Pediatric hand fractures detection on radiographs: do localization cues improve diagnostic performance?

Objective: To compare the diagnostic accuracy and interpretation time for detection of pediatric fractures on hand radiographs with and without localization cues.

Materials and methods: Consecutive children, who underwent radiographic examinations after injury, over 2 years (2019-2021) and with > 2 weeks of follow-up to confirm the presence or absence of a fracture, were included. Four readers, blinded to history and diagnosis, retrospectively reviewed all images twice, without and with cue, at least 1 week apart and after randomization, to determine the presence or absence of a fracture, and if present, anatomic location and diagnostic confidence were recorded. Interpretation time for each study was also recorded and averaged across readers. Inter-reader agreement was calculated using Fleiss' kappa. Diagnostic accuracy and interpretation time were compared between examinations using sensitivity, specificity, and Mann-Whitney U correlation.

Results: Study group included 92 children (61 boys, 31 girls; 10.8 ± 3.4 years) with and 40 (31 boys, 9 girls; 10.9 ± 3.7 years) without fractures. Cue improved inter-reader agreement (κ = 0.47 to 0.62). While the specificity decreased (63 to 62%), sensitivity (75 to 78%), diagnostic accuracy (71 to 73%), and confidence improved (78 to 87%, p < 0.01), and interpretation time (median: 40 to 22 s, p < 0.001) reduced with examinations with localization cue. Specifically, examinations with fracture and cue had the shortest interpretation time (median: 16 s), whereas examinations without fracture and without cue had the longest interpretation time (median: 48 s).

Conclusion: Localization cues increased inter-reader agreement and diagnostic confidence, reduced interpretation time in the detection of fractures on pediatric hand radiographs, while maintaining diagnostic accuracy.