Impact of Test Set Composition on AI Performance for Pediatric Radiograph Appendicular Skeleton Fracture Detection

Radiology 2026

View at publisher
Authors: Nikolaus Stranger, Mario Scherkl, Daniel Stutz, Michael Janisch, Georg Singer, Saskia Hankel, Holger Till, Maximilian Sackl, Franko Hržić, Sereina Herzog, Sebastian Tschauner
DOI: 10.1148/radiol.250540
Cited by: 2
References: 33

Abstract

< .001). Conclusion AI performance in pediatric fracture detection was influenced by test set composition and radiograph complexity, where an internal test set of complex radiographs was associated with decreased odds of correct prediction. © RSNA, 2026

Fields of Study & Subjects

Artificial Intelligence in Healthcare and Education Medical Imaging and Analysis Radiomics and Machine Learning in Medical Imaging

Publication details

Journal / source
Radiology
Publisher
Radiological Society of North America (RSNA)
Volume
318
Issue
2
Pages
e250540–e250540
Publication date
1 February 2026
Language
EN