7

Prediction of diabetes using machine learning techniques

Diabetes is a disease caused due to the increased level of blood glucose. Current practice in hospitals is to collect the required information for diabetes diagnosis through various tests, and appropriate treatment is provided based on the diagnosis. In the existing method, the classification and prediction accuracy is not so high. Using big data analytics, one can study massive datasets and find hidden information, hidden patterns to discover knowledge from the data and predict outcomes accordingly. Several machine learning techniques are used to perform predictive analytics over big data in various fields. This project aims to make an early prediction of Diabetes in humans with higher accuracy through applying multiple machine learning techniques. Dataset of Pima Indian females of at least 21 years old with 768 data points and 9 attributes is taken from National institute of diabetes and digestive and kidney diseases. Various machine learning classification and ensemble techniques like K-nearest neighbors, decision tree, support vector classifier, logistic regression, decision tree, Gaussian naïve Bayes, random forest, gradient boosting are used on this dataset to predict diabetes, as these techniques provide a better result for prediction by constructing models from a dataset collected. The applied algorithms' performance and accuracy are compared with every model, which reveals the highly accurate model. The higher accuracy model shows that the algorithm is capable of predicting diabetes effectively, helping the doctors and practitioners.

Author(s): Padmapriya B, Abhishek S, Nenisi J, Prakalyaa T, Priyadharshini SM

Abstract Full Text PDF

Get the App

replica magic watches