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: Jun 20, 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

RadAnnotate: Large Language Models for Efficient and Reliable Radiology Report Annotation.

Saisha Pradeep Shetty1, Roger Eric Goldman2, Vladimir Filkov1

  • 1Department of Computer Science, University of California, Davis, CA, USA.

AMIA Joint Summits on Translational Science Proceedings. AMIA Joint Summits on Translational Science
|June 19, 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

Intelligent documentation in medical education: can AI replace manual case logging?

JAMIA open·2026
Same author

The impact of the Social Exposome in Cardiovascular Health and Disease.

Journal of precision medicine (Amsterdam, Netherlands)·2026
Same author

Natural language processing of biomedical text to map and prioritize protein-disease associations in HFpEF.

Computers in biology and medicine·2026
Same author

Contrast-enhanced CT as a non-invasive alternative for lung shunt fraction estimation in hepatic transarterial radioembolization.

Radiology advances·2025
Same author

Deep Learning Models for Automatic Classification of Anatomic Location in Abdominopelvic Digital Subtraction Angiography.

Journal of imaging informatics in medicine·2025
Same author

Mental health care needs of caregivers of people with Alzheimer's disease from online forum analysis.

Npj mental health research·2024
Same journal

LabSage: Structural-Semantic Decoupling for Enhanced Retrieval-Augmented Generation in Clinical Laboratories.

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science·2026
Same journal

Evaluating Representation Embeddings from LLMs and Time-Series Foundation Models for Wearable Accelerometer-Based Health Prediction.

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science·2026
Same journal

ClinNoteAgents: An LLM Multi-Agent System for Predicting and Interpreting Heart Failure 30-Day Readmission from Clinical Notes.

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science·2026
Same journal

Mapping the Storm: Linking Tornado Paths to Emergency Room Surges Through Geocoded Patient Data.

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science·2026
Same journal

Multi-Modal Deep Learning-Based Model to Predict Burkitt Lymphoma Recurrence.

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science·2026
Same journal

A Multi-Model LLM Consensus Framework to Identify EHR-Predictable Eligibility Criteria in NSCLC Immunotherapy Trials.

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science·2026
See all related articles

This study introduces RadAnnotate, an LLM framework reducing manual radiology report annotation effort. Retrieval-augmented synthetic reports and selective automation significantly improve entity labeling accuracy, especially for uncertain observations.

Area of Science:

  • Natural Language Processing (NLP)
  • Medical Informatics
  • Artificial Intelligence (AI)

Background:

  • Manual radiology report annotation is crucial for clinical Natural Language Processing (NLP) but is time-consuming and expensive.
  • Existing methods struggle with the nuances of complex medical terminology and uncertain observations.

Purpose of the Study:

  • To develop and evaluate RadAnnotate, a Large Language Model (LLM)-based framework to decrease expert effort in radiology report annotation.
  • To investigate the efficacy of retrieval-augmented generation (RAG) synthetic reports and confidence-based selective automation for entity labeling.

Main Methods:

  • Trained entity-specific classifiers on gold-standard radiology reports to identify strengths and weaknesses.
  • Generated retrieval-augmented synthetic reports to augment training data, particularly for challenging observations.

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: Jun 20, 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

  • Implemented confidence-based selective automation to identify reports for expert review.

    • Main Results:

    • Synthetic-only models achieved performance within 1-2 F1 points of gold-trained models.
    • Synthetic augmentation improved F1 scores for uncertain observations from 0.61 to 0.70 in low-resource settings.
    • RadAnnotate automatically annotated 55-90% of reports with 0.86-0.92 entity match score.

    Conclusions:

    • LLM-based RadAnnotate effectively reduces expert annotation effort for radiology reports.
    • Retrieval-augmented synthetic data generation is a promising strategy for improving NLP model performance, especially for rare or uncertain findings.
    • Confidence-based automation enables efficient and accurate entity labeling in clinical NLP pipelines.