Machine Learning Techniques and Data Extraction Approaches in Diabetes Healthcare: A Comprehensive Review

Abstract

The contemporary world finds itself grappling with the pervasive impact of diseases, and diabetes stands at the forefront. As per the “International Diabetes Federation”, a staggering 246 million individuals worldwide currently live with diabetes, and this figure is projected to soar to a monumental 380 million by the year 2025. This metabolic disorder, characterized by the mismanagement of blood glucose levels, engenders a heightened susceptibility to an array of ailments, including heart attacks, kidney disease, and renal failure. In light of these concerns, healthcare practitioners necessitate a dependable prognostic methodology to effectively diagnose diabetes mellitus. Fortunately, the rapid strides made in the realm of Machine Learning and Data Mining present a plethora of techniques and algorithms within the domain of artificial intelligence that can be harnessed with efficacy for disease prediction and diagnosis. This comprehensive paper endeavors to furnish a discerning review of the machine learning and data mining methods routinely employed in the analysis and prognostication of diabetes.