Prediction and Analysis of Diabetes Using Machine Learning

This study focuses on diabetes prediction and analysis using machine learning techniques. Its goal is to develop accurate and reliable models for early detection and better understanding of diabetes. The Diabetes UCI Dataset, containing variables like gender, polyuria, and polydipsia, is used for model training and evaluation. Data preprocessing ensures feature normalization and consistency, while feature selection identifies the most relevant variables. Several classification algorithms, including the Random Tree algorithm, are tested using WEKA. Model performance is evaluated through metrics such as accuracy, precision, and recall. Results show that Random Tree, when combined with other algorithms, achieves high accuracy and robustness in classifying diabetic and non-diabetic individuals. The study highlights the effectiveness of machine learning in early diabetes detection and decision-making support for healthcare professionals. Overall, it demonstrates how computational approaches can enhance diabetes management, improve patient outcomes, and reduce the impact of this chronic disease.