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

Referral patterns and wait times in complex peripheral nerve injuries: a review of a multidisciplinary clinic in Canada.

Canadian journal of surgery. Journal canadien de chirurgie·2026
Same author

Impact of Facial Paralysis on Oral Health: A Systematic Review.

Facial plastic surgery & aesthetic medicine·2026
Same author

Is Higher Surgeon Volume Associated With Lower Complication and Revision Risk After Distal Radius Fracture Surgery? A Population-based Cohort Study of 13,389 Patients.

Clinical orthopaedics and related research·2026
Same author

Predictors of Facial Synkinesis Severity.

Plastic and reconstructive surgery·2026
Same author

Isolated single-digit clubbing as a clinical sign of benign distal phalanx tumors.

Hand surgery & rehabilitation·2026
Same author

Approche de la douleur chronique au poignet chez les adultes: Revue des pathologies courantes à l'intention des praticiens des soins primaires.

Canadian family physician Medecin de famille canadien·2026

Related Experiment Video

Updated: Mar 19, 2026

Development of a Novel Internal Fixation Model for Rat Radial Fractures: Fracture Healing Assessment and Dorsal Root Ganglion Isolation
11:21

Development of a Novel Internal Fixation Model for Rat Radial Fractures: Fracture Healing Assessment and Dorsal Root Ganglion Isolation

Published on: March 13, 2026

75

Evaluating Generative Artificial Intelligence Models' Responses to Questions About Scaphoid Fracture and Scaphoid

Armaan Dhanoa1, Ann-Sophie Lafreniere2, Carl M Harper3

  • 1Temerty Faculty of Medicine, University of Toronto, Toronto, ON, Canada.

Journal of Hand Surgery Global Online
|March 18, 2026
PubMed
Summary

ChatGPT and Google Gemini show potential for patient care regarding scaphoid fractures and nonunion. However, neither AI platform effectively replicates a clinician interaction, indicating a need for improvement in AI

Keywords:
AIChatGPTGoogle GeminiNonunionScaphoid

More Related Videos

A Simple Critical-sized Femoral Defect Model in Mice
09:41

A Simple Critical-sized Femoral Defect Model in Mice

Published on: March 15, 2015

15.9K
The Generation of Closed Femoral Fractures in Mice: A Model to Study Bone Healing
05:53

The Generation of Closed Femoral Fractures in Mice: A Model to Study Bone Healing

Published on: August 16, 2018

16.4K

Related Experiment Videos

Last Updated: Mar 19, 2026

Development of a Novel Internal Fixation Model for Rat Radial Fractures: Fracture Healing Assessment and Dorsal Root Ganglion Isolation
11:21

Development of a Novel Internal Fixation Model for Rat Radial Fractures: Fracture Healing Assessment and Dorsal Root Ganglion Isolation

Published on: March 13, 2026

75
A Simple Critical-sized Femoral Defect Model in Mice
09:41

A Simple Critical-sized Femoral Defect Model in Mice

Published on: March 15, 2015

15.9K
The Generation of Closed Femoral Fractures in Mice: A Model to Study Bone Healing
05:53

The Generation of Closed Femoral Fractures in Mice: A Model to Study Bone Healing

Published on: August 16, 2018

16.4K

Area of Science:

  • Orthopedic Surgery
  • Artificial Intelligence in Medicine
  • Medical Informatics

Background:

  • Scaphoid fractures and nonunion are common orthopedic injuries requiring accurate patient information.
  • Large language models (LLMs) like ChatGPT and Google Gemini are increasingly used for health information retrieval.
  • Evaluating the clinical utility of LLMs for specific orthopedic conditions is crucial.

Purpose of the Study:

  • To compare the responses of ChatGPT and Google Gemini to patient questions on scaphoid fracture and nonunion.
  • To assess response quality based on accuracy, clarity, and clinician comparability.
  • To evaluate differences in AI responses based on question complexity and surgical specialty (orthopedic vs. plastic hand surgeons).

Main Methods:

  • Developed 30 patient questions on scaphoid fracture/nonunion, categorized by Depth of Knowledge (DOK) levels 1-4.
  • Input questions into ChatGPT-4o and Google Gemini 2.0 Flash.
  • Evaluated responses using a Likert scale (1-5) across four domains: accuracy, clarity, AI metric, and clinician comparability, by six hand surgeons.

Main Results:

  • No significant differences in overall scores between ChatGPT and Google Gemini.
  • Plastic surgeons rated responses higher than orthopedic surgeons, particularly for ChatGPT.
  • Google Gemini excelled in DOK levels 2 and 3; ChatGPT offered greater clarity. Clinician comparability scores were low for both platforms.

Conclusions:

  • Both ChatGPT and Google Gemini demonstrate potential clinical utility for patient education on scaphoid conditions.
  • A significant limitation is the low comparability of AI responses to in-person clinician interactions.
  • Further development is needed to enhance the clinical applicability and patient-provider interaction simulation of AI models.