A COMPARATIVE ANALYSIS FOR MACHINE LEARNING-BASED DIABETES MELLITUS DETECTION

Diabetes Mellitus (DM) is a persistent metabolic ailment that impacts millions worldwide and results in severe health problems, including cardiovascular diseases, renal failure, and neuropathy. Timely identification and ongoing surveillance are crucial for the efficient management of diabetes and the avoidance of complications. Machine learning (ML) offers an innovative approach to disease detection, enabling the analysis of large healthcare datasets for early diagnosis, risk assessment, and personalized treatment. This review provides a comprehensive overview of the applications of machine learning in the detection of Diabetes Mellitus. It discusses various ML algorithms used for predictive modeling, classification, and feature selection in diabetes diagnosis. Additionally, we examine different datasets, the performance of various models, challenges faced in implementing ML-based systems, and future directions. This review aims to provide insights into how machine learning can contribute to improving diabetes management through early detection and individualized care.