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: May 18, 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

Automated Analysis of Radiation Oncology Incident Reports Using Large Language Models: A Multi-Institutional

Nathan Dobranski1, Natalie N Viscariello2, Garrett M Pitcher3

  • 1Department of Physics and Astronomy, Louisiana State University, Baton Rouge, Louisiana.

International Journal of Radiation Oncology, Biology, Physics
|May 16, 2026
PubMed
Summary

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

Multi-TPS institutional surveillance of VMAT plan complexity and PSQA results over three years.

Journal of applied clinical medical physics·2026
Same author

A Dosimetric Comparison of the Accumulated Dose in Prostate SBRT for Non-Adaptive and Adaptive External Beam Radiotherapy.

Cancers·2026
Same author

Evaluation of Two Commercial Artificial Intelligence Segmentation Systems for Radiation Therapy.

Journal of medical physics·2026
Same author

Developing a web-based dashboard for adaptive radiotherapy workflows.

Journal of applied clinical medical physics·2026
Same author

Dosimetric impact of density overrides on treatment planning for prostate MR-guided adaptive radiotherapy.

Medical dosimetry : official journal of the American Association of Medical Dosimetrists·2026
Same author

Phantom-based assessment of a modified 4D-MRI protocol for abdominal tumor motion tracking: Effects of sequence parameters and modality comparison.

Journal of applied clinical medical physics·2025

Large language models (LLMs) show technical feasibility for automating patient safety incident analysis in radiation oncology. This advancement promises more efficient and consistent reporting across cancer centers.

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Healthcare
  • Radiation Oncology Patient Safety

Background:

  • Radiation oncology incident reporting requires time-intensive expert analysis, leading to variability.
  • Automating this process with AI can enhance efficiency and consistency.

Purpose of the Study:

  • To evaluate the technical feasibility of using locally deployed large language models (LLMs) for automating radiation oncology incident report analysis.
  • To assess LLM performance in summarization and taxonomy assignment across multiple cancer centers.

Main Methods:

  • Developed a locally deployed LLM system for automated incident report summarization and taxonomy assignment.
  • Processed 600 Radiation Oncology Incident Learning System (RO-ILS) reports from two anonymized cancer centers.

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Related Experiment Videos

Last Updated: May 18, 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

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

  • Compared performance of different LLM models and prompt engineering techniques across two rounds of evaluation.

    • Main Results:

    • Statistically significant performance improvements were observed between evaluation rounds across both institutions.
    • Institution 1 showed substantial gains in summary (3.34 to 4.20) and tag (3.28 to 4.32) scores.
    • Institution 2 also demonstrated improvements, with tag scores reaching 4.40. Round 2 achieved high-performance thresholds (≥4) of 80.0% for summaries and 86.7% for tags at Institution 1.

    Conclusions:

    • Locally deployed LLMs are technically feasible for automating radiation oncology incident analysis.
    • Performance improvements suggest potential for AI in enhancing patient safety reporting.
    • Institutional variations highlight the need for site-specific optimization and further investigation.