Comparative analysis of an automated bone age tool with manual assessment in a multiethnic Southeast Asian paediatric cohort in Singapore.

Background: Bone age assessment is essential for evaluating growth and pubertal disorders, but manual methods such as the Greulich-Pyle atlas are subject to inter-observer variability. Automated tools like BoneXpert may improve accuracy and consistency.

Objective: To validate the accuracy and reliability of BoneXpert, an automated bone age assessment tool, compared to traditional manual methods performed by paediatric endocrinologists and radiologists in a multiethnic paediatric cohort in Singapore.

Materials and methods: This retrospective cohort study was conducted at KK Women's and Children's Hospital and included paediatric patients aged 0 years to 17 years who presented to the endocrine clinic between February 2012 and September 2021. Bone age was assessed independently using the Greulich and Pyle (GP) method by radiologists and paediatric endocrinologists and compared with BoneXpert's automated assessments.

Results: The study included 200 paediatric patients with a mean age of 9.4 years (± 3.5 years). BoneXpert demonstrated excellent agreement with endocrinologists, with intraclass correlation coefficients (ICC) of 0.983 (95% CI: 0.977-0.987) and 0.974 (95% CI: 0.967-0.980) for Endocrinologists 1 and 2, respectively. The root mean square error (RMSE) between BoneXpert and the endocrinologists was 0.652 years and 0.852 years, indicating high accuracy. However, the RMSE between BoneXpert and radiologists was higher at 1.178 years, reflecting greater variability. Bland-Altman plots showed good agreement between BoneXpert and manual assessments.

Conclusion: BoneXpert provides a reliable and efficient alternative to manual bone age assessments and aligns closely with endocrinologists' evaluations. This tool could significantly reduce inter-rater variability and enhance clinical efficiency, particularly in diverse ethnic populations.