aceDiagnostic accuracy & clinical importance of AI confidence for extremity fracture detection: 2,508-patient retrospective cohort
Purpose To estimate diagnostic performance of a deep learning algorithm for extremity fracture detection on radiographs in patients aged ≥ 2 years using a refined reference standard. Secondary, to compare positive predictive value (PPV) by the algorithm's built-in confidence level (high vs. low) and diagnostic performance between adults (≥ 18 years) and children. Methods This retrospective single-center study consecutively included patients with radiography of a suspected extremity fracture between January and D…
In a single-center review of 2,508 patients, the AI's high-confidence fracture detections on X-rays were correct 99.1% of the time, and the authors judged overall performance good.
Sources
- Peer-reviewedEmergency Radiology2026-09-22
What do you make of this one?
Truvace Impact Record TRV-2026-1176, v2: “Diagnostic accuracy & clinical importance of AI confidence for extremity fracture detection: 2,508-patient retrospective cohort.” Truvace, 2026-11-04. /record/TRV-2026-1176 (accessed on the day you copy it). sha256 e2afde3468e7dc28…
Change history
Every change made to this record since it was first published, and why.
Editorial pass: sharper headline; gain/problem restated as concrete outcomes.
Certified into the record
How to check it yourself, without trusting this page
Download any version from /api/record/TRV-2026-1176 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.