PROJECT TITLE :

A Linear Model Based on Principal Component Analysis for Disease Prediction 

ABSTRACT:

In the medical field, a variety of classification methods are used to predict various diseases, such as diabetes, tuberculosis, and so on. To determine if a patient has diabetes, doctors will look at their blood sugar levels, blood pressure, BMI, skin thickness, and other factors.

Diabetes has been classified using a variety of classification methods. The primary goal of this study is to develop a statistical model for diabetes data and improve classification accuracy.

Principal component analysis is used to project diabetes data into a new space, and then linear regression is used to model the newly formed attributes. This method has an 82.1% accuracy rate for predicting diabetes, which has improved over other classification methods currently in use.