Answers are grounded in this paper and cite their sources.
Background Age assessment in individuals without reliable identification is a recurrent medico-legal challenge in Europe, particularly in migration contexts. Distal radial epiphyseal fusion is among the last skeletal maturation events near the age of majority, yet population-specific reference data and radiation-free assessment strategies remain limited. Methods In this multicentre study conducted across German clinical sites and initial reception facilities, Northwest European (NWE) and Middle Eastern (ME) individuals aged 13–25 years underwent distal forearm assessment using a fully automated ultrasound device. Reference ages were obtained from documented birthdates or Greulich–Pyle bone ages. Gradient-boosting machine-learning models (LightGBM) were evaluated using leave-one-out cross-validation across sex-specific age thresholds. Performance was quantified using precision, recall, F1-scores, ROC/AUC, and Clopper–Pearson confidence intervals for correctly detected fusions. Results Of 1061 recordings, 830 high-quality ultrasound datasets were analysed across four sex–population clusters. Classification performance was biologically plausible and threshold-dependent, with optimal discrimination at 17.5 years in NWE females, 18.0–18.5 years in NWE males, 17.0–17.5 years in ME females, and 18.5 years in ME males. Females fused earlier than males in both populations, and sex-specific population shifts were observed. AUC values indicated good to excellent discrimination near the optimal thresholds (approximately 0.81–1.00). Conclusions Machine-learning–assisted automated ultrasound provides a scalable, radiation-free approach for assessing distal radial epiphyseal fusion in late adolescence. Population- and sex-specific shifts underline the importance of population-appropriate reference data when interpreting fusion status around legally critical age thresholds. While an unfused distal radial plate strongly supported minority status, complete fusion alone could not be considered definitive proof of adulthood. Thus reinforcing the need for probabilistic interpretation, particularly around the legally critical 18-year threshold, within a broader forensic age-assessment framework.
No takes yet. Share an insight, caveat, or question.
Birken et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: