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 Experiment Video

Updated: Apr 25, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.3K

Analysis of AI-Generated Radiography Responses Using a Closed-System LLM.

Kevin R Clark

    Radiologic Technology
    |April 23, 2026
    PubMed
    Summary
    This summary is machine-generated.

    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

    Verifying Outputs in Scopus AI to Promote Critical AI Literacy in Education and Research.

    Radiologic technology·2026
    Same author

    A Practical Guide for Using Generative AI in Academic Research.

    Radiologic technology·2026
    Same author

    Comment on Comparative Analysis of LLMs' Performance on a Practice Radiography Certification Exam.

    Radiologic technology·2026
    Same author

    Emerging Medical Imaging Technologies and Educational Approaches.

    Radiologic technology·2026
    Same author

    Limitations of Tools for Detecting the Use of AI in Student-Written Papers.

    Radiologic technology·2025
    Same author

    Comparative Analysis of LLMs' Performance On a Practice Radiography Certification Exam.

    Radiologic technology·2025
    Same journal

    An Intentional and Ethical Integration of AI in Medical Imaging.

    Radiologic technology·2026
    Same journal

    Benefits of Integrating AI Into Computer-Aided Detection Systems.

    Radiologic technology·2026
    Same journal

    Using Artificial Intelligence to Enhance Analysis of Chest Computed Tomography.

    Radiologic technology·2026
    Same journal

    A Practice-Aligned Approach to Integrating AI in Radiation Sciences Education.

    Radiologic technology·2026
    Same journal

    Site Visitors: The Unsung Heroes of the Accreditation Process.

    Radiologic technology·2026
    Same journal

    Extended Reality Innovations in Medical Imaging Education.

    Radiologic technology·2026
    See all related articles

    Microsoft Copilot shows potential as a radiography study aid, but experts found its responses sometimes inaccurate or outdated. Critical evaluation is essential for safe use in radiologic science education.

    Area of Science:

    • Radiologic Science Education
    • Artificial Intelligence in Healthcare

    Background:

    • Artificial intelligence (AI) tools are increasingly explored for educational support.
    • Microsoft Copilot (GPT-4) offers potential assistance in radiography learning.

    Purpose of the Study:

    • To assess the accuracy and educational value of Microsoft Copilot's radiography responses.
    • To identify strengths, limitations, and implications for radiologic science education.

    Main Methods:

    • Qualitative descriptive study evaluating Copilot's responses to 15 radiography exam questions.
    • Seven subject matter experts assessed AI-generated content for accuracy and utility.
    • Thematic analysis of expert feedback using a 6-phase framework.

    Main Results:

    Keywords:
    critical AI literacylarge language modelsqualitative analysisradiography educationsubject matter expertsMicrosoft Copilot

    Related Experiment Videos

    Last Updated: Apr 25, 2026

    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
    03:14

    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

    Published on: December 6, 2024

    1.3K
    • Experts noted Copilot's clarity and organizational strengths as a supplemental study aid.
    • Concerns included incomplete content, outdated terminology, scope of practice issues, and lack of sourcing.
    • AI responses sometimes lacked specificity and sufficient clinical context.

    Conclusions:

    • Copilot can offer structured support but requires critical appraisal due to potential inaccuracies.
    • AI literacy skills are crucial for radiography students to evaluate AI outputs.
    • Further research needed on AI platform comparison and safe integration into health professions education.