Journal DOI 10.68956/journal.human-performance-futures

Creative Commons source reading · Machine learning for performance

Artificial Intelligence for Weight Management in Children: A Narrative Review

Calcaterra V; Marin L; Cena H; Vandoni M; Conti MV; Guardamagna L; Patanè P; Rossi V; Carnevale Pellino V; Silvestri D; Zuccotti G

Originally published in Healthcare (Basel) · 2026-06-23

From the article

Selected source text. JournalOS removes markup and shortens excerpts where indicated. The full article provides the complete context.

Abstract

AbstractHighlights What are the main findings? Artificial intelligence shows good performance in identifying children at risk of overweight and obesity and can support early, personalized prevention and monitoring using clinical, lifestyle, and wearable data.Current evidence is still largely exploratory; while AI tools improve engagement, risk prediction, and behavioral support, robust long-term clinical effectiveness in pediatric weight outcomes remains limited. What are the implications of the main findings? AI should be integrated as a complementary tool within multidisciplinary, family-centered pediatric care to enhance personalization, monitoring, and adherence rather than replace clinical judgment.Future research and implementation must address ethical issues (privacy, bias, consent), ensure pediatric-specific validation, and…

8. Conclusions

AI is emerging as a promising complementary tool in the prevention and management of childhood overweight and obesity, with potential applications across risk assessment, dietary and lifestyle monitoring, behavioral support, and clinical decision-making. Current evidence suggests that AI-based approaches may enhance personalization, engagement, and continuity of care when integrated into pediatric weight management pathways. However, the available literature remains heterogeneous and largely exploratory, with important gaps in pediatric-specific validation, long-term effectiveness, and real-world implementation. Ethical considerations, including data privacy, transparency, algorithmic bias, and the central role of families, are particularly critical in pediatric populations and must be carefully addressed to ensure responsible use of…

Editorial reading guide

  • What data created and tested the model, and was evaluation independent?
  • What is the cost of a false positive, false negative or out-of-distribution decision?