Feasibility of image-based 3D avatar anthropometry assessment of pediatric obesity: a pilot study.

Clinical Snapshot

Key Findings

• P Value: Adjusted p < 0.05 for correlations (false discovery rate-corrected); no significant difference for waist-to-hip and waist-to-stature ratios

• Effect Size: Spearman's ρ = 0.62–0.72 for avatar vs. manual circumferences; avatar measurements systematically overestimated manual measurements; waist-to-hip and waist-to-stature ratios showed no significant differences between methods

• Primary Outcome: Agreement between AI-derived 3D avatar circumference measurements and ISAK manual anthropometric measurements in children aged 8–10 years

• Nnt Or Sensitivity: Mean absolute error: 6.21–7.11 cm for circumference measurements; Bland-Altman analysis demonstrated systematic overestimation with wide limits of agreement, particularly for waist and hip circumferences; both methods similarly discriminated weight status categories (no formal sensitivity/specificity reported)

• Confidence Interval: Not reported in the abstract for primary agreement statistics

Clinical Application

Technically feasible in school settings for children meeting weight and image quality thresholds, but the 56% failure rate due to software constraints represents a major operational barrier. Equipment requirements, image acquisition protocols, and processing infrastructure are not fully described, making real-world deployment assessment difficult. The technology is not yet commercially available or validated for routine clinical use. In Australia, paediatric obesity assessment is guided by RACGP and the Royal Australasian College of Physicians (RACP) guidelines, which recommend BMI-for-age percentiles alongside waist circumference as primary screening tools. Manual anthropometry remains the standard of care in Australian primary care and school health settings. The 3D avatar technology evaluated in this study is not TGA-registered as a medical device for diagnostic use and is not referenced in current RACGP or Australian Dietary Guidelines frameworks. Given the mean absolute errors of 6–7 cm for waist circumference — a key cardiometabolic risk marker — this technology would not meet the accuracy requirements for individual clinical decision-making in Australian paediatric practice. However, the population-level surveillance application may have relevance for Australian school-based obesity monitoring programs such as the Australian National Children's Nutrition and Physical Activity Survey, provided technical constraints are resolved. PBS listing is not applicable to this diagnostic technology at this stage. Children aged 8–10 years with body weight ≥30 kg in school-based or population surveillance settings; not currently applicable for individual clinical assessment of paediatric obesity

Abstract

UNLABELLED: The purpose of this study is to evaluate the feasibility and validity of 3D avatar-based anthropometry for assessing anthropometric indicators of overweight and obesity in children based on artificial intelligence-derived 3D body reconstruction. This cross-sectional study included 171 children aged 8-10 years from five primary schools in southern Spain. Due to technical constraints of the reconstruction software, 75 children meeting predefined image quality and body weight requirements (≥ 30 kg) were eligible for 3D avatar analysis. Manual anthropometric measurements were obtained following International Society for the Advancement of Kinanthropometry (ISAK) standards and compared with avatar-derived circumferences. Agreement was assessed by using Wilcoxon tests, Spearman correlations, Bland-Altman analyses, and false discovery rate-adjusted comparisons. Avatar-derived circumferences were consistently greater than manual measurements, although waist-to-hip and waist-to-stature ratios demonstrated no significant differences. Avatar and manual circumferences were moderately to strongly correlated (Spearman's ρ = 0.62-0.72; adjusted p < 0.05). However, the mean absolute errors ranged from 6.21 to 7.11 cm, and Bland-Altman analysis revealed systematic overestimation with wide limits of agreement, particularly for waist and hip circumferences. Despite these discrepancies, both methods similarly discriminated between weight status categories. CONCLUSION: Image-based 3D avatar anthropometry is a feasible, noninvasive approach for population-level screening and research in pediatric settings. Although the system reliably captures relative differences and body proportions, its current accuracy is insufficient for individual-level clinical assessment. Further algorithmic refinement and validation in lighter and more diverse pediatric populations are needed before clinical implementation. WHAT IS KNOWN: • Childhood obesity remains a major public health challenge requiring accurate monitoring. • Anthropometric assessment still relies mainly on manual measurements, while AI-based 3D body modeling offers a promising non-invasive alternative. WHAT IS NEW: • Image-based 3D avatar anthropometry is feasible in school settings but is constrained by technical requirements. • Avatar measurements are correlated with manual anthropometry and preserve weight status discrimination but demonstrate systematic overestimation and limited agreement.

References

1. 1.Del Mar Uclés-Torrente, M., Ruiz-Gamarra, G. E., Alcalde-Llergo, J. M., Vaquero-Álvarez, M., Blancas-Sánchez, I. M., Aparicio-Martínez, P., & Vaquero-Abellán, M. (2026). Feasibility of image-based 3D avatar anthropometry assessment of pediatric obesity: a pilot study. European Journal of Pediatrics. https://doi.org/10.2196/40066