<![CDATA[Diabetes mellitus is a chronic disease with a growing global prevalence, posing significant challenges for healthcare systems worldwide. Machine Learning (ML) offers promising solutions for early diagnosis and prediction by analyzing complex medical data efficiently. This study adopts a Systematic Literature Review (SLR) method guided by the PRISMA protocol to analyze 15 open-access articles published between 2022 and 2025 from the ScienceDirect database. These studies explore the use of various ML algorithms—including Support Vector Machine (SVM), Random Forest (RF), and Convolutional Neural Network (CNN)—in diagnosing diabetes. The main objective is to evaluate the effectiveness, strengths, and limitations of each algorithm in clinical applications. The review highlights current trends, performance comparisons, and challenges in implementing ML models for diabetes diagnosis. The findings are expected to provide valuable insights for researchers and practitioners aiming to develop more accurate, efficient, and applicable ML-based diagnostic systems for improved diabetes management and early intervention.]]>
Copyrights © 2025
