Pilot validation study for a large image database of proximal femur fracture anteroposterior radiographs: Searching for the ground truth
The observed interrater reliability between the LC-EG and AO-EG supports the credibility of the reference annotations, establishing a validated ground truth for proximal femur fractures. This evidence justifies using the radiographic image database as a benchmark for future studies and as a foundation for transparent, reproducible AI development and evaluation, thereby facilitating safer integration of decision support tools into orthopedic trauma workflows.
Authors
- Tracy Y. Zhu (ORCID: https://orcid.org/0000-0002-0500-0865)
- Alessandro Aprato (ORCID: https://orcid.org/0000-0002-2514-4719)
- Andrea Audisio (ORCID: https://orcid.org/0000-0002-1809-5058)
- An Sermon
- Frank F.A. IJpma
- Vincenzo Giordano
- Dhaval Desai
- Peter V. Giannoudis
Institutions
- University of Leeds (GB)
- University Medical Center Groningen (NL)
- AO Foundation (CH)
- Surya Hospitals (IN)
- Hospital Geral de Bonsucesso (BR)
- University of Turin (IT)
- KU Leuven (BE)
Publication Details
- Journal
- Injury
- Published
- 2026-01-22
- DOI
- https://doi.org/10.1016/j.injury.2026.113056
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00