AI-Powered Approaches for Diabetes Detection in Healthcare and Monitoring: A Review of Recent Advances

Abstract

Artificial Intelligence (AI) is being investigated more and more in the treatment of diabetes to tailor care for individuals with the disease and modify therapies for complicated presentations. Diabetes is a common condition with a significant chance of complications. According to reports, the number of diabetics globally is rising each. The growing incidence of diabetes worldwide has put a significant strain on healthcare systems, highlighting the need for efficient diagnosis, monitoring, and treatment techniques. New, integrated, tailored healthcare connected to diabetes is, however, inadequately developed. Traditional diagnostic approaches, sometimes limited in scope, do not address the increasing prevalence of diabetes-related comorbidities such as neuropathy, nephropathy, and retinopathy. Recent developments in Artificial Intelligence (AI) and Machine Learning (ML) have made it possible to develop new techniques for diabetes monitoring and diagnosis.  This research offers a thorough analysis of AI-powered diabetes treatment strategies, emphasizing important algorithms like Decision Trees (DT), Support Vector Machines (SVM), and Neural Networks (NN). The study also examines how Explainable Artificial Intelligence (XAI) might enhance clinical settings by making AI models more transparent and interpretable. Future directions to increase the efficacy of AI-driven diabetes detection systems are also explored, along with issues like data quality, clinical integration, and user-centred design.