The AI implementation gap in trauma radiography: standalone versus discretionary AI-integrated fracture detection
Anna Gurabi, Sirus S. Hosseini-Begtary, Peter Hegedus, Andor Viktor Gal, Pal Maurovich-Horvat, Nikolett Marton · 2026
Read The AI implementation gap in trauma radiography: standalone versus discretionary AI-integrated fracture detection by Anna Gurabi, Sirus S. Hosseini-Begtary, Peter Hegedus, Andor Viktor Gal, Pal Maurovich-Horvat, Nikolett Marton (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13272699.txt.
Description
Anna Gurabi leads a 2026 study of artificial intelligence help for finding fractures on trauma X-rays. The team reviewed 2,317 trauma radiographs from one center, comparing a period without AI access in November 2023 with one in February 2024 when AI use was optional. A senior specialist set the true results.
On its own, AI reached up to 94.1 percent accuracy at the fracture level and 96.5 percent at the patient level in February. Radiologists with optional AI scored 93.4 percent accuracy, only slightly above those without it. The authors say optional use does not reliably lift sensitivity, so how AI is built into daily work matters as much as its raw skill.
Catalog record
| CREATOR | Anna Gurabi, Sirus S. Hosseini-Begtary, Peter Hegedus, Andor Viktor Gal, Pal Maurovich-Horvat, Nikolett Marton |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 51500 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |