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

Chain-of-verification prompting for NIH stroke scale extraction using small and frontier large language models.

International journal of medical informatics·2026
Same author

A selective deep learning framework for pressure injury staging with calibrated confidence and automated clinical documentation.

Intensive & critical care nursing·2026
Same author

Prompt-Induced Diagnostic Bias in Large Language Model Classification of Echocardiography Reports.

The American journal of cardiology·2026
Same author

Salvage surgery for residual and recurrent head and neck squamous cell carcinoma (RESCUE): An IReC multicentre consecutive cohort study.

Oral oncology·2026
Same author

Automated auditing of emergency department documentation using large language models.

The American journal of emergency medicine·2026
Same author

Identification of Pancreatic Neuroendocrine Tumor During Evaluation for Severe Valvulopathy in a Patient With a History of Lung Carcinoid Tumor: A Case Report.

Cureus·2026

Related Experiment Video

Updated: May 15, 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

466

Prompt Engineering for Large Language Models in Interventional Radiology.

Nicholas Dietrich1, Nicholas C Bradbury2, Christopher Loh2

  • 1Temerty Faculty of Medicine, University of Toronto, 1 King's College Cir, Toronto, ON M5S 1A8, Canada.

AJR. American Journal of Roentgenology
|May 7, 2025
PubMed
Summary
This summary is machine-generated.

Prompt engineering optimizes artificial intelligence (AI) and large language models (LLM) for interventional radiology (IR). This guide details techniques and best practices for effective clinical application and future advancements.

Keywords:
AIartificial intelligenceeducationgenerative AIinterventional radiologylarge language modelsprompt engineering

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

2.7K
PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator
10:48

PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator

Published on: December 28, 2017

9.4K

Related Experiment Videos

Last Updated: May 15, 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

466
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

2.7K
PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator
10:48

PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator

Published on: December 28, 2017

9.4K

Area of Science:

  • Artificial Intelligence in Medicine
  • Clinical Applications of Large Language Models
  • Interventional Radiology Workflow Optimization

Background:

  • Prompt engineering is vital for enhancing AI and LLM performance, particularly in high-stakes medical fields.
  • Precision and reliability in AI outputs are critical for safe and effective clinical decision-making.
  • Interventional radiology (IR) can benefit from structured AI inputs for improved practice.

Purpose of the Study:

  • To provide an overview of prompt engineering techniques relevant to interventional radiology.
  • To demonstrate practical applications of various prompting strategies in an IR context.
  • To discuss challenges and future directions for generative AI in clinical IR.

Main Methods:

  • Exploration of key prompt engineering strategies: zero-shot, few-shot, chain-of-thought, tree-of-thought, self-consistency, and directional stimulus prompting.
  • Illustration of techniques with IR-specific examples for workplace and clinical integration.
  • Discussion of best practices for prompt design and analysis of clinical generative AI challenges.

Main Results:

  • Demonstrated applicability of diverse prompt engineering techniques to IR tasks.
  • Provided practical examples for structuring prompts in clinical and workplace settings.
  • Identified key challenges including data privacy and regulatory considerations for generative AI in IR.

Conclusions:

  • Effective prompt engineering is essential for leveraging AI and LLMs in interventional radiology.
  • Future advancements like retrieval-augmented generation and multimodal models promise further integration.
  • Addressing challenges is crucial for the responsible and successful adoption of generative AI in IR.