DIABOT: REVOLUTIONIZING T2DM COMPLICATION PREVENTION WITH AI RECOMMENDATIONS &NOTIFICATIONS: A SCOPING REVIEW.

Abstract

Background:
“Type 2 Diabetes Mellitus (T2DM)” is a “chronic condition impacting millions of individuals globally, significantly influencing to “morbidity and mortality” due to complications such as “cardiovascular disease”, nephropathy and neuropathy. Traditional management methods often fail to provide personalized and timely interventions leading to missed opportunities in preventing these complications. Artificial Intelligence (AI)-driven mobile health (mHealth) applications offer a novel approach by delivering personalized recommendations and notifications to enhance diabetes management and prevent complications.

Objective:
This “scoping review” aims to map the existing literature on AI-powered mHealth applications such as Diabot in preventing T2DM complications. The review explores the efficacy of “AI-driven interventions” in improving “glycemic control” and reducing the incidence of key complications.

Methods:
Following the “Arksey and O’Malley framework for scoping reviews”, a systematic search was conducted across databases including “PubMed, Scopus, Web of Science, IEEE Xplore and Google Scholar”. Studies published between 2010 and 2024, focused on AI-based T2DM complication prevention were included. Data were extracted on study design, AI system details, outcomes (HbA1c, complication rates) and barriers to implementation.

Results:
AI-driven interventions were effective in reducing HbA1c and improving glycemic control. Shaikh et al. (2024) and Bretschneider et al. (2023) reported significant reductions in HbA1c (p < 0.001) in their studies. However, long-term user engagement and integration with healthcare systems emerged as significant challenges. Data privacy and accessibility were also noted as barriers to widespread adoption.

Conclusion:
AI-powered mHealth applications hold promise in preventing T2DM complications through personalized care. Future research should address barriers such as user engagement, healthcare integration and data privacy to fully harness the “potential of AI in diabetes management”.