AI for fracture diagnosis in clinical practice: Four approaches to systematic AI-implementation and their impact on AI-effectiveness
Implementation methods have a large impact on AI-effectiveness. These results suggest AI should not be considered for problem-solving or triage at this time; AI standalone performs better than either and may be a source of assistance where radiologists are unavailable. Best results were obtained implementing AI as safety net, which eliminates missed fractures with serious clinical consequences; even though false positives are increased, unnecessary treatments are limited.
Authors
- D. Loeffen (ORCID: https://orcid.org/0009-0001-3024-9822)
- Joachim Ernst Wildberger (ORCID: https://orcid.org/0000-0002-4810-6854)
- Estelle C. Nijssen (ORCID: https://orcid.org/0000-0001-5537-3283)
- Tim A. E. J. Boymans (ORCID: https://orcid.org/0000-0002-6047-9581)
- Frank M. Zijta (ORCID: https://orcid.org/0000-0001-9813-5226)
Institutions
- Maastricht University Medical Centre (NL)
- Maastricht University (NL)
Publication Details
- Journal
- European Journal of Radiology
- Published
- 2025-04-14
- DOI
- https://doi.org/10.1016/j.ejrad.2025.112113
- Citations
- 5
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 2.62