Diabetic Prediction using ML Techniques

Abstract

In today's world, diabetes is a huge problem. Diabetes can cause blood sugar levels to rise, which can contribute to strokes and heart attacks. One of the most rapidly spreading diseases is this one. After speaking with a doctor and receiving a diagnosis, patients are normally required to receive their reports. Because this procedure is time-consuming and costly, we were able to fix the problem utilizing machine learning techniques. In medical organizations, many machine learning applications are both exciting and important. Machine learning is being more widely used in the medical field. Our study aims to create a system that can better predict a patient's diabetic risk level. The medical data set is put to many different uses. in order to develop an artificial intelligence model for disease prediction The National Institute of Diabetes and Digestive and Kidney Diseases provided the data. Among the items on the list are blood pressure, age, insulin level, BMI, and glucose. Models are created using classification methods such as Ada Boost, Gradient Boost, XG Boost, and Cat Boost. The outcomes reveal that the processes are extremely precise. According to the findings, the prediction made with the use the prediction utilizing the Gradient Boosting model had the highest accuracy, according to the findings. Our investigation covers a wide range of machine learning topics as well as the numerous types of prediction models available. We go over the different sorts of models that can be used to create predictions, as well as the characteristics of machine learning.