Health AI Central
Peer-Reviewed Publication
Emerg Radiol2026September 22, 2026Journal Article

Diagnostic accuracy & clinical importance of AI confidence for extremity fracture detection: 2,508-patient retrospective cohort.

Sabine Morris Delhez1,2,3,4, Thomas Breiner Enøe5, Oke Gerke6,7, Bjarke Viberg6,8, Pia Iben Pietersen5,9, Benjamin Schnack Brandt Rasmussen5,9,10,6, Janni Jensen5,9,10
1Research and Innovation Unit of Radiology (UNIFY), University Southern Denmark, J. B. Winsløws Vej 4, 5000, Odense, Denmark. Smd@rsyd.dk.
2Department of Radiology, Odense University Hospital, J. B. Winsløws Vej 4, 5000, Odense, Denmark. Smd@rsyd.dk.
3Centre for Artificial Intelligence (CAI-X), Odense University Hospital, J. B. Winsløws Vej 4, 5000, Odense, Denmark. Smd@rsyd.dk.
4Department of Clinical Research, University of Southern Denmark, J. B. Winsløws Vej 4, 5000, Odense, Denmark. Smd@rsyd.dk.
5Research and Innovation Unit of Radiology (UNIFY), University Southern Denmark, J. B. Winsløws Vej 4, 5000, Odense, Denmark.
6Department of Clinical Research, University of Southern Denmark, J. B. Winsløws Vej 4, 5000, Odense, Denmark.
7Department of Nuclear Medicine, Odense University Hospital, J. B. Winsløws Vej 4, 5000, Odense, Denmark.
8Department of Orthopedic Surgery and Traumatology, Odense University Hospital, J. B. Winsløws Vej 4, 5000, Odense, Denmark.
9Department of Radiology, Odense University Hospital, J. B. Winsløws Vej 4, 5000, Odense, Denmark.
10Centre for Artificial Intelligence (CAI-X), Odense University Hospital, J. B. Winsløws Vej 4, 5000, Odense, Denmark.
PubMed DOI

Abstract

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 sing…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free AccountSign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.