DIABETES PREDICTION USING MACHINE LEARNING TECHNIQUES

Abstract

Diabetes is a disease that develops as a result of a high glucose
level in the bloodstream of a person. A person's diabetes
should not be disregarded; if left untreated, diabetes may lead
to serious health complications in the long run. Such as heart
disease, renal disease, high blood pressure, and so on it may
cause eye damage and can also have an impact on other
organs in the human body. Diabetes may be managed if it is
identified and treated early on. In order to accomplish this is
the objective during this project's effort; we will look at early
diabetes detection. In a human body or on a patient in order to
gets more precision Different Machine Learning Techniques
are being used. Machine gaining knowledge of methods by
constructing models using data gathered from patients, it is
possible to get better results for prediction. This is the case in
this effort that we will put to use Classification and ensemble
learning with machine learning Using statistical methods on a
dataset, diabetes may be predicted. Which of the following are
K-Nearest? KNN (Kindest Neighbour), Logistic Regression
(LR), and Decision Tree (DT), Support Vector Machine
(SVM), Gradient Boosting (GB), and Support Vector Machine
(SVM) The Forest of Chance (RF). Every model has a
different level of accuracy than the others. Whenever they are
contrasted with other models. The project work provides the
opportunity to the model's ability to forecast diabetes with high
accuracy or greater accuracy demonstrates that the model is
capable of doing so. As a result of our research, we have
discovered that when compared to other methods, Random
Forest produced greater accuracy. Techniques using machine
learning.