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

Positron Emission Tomography01:29

Positron Emission Tomography

4.3K
Positron emission tomography (PET) is a medical imaging technique involving radiopharmaceuticals — substances that emit short-lived radiation. Although the first PET scanner was introduced in 1961, it took 15 more years before radiopharmaceuticals were combined with the technique and revolutionized its potential.
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body...
4.3K
Radiation: Applications01:17

Radiation: Applications

1.2K
The average temperature of Earth is the subject of much current discussion. Earth is in radiative contact with both the Sun and dark space; it receives almost all its energy from the radiation of the Sun and reflects some of it into outer space. Dark space is very cold, about 3 K, so Earth radiates energy into it. For instance, heat transfer occurs from soil and grasses, the rate of which can be so rapid that frost can occur on clear summer evenings, even in warm latitudes.
The average...
1.2K

You might also read

Related Articles

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

Sort by
Same author

Research through Evaluation for Large Language Model in Patient-Clinician Communications.

Research square·2026
Same author

A Radiation Oncology Department Open House Improves Medical Students' Reported Familiarity With and Interest in the Specialty.

Cureus·2026
Same author

A prospective risk analysis for the clinical commissioning of a dose-driven continuous scanning proton therapy system.

Frontiers in oncology·2026
Same author

Noisy probing dose facilitated dose prediction for pencil beam scanning proton therapy: Physics enhances generalizability.

Medical physics·2026
Same author

Innovative Targets, New Technologies, Same Tenacity: Radiation Therapy's Evolving Role in Pancreatic Cancer.

International journal of radiation oncology, biology, physics·2026
Same author

Gaining New Ground: The Evolving Role of Radiation Therapy in Esophageal Cancer.

International journal of radiation oncology, biology, physics·2026

Related Experiment Video

Updated: Jul 20, 2025

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

623

Evaluating large language models on a highly-specialized topic, radiation oncology physics.

Jason Holmes1, Zhengliang Liu2, Lian Zhang1

  • 1Department of Radiation Oncology, Mayo Clinic, Phoenix, AZ, United States.

Frontiers in Oncology
|August 2, 2023
PubMed
Summary

Large Language Models (LLMs) show promise in radiation oncology physics. ChatGPT GPT-4 excelled, demonstrating potential as expert assistants, though human collaboration improved results.

Keywords:
ChatGPTartificial intelligencelarge language modelmedical physicsnatural language processing

More Related Videos

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform
07:57

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform

Published on: March 24, 2022

2.8K
Radiation Planning Assistant - A Streamlined, Fully Automated Radiotherapy Treatment Planning System
08:25

Radiation Planning Assistant - A Streamlined, Fully Automated Radiotherapy Treatment Planning System

Published on: April 11, 2018

15.3K

Related Experiment Videos

Last Updated: Jul 20, 2025

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

623
Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform
07:57

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform

Published on: March 24, 2022

2.8K
Radiation Planning Assistant - A Streamlined, Fully Automated Radiotherapy Treatment Planning System
08:25

Radiation Planning Assistant - A Streamlined, Fully Automated Radiotherapy Treatment Planning System

Published on: April 11, 2018

15.3K

Area of Science:

  • Medical Physics
  • Artificial Intelligence
  • Radiation Oncology

Background:

  • Assessing Large Language Models (LLMs) on standardized tests may not reflect their true capabilities.
  • Radiation oncology physics presents a specialized, relevant domain for LLM evaluation.

Purpose of the Study:

  • To evaluate the performance of LLMs in answering radiation oncology physics questions.
  • To establish a benchmark for LLM capabilities in a specialized scientific field.

Main Methods:

  • Developed a 100-question radiation oncology physics exam.
  • Evaluated four LLMs (ChatGPT GPT-3.5, ChatGPT GPT-4, Bard, BLOOMZ) against medical physicists and non-experts.
  • Assessed LLM deductive reasoning and collaborative potential.

Main Results:

  • ChatGPT GPT-4 outperformed other LLMs and human groups when prompted to explain answers first.
  • ChatGPT models demonstrated high response consistency; Bard did not.
  • ChatGPT GPT-4 showed emergent deductive reasoning capabilities.
  • Medical physicists significantly outperformed ChatGPT GPT-4 using a majority vote.

Conclusions:

  • LLMs, particularly ChatGPT GPT-4, show significant potential as assistants for radiation oncology experts.
  • Human collaboration, through majority voting, enhanced performance beyond individual LLM capabilities.