Diabetes Prediction in Healthcare Utilizing Machine Learning Algorithms

Diabetes mellitus is among the most dangerous conditions that many people suffer from. Age, obesity, poor food, heredity, high blood pressure, and inactivity are some of the variables that might lead to diabetes mellitus. Though there are additional forms of diabetes, such as gestational diabetes, which appears during pregnancy, the two most common types are type 1 and type 2. In data science, machine learning is a relatively new field of study that looks at how machines pick up knowledge via experience. The goal of this work is to build a system that can more accurately forecast a patient's risk of developing diabetes in their early years by utilizing a combination of research data and machine learning techniques. Interpretable findings using logistic regression (LR) show how various risk variables affect the chance of acquiring diabetes. The most crucial characteristics for diabetes prediction may be automatically discovered by neural networks (NN) from unprocessed input data, eliminating the requirement for human feature selection. While compared to previous models, both the logistic regression and the neural network in this study provide a respectable accuracy score following a 10-fold classification.