JMIR Publications

ABSTRACT

Background:

Digital twin (DT) systems have emerged as a transformative approach in healthcare, enabling real-time, patient-specific modeling and personalized interventions. In diabetes care, DTs offer the potential to revolutionize glucose management, decision support, and therapy personalization.

Objective:

This systematic review synthesizes the current landscape of digital twin applications in diabetes. Thirteen structured research questions were addressed, organized under seven thematic domains spanning system design, target conditions, data sources, personalization strategies, intelligence/adaptability, validation methods, and implementation.

Methods:

Following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, we conducted a systematic review of 28 peer-reviewed articles applying digital twin frameworks in diabetes. Data extraction was guided by thirteen structured research questions, with findings categorized into model types, system components, data sources, personalization mechanisms, adaptive intelligence, validation strategies, and implementation challenges.

Results:

Most DTs employed machine learning, hybrid, or simulation-based approaches, targeting primarily type 1 and type 2 diabetes. Clinical goals included therapeutic control, prediction, decision support, and disease management. Lifestyle data, wearables, CGM, and EHRs were the dominant inputs, while personalization relied on adaptive feedback, insulin optimization, and behavior-driven tools. Intelligent features such as adaptive learning, explainable AI, and real-time synchronization enhanced adaptability, though human oversight was rare. Validation was mainly retrospective or simulation-based, with few clinical trials; reported outcomes included improved HbA1c, time-in-range, and reduced hypoglycemia. Ethical discussions focused on data privacy, while implementation barriers centered on validation gaps, data quality, and workflow integration.

Conclusions:

Digital twins for diabetes are technically diverse and increasingly patient-centered, but evidence for real-world clinical validation remains scarce. Key barriers include data quality, interoperability, ethical safeguards, and scalability. Future research should emphasize robust clinical trials, regulatory alignment, and standardized system architectures to enable equitable and clinically reliable deployment.