DIABETES PREDICTION MODEL USING MACHINE LEARNING

ABSTRACT

Diabetes Mellitus is one of the most chronic diseases where a large number of people are affected in the world. Early detection of this disease is crucial in a person’s health. With the rapid development of machine learning, it has been applied to many aspects of health, especially in performing predictive analysis. The aim of this research is to predict if a patient has diabetes or not. In this project, four different algorithms such as K-Nearest Neighbour, which was used as the baseline model, Decision Tree classifier, Random Forest Classifier, Extreme Gradient Boost were used with a dataset sourced from Kaggle's repository of community-published data for machine learning projects. XGBoost performed best with an accuracy of 97% Essential Python libraries within the Jupyter Notebook in a Conda Environment, facilitated flexible model development. A Streamlit web interface enabled easy data predictions and feature selection. Its significance lies in providing a reliable tool for early diabetes prediction, improving patient outcomes. This approach combines Python, Streamlit's web interface, and XGBoost algorithm for effective early diabetes prediction, offering substantial benefits to healthcare efficiency and patient care