EUVIMEDEUVIMED entdecken
Crossref

Artificial Intelligence-Assisted Fracture Detection on Plain Radiographs: Diagnostic Accuracy, Bias and Clinical Workflow Outcomes

Sun Yue, Chrismis Novalinda Ginting, Liena .

International Journal of Drug Delivery Technology · 06.06.2026 · 16 (47s)

DOI: 10.25258/ijddt.16.47s.61 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, erschienen am 06.06.2026. Verfasst von Sun Yue und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Unnoticed fractures on radiographs remain a patient-safety issue, as high-volume emergency radiology, excessive fatigue, irregular cortical disruption, and inconsistent interpretative skills create conditions conducive to diagnostic error. This article entails a secondary rapid review of the artificial intelligence-aided detection of fractures on plain radiographs. Secondary reviews and reporting structures informed the literature review and theoretical framing; the findings were carefully limited to primary research on diagnostics, reader performance and workflow. They were used to code twenty main studies using the thematic analysis. Three findings emerged. First, standalone AI demonstrated high sensitivity and specificity for limited tasks depending on anatomy; however, accuracy decreased for less pronounced, older, irregular, or represented fractures. Second, AI was most robust as a second reader: most reader experiments showed increased sensitivity, including smaller, less stereotyped specificity and reading-time variations. Third, the risks of bias and implementation were not thoroughly reported, particularly the subgroup performance by age, bone type, image quality, and clinical setting. This evidence justifies the use of supervised AI as a backup, not a substitute for clinical judgement. Future research ought to focus on prospective multicenter validation, transparent subgroup audit, workflow outcomes, and post-deployment monitoring.

Zitieren

APA

Yue, S., Ginting, C. N., & ., L. (2026). Artificial Intelligence-Assisted Fracture Detection on Plain Radiographs: Diagnostic Accuracy, Bias and Clinical Workflow Outcomes. International Journal of Drug Delivery Technology, 16(47s). https://doi.org/10.25258/ijddt.16.47s.61

Vancouver

Yue S, Ginting CN, . L. Artificial Intelligence-Assisted Fracture Detection on Plain Radiographs: Diagnostic Accuracy, Bias and Clinical Workflow Outcomes. International Journal of Drug Delivery Technology. 2026;16(47s). doi:10.25258/ijddt.16.47s.61

BibTeX
@article{Yue2026,
  author = {Yue, Sun and Ginting, Chrismis Novalinda and ., Liena},
  title = {Artificial Intelligence-Assisted Fracture Detection on Plain Radiographs: Diagnostic Accuracy, Bias and Clinical Workflow Outcomes},
  journal = {International Journal of Drug Delivery Technology},
  year = {2026},
  volume = {16},
  number = {47s},
  doi = {10.25258/ijddt.16.47s.61}
}
Kostenlos starten →