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: Mar 4, 2026

A Data-Driven Approach to Quantifying Immune States in Sepsis
07:42

A Data-Driven Approach to Quantifying Immune States in Sepsis

Published on: February 7, 2025

559

A Case Study on Sepsis Using PubMed and Deep Learning for Ontology Learning.

Mercedes Arguello Casteleiro1, Diego Maseda Fernandez2, George Demetriou1

  • 1School of Computer Science, University of Manchester (UK).

Studies in Health Technology and Informatics
|April 21, 2017
PubMed
Summary

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

Legionella pneumophila pneumonia in South Eastern Sydney: diagnosis, prognosis and public health outcomes.

Internal medicine journal·2026
Same author

Recognition and linking of discontinuous named entities in healthcare: a comparative performance analysis.

Frontiers in digital health·2026
Same author

Micro-ultrasound guided versus multiparametric MRI-guided prostate biopsy: a systematic review and meta-analysis.

International urology and nephrology·2026
Same author

Health inequalities in outpatient neurological conditions across a large UK urban population: a retrospective observational study using automated coding.

BMJ neurology open·2026
Same author

Co-Curricular Science Experiences Support Undergraduate Students' Science GPA, Degree Completion, Workforce Entry, and Motivation.

CBE life sciences education·2026
Same author

Development and validation of prediction models for predicting social care strengths and vulnerability in older people: Cohort study using routine data in Adult Social Care.

PloS one·2026

Deep learning models significantly improve unsupervised biomedical term extraction from research papers. This advancement enhances the automatic annotation of medical concepts and relations, particularly for critical conditions like sepsis.

Area of Science:

  • Biomedical Informatics
  • Natural Language Processing
  • Computational Linguistics

Background:

  • Unsupervised extraction of biomedical terms is crucial for ontology learning and concept annotation.
  • Existing methods like Latent Semantic Analysis (LSA) and Latent Dirichlet Allocation (LDA) have limitations in accuracy.
  • Large-scale biomedical text corpora, such as PubMed, offer rich data for term discovery.

Purpose of the Study:

  • To evaluate the effectiveness of distributional semantics models for unsupervised biomedical term extraction.
  • To compare traditional methods (LSA, LDA) with deep learning approaches (CBOW, Skip-gram).
  • To assess the impact of these models on the semi-automatic annotation of biomedical concepts and relations.

Main Methods:

  • Applied Latent Semantic Analysis (LSA) and Latent Dirichlet Allocation (LDA) for term extraction.
Keywords:
Deep LearningOWLOntology LearningPubMedSPARQL

More Related Videos

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

1.6K

Related Experiment Videos

Last Updated: Mar 4, 2026

A Data-Driven Approach to Quantifying Immune States in Sepsis
07:42

A Data-Driven Approach to Quantifying Immune States in Sepsis

Published on: February 7, 2025

559
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

1.6K
  • Utilized deep learning models, specifically Continuous Bag-of-Words (CBOW) and Skip-gram, for term extraction.
  • Experimented on over 300,000 PubMed titles and abstracts, focusing evaluation on sepsis-related literature.

    • Main Results:

    • Deep learning models (CBOW, Skip-gram) demonstrated superior performance compared to LSA and LDA.
    • Higher precision was achieved using neural language models for biomedical term extraction.
    • The study confirmed the potential of these models for enhancing ontology learning processes.

    Conclusions:

    • Deep learning-based distributional semantics models offer a more precise approach to unsupervised biomedical term extraction.
    • These advanced methods can significantly improve the efficiency and accuracy of annotating biomedical concepts and relations.
    • The findings suggest a promising direction for advancing automated biomedical knowledge discovery.