Paper Contents
Abstract
Diabetes mellitus is a chronic condition that has significant health and economic burdens worldwide. The rapid advancements in machine learning (ML) have provided new methodologies for early detection, prediction, and management of diabetes. This paper reviews key developments in ML applications for diabetes care, focusing on three critical areas: automated insulin delivery (AID) systems for Type 1 diabetes (T1D), phenotypic markers for Type 2 diabetes (T2D) prediction, and hybrid ML models integrating Support Vector Machines (SVM), Artificial Neural Networks (ANN), and fuzzy logic for early disease detection. The paper evaluates the effectiveness of these approaches, highlights their strengths and limitations, and discusses future directions for improving diabetes management through ML-driven solutions. The need for robust datasets, standardization, interpretability, and real-world validation is emphasized to ensure the successful deployment of ML in clinical settings.
Copyright
Copyright © 2025 Devang Satani. This is an open access article distributed under the Creative Commons Attribution License.
