The reliability of bone age determination in central European children using the Greulich and Pyle method

Abstract

This study assessed the reliability of bone age determination in normal central European children using the Greulich and Pyle method and determined the effects of readers' experience on the measured bone ages. Plain hand radiographs of 47 children (aged 2 months to 18.8 years) with normal growth were analysed by four radiologists (two experienced paediatric radiologists and two radiology residents). The readers were blinded to the age of the children. The images were re-read by the same readers 2 months later. The mean intraobserver and interobserver variations were lower for experienced readers than for radiology residents. However, these differences were not statistically significant at the 5% level. The difference between the chronological age and the measured bone age was -1.5 +/- 7.6 months (p = 0.20) for the experienced readers and 2.7 +/- 10.3 months (p = 0.09) for the radiology residents. The differences between the measured bone age and chronological age were statistically significant (p = 0.04) for only one of the two radiology residents. Although the measurements by all four readers underestimated the chronological age, the differences between chronological age and bone age were within the normal variations of skeletal maturation as reported by Greulich and Pyle. Our data suggest that the reliability of bone age measurements increases with experience and that the Greulich and Pyle method may be used for central European children.