IRJET - Machine Learning for Diagnosis of Diabetes

This document describes a study that uses machine learning models to predict whether a person has diabetes based on patient data. The researchers created several classification models using algorithms like logistic regression and support vector machines on a diabetes dataset. The models with the highest accuracy at predicting diabetes were random forest and gradient boosting. An Android app was also developed to input patient data, run the predictions from the trained models, and display the results to help diagnose diabetes. The goal is to help reduce diabetes rates and healthcare costs by improving diagnosis.