AI Enabled Digital Twin Approaches in Nutrition and Dietetics: Evidence, Potential, and Limitations
TL;DR
This narrative review defines the concept of DT from a healthcare perspective, summarizes its current applications in nutrition and dietetics, and outlines its high potential, key limitations, and challenges.
Abstract
Rapid advances in technology, particularly the integration of artificial intelligence (AI) technology into our lives, have increased interest in digital twin (DT) technology, which is a dynamic virtual model of a physical system. In the healthcare sector, DT is also seen as having the potential to bring about lasting transformation in areas such as drug development, advanced diagnostics and preventive treatment, clinical research, and personalized medicine. In the coming years, DT is expected to enable personalized nutrition by integrating genetic, epigenetic, microbiome, metabolic, immunological, and lifestyle data into comprehensive virtual models. This new paradigm has the potential to provide groundbreaking opportunities for the management and prevention of various nutrition-related diseases, obesity, and support healthy aging. Although early research in the field of nutrition is promising, various challenges and limitations persist, including data standardization, privacy, data quality and security, ethical concerns, high costs, scalability, and clinical validation issues. Currently, the use of DT in the field of nutrition and dietetics remains in the proof-of-concept stage. Nevertheless, it is anticipated that as these limitations are overcome over time, this technology will transform and guide global healthcare systems. This narrative review defines the concept of DT from a healthcare perspective, summarizes its current applications in nutrition and dietetics, and outlines its high potential, key limitations, and challenges.