Machine Learning Approach for Diabetes Prediction

One of the most deadly diseases, diabetes mellitus, affects many people. Diabetes mellitus can be brought on by many different reasons, including age, obesity, inactivity, genetics, a poor diet, high blood pressure, and others. Diabetes raises one's risk of contracting diseases, such as heart disease, kidney disease, stroke, visual issues, nerve damage. Hospitals presently use a variety of tests to gather the information required to diagnose diabetes, and depending on those results, the appropriate therapy is subsequently administered. Because these algorithms are exact and essential in the medical industry, they were utilised to predict the risk of type 2 diabetes. Once the model has been successfully trained, individuals can evaluate their own risk of developing diabetes. This work aims to create a system that can accurately detect early diabetes in 1a patients by combining the results of various machine learning algorithms. Using three different supervised machine learning methods—decision trees, random forests, and support vector machines—this work aims to predict diabetes. Offering a trustworthy mechanism for early diabetes detection is another objective of this research.