A Review on Diabetes Classification Based on Machine Learning Algorithms

Abstract

Diabetes, a chronic metabolic disorder, is a significant global health concern affecting millions of individuals worldwide. Early and accurate diagnosis of diabetes is crucial for effective management and prevention of complications. Machine learning (ML) techniques have emerged as powerful tools for analyzing diabetes-related data, aiding in the classification and prediction of diabetes types. This review provides a comprehensive overview of recent advancements in diabetes classification using ML algorithms, highlighting their strengths, limitations, and future directions. Various ML algorithms, including but not limited to support vector machines, decision trees, random forests, artificial neural networks, and ensemble methods, are discussed in details. Furthermore, data preprocessing techniques, feature selection methods, and evaluation metrics employed in diabetes classification studies are examined. Additionally, challenges such as data imbalance, interpretability, and generalization across diverse populations are addressed. Finally, potential avenues for future research to enhance the accuracy and applicability of ML-based diabetes classification systems are proposed.