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

Imaging Studies for Cardiovascular System I:Echocardiography01:17

Imaging Studies for Cardiovascular System I:Echocardiography

280
Cardiac imaging studies encompass a wide range of noninvasive and minimally invasive techniques designed to visualize the heart's structure and function in detail. One such technique is echocardiography, which uses high-frequency ultrasound waves to produce detailed images of the heart, known as echocardiograms.
Indications: Echocardiography is utilized to diagnose heart failure, valve disorders, and myocardial infarction. It also assesses cardiac structures' size, shape, and motion,...
280
Imaging Studies for Cardiovascular System II:Types of Echocardiography01:20

Imaging Studies for Cardiovascular System II:Types of Echocardiography

215
Echocardiography plays a role in assessing cardiac health and detecting heart conditions, with various types providing critical insights for diagnosis and treatment.
Types of Echocardiography
Transthoracic Echocardiography (TTE)
TTE is the most common type of echocardiogram which involves placing a transducer on the patient's chest, emitting sound waves to create heart images. TTE is invaluable for evaluating the heart's size, structure, and motion, making it particularly useful for...
215

You might also read

Related Articles

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

Sort by
Same author

Sex differences in documented clinical features of memory clinic patients: a natural language processing study.

Cerebral circulation - cognition and behavior·2026
Same author

Liver enzyme alterations during pregnancy in IBD are not attributable to disease activity or medication.

Scandinavian journal of gastroenterology·2026
Same author

How long is long enough? Timing of pre-conceptional remission predicts relapse risk during pregnancy in IBD.

Journal of Crohn's & colitis·2025
Same author

MyDigiTwin: A privacy-preserving framework for personalized cardiovascular risk prediction and scenario exploration.

Computers in biology and medicine·2025
Same author

Long-Term Routine Laboratory Toxicity Monitoring of Immunomodulatory Drugs in Rheumatoid Arthritis : A Retrospective Cohort Study.

Annals of internal medicine·2025
Same author

[Large language models in healthcare].

Nederlands tijdschrift voor geneeskunde·2025

Related Experiment Video

Updated: May 24, 2025

Evaluation of Left Ventricular Structure and Function using 3D Echocardiography
06:34

Evaluation of Left Ventricular Structure and Function using 3D Echocardiography

Published on: October 28, 2020

3.8K

Diagnosis extraction from unstructured Dutch echocardiogram reports using span- and document-level characteristic

Bauke Arends1, Melle Vessies2, Dirk van Osch2

  • 1Department of Cardiology, University Medical Center Utrecht, Utrecht, The Netherlands. b.k.o.arends-4@umcutrecht.nl.

BMC Medical Informatics and Decision Making
|March 6, 2025
PubMed
Summary

Automated extraction of diagnoses from Dutch echocardiogram reports is feasible using advanced machine learning models like SpanCategorizer and MedRoBERTa.nl. These tools significantly reduce manual effort, improving efficiency in clinical research and decision support.

Keywords:
Clinical natural language processingDocument classificationEchocardiogramEntity classificationSpan classification

More Related Videos

Ultrasonic Assessment of Myocardial Microstructure
10:53

Ultrasonic Assessment of Myocardial Microstructure

Published on: January 14, 2014

5.4K
Morphological and Functional Assessment of the Right Ventricle Using 3D Echocardiography
07:11

Morphological and Functional Assessment of the Right Ventricle Using 3D Echocardiography

Published on: October 28, 2020

2.8K

Related Experiment Videos

Last Updated: May 24, 2025

Evaluation of Left Ventricular Structure and Function using 3D Echocardiography
06:34

Evaluation of Left Ventricular Structure and Function using 3D Echocardiography

Published on: October 28, 2020

3.8K
Ultrasonic Assessment of Myocardial Microstructure
10:53

Ultrasonic Assessment of Myocardial Microstructure

Published on: January 14, 2014

5.4K
Morphological and Functional Assessment of the Right Ventricle Using 3D Echocardiography
07:11

Morphological and Functional Assessment of the Right Ventricle Using 3D Echocardiography

Published on: October 28, 2020

2.8K

Area of Science:

  • Medical Informatics
  • Natural Language Processing
  • Cardiology

Background:

  • Clinical machine learning and AI decision support require accurate labels.
  • Manual label extraction from clinical reports is time-consuming and costly.
  • This study evaluates automatic diagnosis extraction from Dutch echocardiogram reports.

Purpose of the Study:

  • To assess the feasibility of automatic span- and document-level diagnosis extraction.
  • To compare the performance of various automated labeling techniques.
  • To identify optimal models for clinical report analysis.

Main Methods:

  • Utilized 115,692 Dutch echocardiogram reports.
  • Manually annotated a subset for cardiac characteristics.
  • Developed and evaluated span and document-level labeling models (SpanCategorizer, MedRoBERTa.nl, SetFit).
  • Performance measured using weighted and macro F1-score, precision, and recall.

Main Results:

  • SpanCategorizer and MedRoBERTa.nl demonstrated superior performance for span and document classification, respectively.
  • Weighted F1-scores ranged from 0.60-0.93 (SpanCategorizer) and 0.96-0.98 (MedRoBERTa.nl).
  • Direct document classification outperformed indirect methods; SetFit showed promise with limited data.

Conclusions:

  • Recommends SpanCategorizer and MedRoBERTa.nl for diagnosis extraction from Dutch echocardiograms.
  • Suggests SetFit as an alternative for document classification with limited training data.
  • Proposes future research on RoBERTa-based span classifiers and English model translation.