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

Improving Translational Accuracy02:07

Improving Translational Accuracy

2.5K
2.5K
MALDI-TOF Mass Spectrometry01:19

MALDI-TOF Mass Spectrometry

4.7K
Mass spectrometry is a powerful characterization technique that can identify and separate a wide variety of compounds ranging from chemical to biological entities, based on their mass-to-charge ratio (m/z). The instruments that allow this detection, known as mass spectrometers, have three components: an ion source, a mass analyzer, and a detector. These spectrometers differ based on the nature of their ion source and analyzers.
Matrix-assisted laser desorption ionization (MALDI) is a commonly...
4.7K

You might also read

Related Articles

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

Sort by
Same author

Improving Meditron for Medical Coding Through Fine-Tuning: A Comparative Evaluation Against GPT-4.

Studies in health technology and informatics·2026
Same author

Evaluating Differentially Private Synthetic Data for Multi-Site Clinical Research: A Case Study from 5 Swiss University Hospitals.

Studies in health technology and informatics·2026
Same author

Unequal Flows? Economic Dimensions of Sharing Anonymized Data in Biomedical Research.

Studies in health technology and informatics·2026
Same author

Correction: An End-to-End Natural Language Processing Application for Prediction of Medical Case Coding Complexity: Algorithm Development and Validation.

JMIR medical informatics·2026
Same author

[Towards improved sepsis management : AI as a tool for clinicians].

Revue medicale suisse·2026
Same author

[Artificial intelligence in nephrology : promises, challenges and perspectives].

Revue medicale suisse·2026

Related Experiment Video

Updated: Jun 15, 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

15.9K

Accelerating Clinical Text Annotation in Underrepresented Languages: A Case Study on Text De-Identification.

He A Xu1, Valentin Loftsson1, Bogdan Kulynych1

  • 1Biomedical Data Science Center, Lausanne University Hospital (CHUV) and Lausanne University, Lausanne, Switzerland.

Studies in Health Technology and Informatics
|August 23, 2024
PubMed
Summary
This summary is machine-generated.

Motivating annotators with contests and pre-annotations significantly speeds up Named Entity Recognition (NER) for clinical notes. This approach enhances annotation quality and enables high-performance text de-identification models.

Keywords:
Clinical NotesDe-identificationNLPName Entity Recognition

More Related Videos

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

525
Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
09:09

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

425

Related Experiment Videos

Last Updated: Jun 15, 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

15.9K
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

525
Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
09:09

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

425

Area of Science:

  • Natural Language Processing
  • Clinical Informatics
  • Machine Learning

Background:

  • Clinical notes are rich data sources for research and quality monitoring.
  • Named Entity Recognition (NER) structures unstructured clinical text but faces challenges due to limited specialized training data, especially in hospital settings.
  • Annotation costs and local specificities further complicate NER model development.

Purpose of the Study:

  • To investigate strategies for accelerating the annotation process in clinical NER.
  • To evaluate the impact of gamification (proactive contests) and pre-annotations on annotation efficiency and quality.
  • To develop a high-performance text de-identification model for French clinical notes.

Main Methods:

  • Implemented a proactive contest to motivate human annotators for a text de-identification task.
  • Provided pre-annotations for participants to assess their effect on annotation performance (recall and precision).
  • Applied these strategies to French clinical notes and discharge summaries at a Swiss university hospital.

Main Results:

  • The proactive contest and average-quality pre-annotations significantly reduced annotation time.
  • Annotation quality was demonstrably increased by these combined strategies.
  • A text de-identification model for French clinical notes achieved a high F1 score of 0.94.

Conclusions:

  • Combining proactive contests with pre-annotations is an effective method to accelerate clinical NER.
  • These strategies enhance both the speed and quality of the annotation process.
  • The developed approach enables the creation of robust de-identification models for sensitive clinical data.