Small lesion–high risk: diagnostic performance of artificial intelligence in paediatric fractures with medicolegal impact
While the AI-based software demonstrated overall strong performance, its emphasis on specificity limits its utility in detecting high-risk fractures for which sensitivity is paramount. Future development should focus on enhancing sensitivity, particularly for the detection of elbow dislocations.
Authors
- Oliver Johannes Deffaa
- Martin Lacher (ORCID: https://orcid.org/0000-0002-4616-9464)
- Daniel Gräfe (ORCID: https://orcid.org/0000-0002-7680-0990)
- W. Hirsch (ORCID: https://orcid.org/0000-0003-0960-3740)
- J Pape (ORCID: https://orcid.org/0009-0002-1280-3866)
- Peter Zimmermann (ORCID: https://orcid.org/0000-0001-6571-5283)
Institutions
- University Hospital Leipzig (DE)
Publication Details
- Journal
- Pediatric Radiology
- Published
- 2025-11-12
- DOI
- https://doi.org/10.1007/s00247-025-06456-3
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00