Scoping insights into artificial intelligence-driven treatment of diabetes mellitus in clinical practice

Diabetes mellitus (DM) is a significant health concern around the world due to its increasing prevalence, high rates of morbidity and morbidity from diabetes and diabetic complications, and the associated economic burden. Despite the rapid development of digital healthcare ecosystem, DM remains an incurable lifelong disorder. Nevertheless, there has been a growing interest in developing and using artificial intelligence (AI) technologies for DM management and care. By advancing the understanding of AI-driven technology in treatment of DM and refining clinical approaches, healthcare providers can better navigate the challenges and maximize the benefits associated with these technologies. From this perspective, this scoping review aimed to provide insights to the most recent applications and progress of AI technology to various aspects and opportunities of DM treatment in clinical practice. Comprehensive review following database search on the applications of AI in treatment of DM (T1DM and T2DM) in clinical settings. A literature search was conducted in databases, such as PubMed, Web of Science, and Scopus. The search covered references from 2000 to 2024 with data extraction and organized thematically yielding a total of 14 relevant studies included in this study. The majority of the studies were based on database analysis using AI (n = 7) followed by randomized controlled trials (n = 5). This review found that the application of AI, specifically machine learning (ML) and deep learning (DL)-based medical devices and prediction models, shows great promise for real-time monitoring and management, personalized treatment planning, and has advanced significantly in supporting predictive models for the treatment of DM or its complications. AI has the potential to change the way this chronic disease is treated and can provide an additional opportunity to achieve better efficiency in DM care. Nevertheless, most applications are still adjunctive (decision-support) and face significant practical, ethical, and validation hurdles.