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

Safeguarding AI-driven digital health - An adaptation of the Swiss cheese model for safety.

Digital health·2026
Same author

Large Language Model-Based Classification of Case Report Abstracts: A Pilot Study on Interactions Between Radiotherapy and Systemic Therapies.

JCO clinical cancer informatics·2026
Same author

Rare Appearance of a Primary Hepatic Angiosarcoma of the Intrahepatic Portal Veins.

RoFo : Fortschritte auf dem Gebiete der Rontgenstrahlen und der Nuklearmedizin·2026
Same author

Performance Evaluation of Large Language Models in Multilingual Medical Multiple-Choice Questions: Mixed Methods Study.

JMIR medical education·2026
Same author

Feasibility and usability of a ChatGPT-based app to support physical activity: A pilot study.

Digital health·2026
Same author

Large Language Models for Supporting Clear Writing and Detecting Spin in Randomized Controlled Trials in Oncology: Comparative Analysis of GPT Models and Prompts.

JMIR cancer·2026
Same journal

Correction: Confidence Measurement Metrics in Multimodal Large Language Models for Ultrasound-Based Radiology Cases: Comparative Evaluation Study of Self-Reported, Consistency-Based, and Hybrid Methods.

Journal of medical Internet research·2026
Same journal

Centering Equity During Health Technology Innovation: Scoping Review of Methods and Research Adjustments to Promote Inclusive Coproduction.

Journal of medical Internet research·2026
Same journal

Comparative Effectiveness of AI-Assisted Telerehabilitation, Telerehabilitation, In-Person Care, and Usual Care for Chronic Nonspecific Low Back Pain: Bayesian Network Meta-Analysis.

Journal of medical Internet research·2026
Same journal

Effectiveness of WeChat Public Account Intervention Based on the Information-Motivation-Behavioral Skills Model Among College Students With Internet Addiction: Randomized Controlled Trial.

Journal of medical Internet research·2026
Same journal

Are Traditional Registries Becoming Obsolete in the Modern Digital Health Ecosystem?

Journal of medical Internet research·2026
Same journal

Detecting and Preventing Fraudulent Participation in Qualitative Research: Content Analysis of Two Multisite Studies.

Journal of medical Internet research·2026
See all related articles

Related Experiment Video

Updated: May 13, 2025

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
07:50

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

15.7K

Enhancing Bidirectional Encoder Representations From Transformers (BERT) With Frame Semantics to Extract Clinically

Daniel Reichenpfader1,2, Jonas Knupp3, Sandro Urs von Däniken4

  • 1Institute for Patient-Centered Digital Health, School of Engineering and Computer Science, Bern University of Applied Sciences, Biel/Bienne, Switzerland.

Journal of Medical Internet Research
|April 25, 2025
PubMed
Summary
This summary is machine-generated.

This study combines Bidirectional Encoder Representations from Transformers (BERT) with frame semantics to extract structured data from mammography reports, achieving high precision and enabling efficient, private deployment.

Keywords:
annotationinformation extractionlarge language modelsmammographynatural language processingquality controlradiologystructured reportingtemplate filling

More Related Videos

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

42.6K
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

463

Related Experiment Videos

Last Updated: May 13, 2025

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
07:50

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

15.7K
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

42.6K
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

463

Area of Science:

  • Natural Language Processing
  • Computational Linguistics
  • Medical Informatics

Background:

  • Structured reporting enhances clarity in radiology but faces low adoption due to free-text variability.
  • Manual structuring is time-consuming and inconsistent.
  • Large language models show promise for clinical data extraction but have limitations in domain adaptation and privacy.

Purpose of the Study:

  • To explore the integration of Bidirectional Encoder Representations from Transformers (BERT) and frame semantics for extracting and normalizing information from free-text mammography reports.
  • To develop and evaluate a novel information extraction pipeline for radiological reports.

Main Methods:

  • Fine-tuning BERT models on an annotated corpus of 210 German mammography reports.
  • Developing a fact extraction pipeline using extractive question-answering and sequence labeling models.
  • Quantitative evaluation using perplexity, SQuAD 2.0, and seqeval metrics, alongside qualitative clinician evaluation and comparison with generative models.

Main Results:

  • The system successfully extracts 14 fact types and 40 entities from mammography reports.
  • Achieved average F1-scores of 90.4% for question answering and 81% for sequence labeling.
  • Qualitative evaluation demonstrated high precision (96.1% for facts, 99.6% for entities) compared to generative approaches.

Conclusions:

  • Frame semantics offers a robust framework for automating structured reporting in radiology.
  • The BERT-based approach enables customizable, generalizable, and privacy-preserving information extraction.
  • Further validation across diverse datasets and report types is recommended for broader clinical applicability.