Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Adapting transformer-based encoder models for automated billing code assignment of current procedural terminology from pathology reports in multi-institutional settings.

Journal of pathology informatics·2026
Same author

Guideline-concordant cefazolin prophylaxis in penicillin allergy labeled arthroplasty patients: Progress and persistent barriers.

Journal of clinical orthopaedics and trauma·2026
Same author

GelMA Hydrogel Stiffness Modulates IL-6- and BMP-2-Induced Immune Dysregulation in Human Mesenchymal Stem Cells.

Biomedicines·2026
Same author

Talus Fracture-Dislocations With Talar Body Extrusion Have High Complication Rates, With Uneventful Outcomes in a Minority of Patients After Open Reduction Internal Fixation.

Foot & ankle orthopaedics·2026
Same author

The Association Between Diagnosed Cannabis Use Disorder and Post-Operative Outcomes in Lower Extremity Trauma Patients: A Retrospective Database Review.

Journal of orthopaedic experience & innovation·2026
Same author

Incidence and surgical management of secondary spine infections: A retrospective case series study of 4,921 consecutive patients.

Journal of clinical orthopaedics and trauma·2026

Related Experiment Video

Updated: Jan 17, 2026

Anterior Cruciate Ligament Transection and Synovial Fluid Lavage in a Rodent Model to Study Joint Inflammation and Posttraumatic Osteoarthritis
06:28

Anterior Cruciate Ligament Transection and Synovial Fluid Lavage in a Rodent Model to Study Joint Inflammation and Posttraumatic Osteoarthritis

Published on: September 2, 2025

1.1K

Assessing Inter-rater Reliability of ChatGPT-4 and Orthopaedic Clinicians in Radiographic Fracture Classification.

Aliyah N Walker1, J B Smith2, Samuel K Simister2

  • 1University of California, Davis School of Medicine, Sacramento, CA, USA.

Journal of Orthopaedic Trauma
|September 19, 2025
PubMed
Summary

ChatGPT-4 shows promise in classifying basic fracture features on radiographs, achieving substantial agreement on location and fracture type. However, it is not yet comparable to expert clinicians, especially for complex classifications, suggesting AI should be an adjunct tool.

Keywords:
Artificial IntelligenceChatGPTFracture ClassificationMedical Imaging

More Related Videos

Assessment of Bone Fracture Healing Using Micro-Computed Tomography
12:04

Assessment of Bone Fracture Healing Using Micro-Computed Tomography

Published on: December 9, 2022

2.4K
A Method to Estimate Cadaveric Femur Cortical Strains During Fracture Testing Using Digital Image Correlation
09:34

A Method to Estimate Cadaveric Femur Cortical Strains During Fracture Testing Using Digital Image Correlation

Published on: September 14, 2017

7.8K

Related Experiment Videos

Last Updated: Jan 17, 2026

Anterior Cruciate Ligament Transection and Synovial Fluid Lavage in a Rodent Model to Study Joint Inflammation and Posttraumatic Osteoarthritis
06:28

Anterior Cruciate Ligament Transection and Synovial Fluid Lavage in a Rodent Model to Study Joint Inflammation and Posttraumatic Osteoarthritis

Published on: September 2, 2025

1.1K
Assessment of Bone Fracture Healing Using Micro-Computed Tomography
12:04

Assessment of Bone Fracture Healing Using Micro-Computed Tomography

Published on: December 9, 2022

2.4K
A Method to Estimate Cadaveric Femur Cortical Strains During Fracture Testing Using Digital Image Correlation
09:34

A Method to Estimate Cadaveric Femur Cortical Strains During Fracture Testing Using Digital Image Correlation

Published on: September 14, 2017

7.8K

Area of Science:

  • Orthopaedic Surgery
  • Artificial Intelligence in Medicine
  • Radiographic Fracture Classification

Background:

  • Artificial intelligence (AI) is increasingly explored for medical image analysis.
  • Evaluating AI's performance against human experts is crucial for clinical integration.
  • Fracture classification accuracy is vital for effective orthopaedic treatment planning.

Purpose of the Study:

  • To compare the inter-rater reliability of ChatGPT-4 with orthopaedic surgery attendings and residents.
  • To assess ChatGPT-4's accuracy in classifying fractures on upper extremity (UE) and lower extremity (LE) radiographs.
  • To determine AI's potential role in radiographic fracture assessment.

Main Methods:

  • 84 radiographs with various fracture patterns were analyzed.
  • ChatGPT-4 and human raters (orthopaedic residents and attendings) independently classified view, location, fracture type, and AO/OTA classification.
  • Fleiss' Kappa values were calculated to measure inter-rater reliability across different rater groups (AI vs. Residents, AI vs. Attendings, Attendings vs. Residents).

Main Results:

  • ChatGPT-4 demonstrated substantial to almost perfect agreement with clinicians for fracture location and type.
  • Agreement was fair for radiographic view and slight to moderate for AO/OTA classification.
  • Human raters (Attendings vs. Residents) showed almost perfect agreement for location and fracture type, and moderate agreement for AO/OTA classification.

Conclusions:

  • ChatGPT-4 shows potential for classifying basic fracture characteristics but does not yet match expert clinician performance for nuanced interpretations.
  • AI is best utilized as a supplementary tool to aid, not replace, the diagnostic judgment of trained orthopaedic surgeons.
  • Further development is needed to enhance AI's capabilities in complex fracture classification.