EUVIMEDOntdek EUVIMED
BeobachtungsstudieOpen access

Prospective Diagnostic Accuracy and Technical Feasibility of Artificial Intelligence-Assisted Rib Fracture Detection on Chest Radiographs: Observational Study

Shu-Tien Huang iD, Liong-Rung Liu iD, Ming-Feng Tsai iD, Ming-Yuan Huang iD, Hung-Wen Chiu iD

JMIR Medical Informatics · 2026

DOI: 10.2196/77965 ↗

At a glance

Beobachtungsstudie in JMIR Medical Informatics, 2026. Written by Shu-Tien Huang and 4 co-authors. Institution: Department of Emergency Medicine, Mackay Memorial Hospital, Taipei, Taiwan. Major MEDLINE topics: Artificial Intelligence, Rib Fractures, Radiography, Thoracic. Cited 5 times so far (Crossref); 35 references. The full text is freely available in PubMed Central.

SamenvattingSubjectsBibliografische gegevensCiteRelated studies

Abstract (original language)

Background

Rib fractures are present in 10%‐15% of thoracic trauma cases but are often missed on chest radiographs, delaying diagnosis and treatment. Artificial intelligence (AI) may improve detection and triage in emergency settings.

Objective

This study aims to evaluate diagnostic accuracy, processing speed, and technical feasibility of an artificial intelligence–assisted rib fracture detection system using prospectively collected data within a real-world, high-volume emergency department workflow.

Methods

We conducted an observational feasibility study with prospective data collection of a faster region-based convolutional neural network–based AI model deployed in the emergency department to analyze 23,251 real-world chest radiographs (22,946 anteroposterior; 305 oblique) from April 1 to July 2, 2023. This study was approved by the Institutional Review Board of MacKay Memorial Hospital (IRB No. 20MMHIS483e). AI operated passively, without influencing clinical decision-making. The reference standard was the final report issued by board-certified radiologists. A subset of discordant cases underwent post hoc computed tomography review for exploratory analysis.

Results

AI achieved 74.5% sensitivity (95% CI 0.708-0.780), 93.3% specificity (95% CI 0.930-0.937), 24.2% positive predictive value, and 99.2% negative predictive value. Median inference time was 10.6 seconds versus 3.3 hours for radiologist reports (paired Wilcoxon signed-rank test W =112 987.5, P

Subjects

MeSH terms (MEDLINE)

Artificial IntelligenceRib FracturesRadiography, ThoracicHumansFeasibility StudiesProspective StudiesMaleFemaleMiddle AgedEmergency Service, HospitalSensitivity and SpecificityAdultAged

Author keywords

artificial intelligencechest radiographclinical decision supportdigital healthemergency radiologyfaster R-CNNfeasibility studyreal-world datarib fracture

Authors and institutions

  • Department of Emergency Medicine, Mackay Memorial Hospital, Taipei, Taiwan.
  • Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, 9F, Education & Research Building, Shuang-Ho Campus, No. 301, Yuantong Rd., Zhonghe Dist., New Taipei C…
  • College of Medicine, Mackay Medical University, New Taipei City, Taiwan.
  • Division of Plastic Surgery, Mackay Memorial Hospital, Taipei, Taiwan.
  • Clinical Big Data Research, Taipei Medical University Hospital, Taipei City, Taiwan.

ORCID profiles: Shu-Tien Huang, Liong-Rung Liu, Ming-Feng Tsai, Ming-Yuan Huang, Hung-Wen Chiu

Cite

APA

Huang, S. T., Liu, L. R., Tsai, M. F., Huang, M. Y., & Chiu, H. W. (2026). Prospective Diagnostic Accuracy and Technical Feasibility of Artificial Intelligence-Assisted Rib Fracture Detection on Chest Radiographs: Observational Study. JMIR Medical Informatics. https://doi.org/10.2196/77965

Vancouver

Huang ST, Liu LR, Tsai MF, Huang MY, Chiu HW. Prospective Diagnostic Accuracy and Technical Feasibility of Artificial Intelligence-Assisted Rib Fracture Detection on Chest Radiographs: Observational Study. JMIR Medical Informatics. 2026. doi:10.2196/77965

BibTeX
@article{Huang2026,
  author = {Huang, Shu-Tien and Liu, Liong-Rung and Tsai, Ming-Feng and Huang, Ming-Yuan and Chiu, Hung-Wen},
  title = {Prospective Diagnostic Accuracy and Technical Feasibility of Artificial Intelligence-Assisted Rib Fracture Detection on Chest Radiographs: Observational Study},
  journal = {JMIR Medical Informatics},
  year = {2026},
  doi = {10.2196/77965}
}
Start for free →