Data mining techniques for type 2 diabetes prediction: A literature review

Abstract

Type 2 Diabetes Mellitus (T2DM) is rapidly becoming one of the most prevalent chronic diseases globally. It has elevated blood glucose levels in the body due to insulin resistance and inadequate insulin production. Diabetes, a rapidly growing chronic disease affecting millions of peoples globally. T2DM affects over 90% of people with diabetes. Its worldwide influence necessitates precise diagnosis, prognosis, treatment, and efficient administration. The growing widespread occurrence of type 2 diabetes necessitates the creation of efficient models for prediction that allow for prompt diagnosis and care. This research analyses different information mining procedures that are utilized for anticipating T2DM. It evaluates their suitability, limitations, and assets. Various data mining techniques (DMT) have shown potential in examining huge datasets to diagnose and manage T2DM. Different strategies like choice trees, support vector machines (SVM), brain organizations, and irregular woods are surveyed in view of exactness, interpretability, computational effectiveness, and overfitting powerlessness of these huge datasets. Data quality issues, feature selection, model interpretability, and scalability are major obstacles in T2DM prediction. This study examines the potential applications of data mining approaches for T2DM prediction in the years to come. Future research directions might include combining data from many sources, utilizing deep learning developments, and creating Artificial Intelligence (AI) models with explicable features.