This project aims to predict the likelihood of diabetes in individuals based on various health-related features. It contains machine learning algorithm to analyze a dataset of features such as pregnancies, glucose levels, blood pressure, skin thickness, insulin levels, BMI, diabetes pedigree function, age and outcome.
Project includes the simple implementation of machine learning models for finding the one with the best accuracy. It was observed that the Decision Tree Classifier shown the highest accuracy (75%) among the implemented models.
Dataset source: https://www.kaggle.com/datasets/akshaydattatraykhare/diabetes-dataset/data