Development of Diabetes Diagnosis Tool Using Machine Learning

Abstract

This work endeavors to create an anticipatory system employing a diverse array of machine learning methodologies, encompassing Logistic Regression, Support Vector Machine, and K-Nearest Neighbor algorithms. The efficacy of each technique is meticulously evaluated, with a keen focus on identifying the most precise model for the early prediction of diabetes. The overarching goal of this initiative is to enhance the early detection capabilities and overall awareness of diabetes within the context of Malaysia. By identifying and implementing the most accurate predictive model, the work aspires to contribute significantly to mitigating the pervasive impact of this prevalent non-communicable disease. Through the advancement of predictive analytics, the work holds the potential to alleviate the burden imposed by diabetes on individuals and healthcare systems, ultimately fostering a healthier population and promoting proactive health management in the Malaysian context.