Use of Automated Bone Age for Critical Growth Assessment

Abstract

Background. We compared the variability of bone age (BA) rating between clinicians and an automated system in children with congenital adrenal hyperplasia (CAH). Method. A total of 126 radiographs assessed by 3 clinicians blinded to patient details using Greulich and Pyle (GP) (readers 1, 2, and 3) and BoneXpert (BX). Results. Comparing BA rating with each other, the mean of the absolute differences varied from 0.42 ± 0.53 years (reader 1 and BX) to 0.57 ± 0.58 years (reader 2 and reader 3), P = .368. Comparing ratings that were consistent with all 4 methods (within 1 year of each other, 93/126, 74%) and the remaining, “outliers” (33/126, 26%), the outliers were younger ( P = .003), smaller (height, P = .011, weight, P = .000), and prepubertal ( P = .001). Conclusion. The variability of BA rating in CAH children is similar whether performed by clinicians or an automated system. The greatest variability was in prepubertal children.