Diagnostic accuracy & clinical importance of AI confidence for extremity fracture detection: 2,508-patient retrospective cohort
Emergency Radiology · 22.09.2026
DOI: 10.1007/s10140-026-02546-3 ↗Kurz gefasst
Fachartikel in der Zeitschrift Emergency Radiology, online erschienen am 22.09.2026. Verfasst von Sabine Morris Delhez und 6 weiteren Autor:innen. Beteiligte Einrichtung: Research and Innovation Unit of Radiology (UNIFY), University Southern Denmark, J. B. Winsløws Vej 4, 5000, Odense, Denmark. Smd@rsyd.dk. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Southern Denmark.
Abstract (Originalsprache)
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 December 2024. The index test was the algorithm output (bounding boxes with confidence). The reference standard was the radiology report with discordant cases adjudicated by follow-up imaging when available or specialist review. Sensitivity, specificity, PPV and negative predictive value (NPV) were calculated with 95% confidence intervals; differences were tested using the McNemar and a score test and patient-clustered logistic regression.
Results
There were 2,508 patients, median age 34 years (range 2–105), 1,236 males; 815 patients had a total of 1,028 fractures. Per-fracture sensitivity and PPV were 92.7% (95% CI: 90.9–94.5) and 87.6% (95% CI: 85.5–89.7); Specificity and NPV were 94.4% (95% CI: 93.2-95.4) and 96.6% (95% CI: 95.6–97.4). PPV for high-confidence was superior to low-confidence detections (99.1% vs 59.1%, p < 0.001). Children had higher per-fracture PPV than adults (91.7% vs. 86.1%; p = 0.01), with no significant difference in per-fracture sensitivity, or case-wise performance.
Conclusion
The algorithm showed good diagnostic performance for extremity fracture detection on radiographs. The AI’s confidence stratification strongly influenced PPV, and higher PPV was seen among children.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Research and Innovation Unit of Radiology (UNIFY), University Southern Denmark, J. B. Winsløws Vej 4, 5000, Odense, Denmark. Smd@rsyd.dk.
- Department of Radiology, Odense University Hospital, J. B. Winsløws Vej 4, 5000, Odense, Denmark. Smd@rsyd.dk.
- Centre for Artificial Intelligence (CAI-X), Odense University Hospital, J. B. Winsløws Vej 4, 5000, Odense, Denmark. Smd@rsyd.dk.
- Department of Clinical Research, University of Southern Denmark, J. B. Winsløws Vej 4, 5000, Odense, Denmark. Smd@rsyd.dk.
- Research and Innovation Unit of Radiology (UNIFY), University Southern Denmark, J. B. Winsløws Vej 4, 5000, Odense, Denmark.
- Department of Clinical Research, University of Southern Denmark, J. B. Winsløws Vej 4, 5000, Odense, Denmark.
Förderung
- University of Southern Denmark
Zitieren
APA
Delhez, S. M., Enøe, T. B., Gerke, O., Viberg, B., Pietersen, P. I., Rasmussen, B. S. B., & Jensen, J. (2026). Diagnostic accuracy & clinical importance of AI confidence for extremity fracture detection: 2,508-patient retrospective cohort. Emergency Radiology. https://doi.org/10.1007/s10140-026-02546-3
Vancouver
Delhez SM, Enøe TB, Gerke O, Viberg B, Pietersen PI, Rasmussen BSB, et al. Diagnostic accuracy & clinical importance of AI confidence for extremity fracture detection: 2,508-patient retrospective cohort. Emergency Radiology. 2026. doi:10.1007/s10140-026-02546-3
BibTeX
@article{Delhez2026,
author = {Delhez, Sabine Morris and Enøe, Thomas Breiner and Gerke, Oke and Viberg, Bjarke and Pietersen, Pia Iben and Rasmussen, Benjamin Schnack Brandt and Jensen, Janni},
title = {Diagnostic accuracy & clinical importance of AI confidence for extremity fracture detection: 2,508-patient retrospective cohort},
journal = {Emergency Radiology},
year = {2026},
doi = {10.1007/s10140-026-02546-3}
}
EUVIMED