Artificial Intelligence in Digital Health Interventions for Obesity Management with focus on Generative Artificial Intelligence: a Scoping Review (Preprint)

Abstract

<sec> <title>BACKGROUND</title> The high prevalence rates of obesity place it as a public health concern. Obesity management increasingly incorporates digital health interventions with rapid growth in artificial intelligence applications. However, the role of generative artificial intelligence (GenAI) remains unclear, particularly in relation to health literacy and community engagement. </sec> <sec> <title>OBJECTIVE</title> To systematically map an overview of generative artificial intelligence (AI) applications within digital health interventions for adult obesity management and identify how health literacy and community engagement are addressed within these applications. </sec> <sec> <title>METHODS</title> A scoping review of literature published from inception to October 2025 was conducted according to the JBI Manual for Evidence Synthesis for Scoping Reviews by the Joanna Briggs Institute. Three databases (PubMed, Web of Science and Scopus) were searched. Eligible studies included records reporting the use of artificial intelligence, including GenAI, for obesity management in adults. Data was extracted and synthesised descriptively through quantitative and qualitative analysis. The results are presented according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for scoping reviews (PRISMA-ScR) guidelines. </sec> <sec> <title>RESULTS</title> Database searches retrieved 18,955 records, 108 met the inclusion criteria. Traditional AI methods appeared in 69% (n = 75) of studies, while generative AI was used in 10% (n = 11). Among GenAI records, 55% (n = 6) supported diet planning or nutritional guidance, 18% (n = 2) incorporated health literacy-related features, and 9% (n = 1) reported community engagement elements. </sec> <sec> <title>CONCLUSIONS</title> Evidence on GenAI in obesity management interventions remains limited. Future research should evaluate generative artificial intelligence tools in real-world settings and incorporate health literacy and community engagement frameworks in their implementation. </sec>

Ähnliche Arbeiten