Back to all papers

Minimizing Missed Diagnoses of Tibial Plateau Fractures: The Role of AI in Radiographic Evaluation.

February 18, 2026pubmed logopapers

Authors

Chen MZ,Chen YP,Hung YC,Huang YJ,Fan TY,Liu HL,Yang CP,Chang SS,Kuo CF,James Chu CC,Chan YS

Affiliations (8)

  • Department of Orthopedic Surgery, Linkou Chang Gung Memorial Hospital, Taoyuan City, Taiwan.
  • Center for Artificial Intelligence in Medicine, Chang Gung Memorial Hospital, Linkou, Taoyuan City, Taiwan.
  • Master of Science Degree Program in Innovation for Smart Medicine, Chang Gung University, Taoyuan City, Taiwan.
  • Technology R&D Department, Chang Gung Medical Technology Co., Taoyuan City, Taiwan.
  • Department of Research and Development, Chang Gung Medical Technology Co., Taoyuan City, Taiwan.
  • Division of Rheumatology, Allergy and Immunology, Chang Gung Memorial Hospital, Linkou, Taoyuan City, Taiwan.
  • College of Medicine, Chang Gung University, Taoyuan City, Taiwan.
  • Department of Orthopedic Surgery, Keelung Chang Gung Memorial Hospital, Keelung City, Taiwan.

Abstract

Tibial plateau fractures represent a diverse group of intra-articular injuries that can be difficult to detect and characterize on initial imaging. The aim of the present study was to develop an artificial intelligence (AI) diagnostic tool for identifying tibial plateau fractures on radiographs. In this retrospective study, we analyzed radiographs that had been made from January 2018 to December 2020 for 1,809 patients, with an equal distribution of male and female adults. A total of 3,821 anteroposterior and lateral knee radiographs were evaluated with use of the EfficientNet B3 AI model, with computed tomography (CT) images being used as the ground truth. Evaluation metrics focused on the area under the receiver operating characteristic curve (AUC) and positive predictive values across different subgroups. Our AI model attained AUCs of 0.98 and 0.97 for detecting tibial plateau fractures in the test and external validation datasets, respectively. Subgroup analysis revealed diverse positive predictive values across different Schatzker types and 3-column classifications. Our deep learning model exhibits newfound ability for identifying tibial plateau fractures. However, we encountered several limitations, such as imbalances among the sizes of various subgroups in the dataset and an inability to identify radiographs containing foreign objects or other defects. Diagnostic Level III. See Instructions for Authors for a complete description of levels of evidence.

Topics

Tibial FracturesArtificial IntelligenceMissed DiagnosisJournal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.