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

KG-Microbe - Building Modular and Scalable Knowledge Graphs for Microbiome and Microbial Sciences.

GigaScience·2026
Same author

Distinct associations of pioneer factor Ascl1-E12a with nucleosomes drive changes in cell fate.

Molecular cell·2026
Same author

AdaptMol: domain adaptation for molecular image recognition with limited supervision.

Journal of cheminformatics·2026
Same author

Dynamic thermodynamic-informational entropic relationship (TIER) models of selective vulnerability to neurodegeneration.

bioRxiv : the preprint server for biology·2026
Same author

Desiderata for a biomedical knowledge network: opportunities, challenges and future directions.

Bioinformatics advances·2026
Same author

Governing real-world health data as a public utility.

Science (New York, N.Y.)·2026

Related Experiment Video

Updated: May 2, 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

1.3K

Large-scale biomedical concept recognition: an evaluation of current automatic annotators and their parameters.

Christopher Funk1, William Baumgartner, Benjamin Garcia

  • 1Computational Bioscience Program, U, of Colorado School of Medicine, Aurora, CO 80045, USA. christopher.funk@ucdenver.edu.

BMC Bioinformatics
|February 28, 2014
PubMed
Summary

Establishing baselines for biomedical concept recognition, this study found ConceptMapper generally outperformed MetaMap and NCBO Annotator across eight ontologies. Optimizing parameters significantly improved performance, highlighting the need for tailored system-ontology configurations.

More Related Videos

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.0K
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.9K

Related Experiment Videos

Last Updated: May 2, 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

1.3K
Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.0K
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.9K

Area of Science:

  • Biomedical Informatics
  • Natural Language Processing
  • Ontology Engineering

Background:

  • Biomedical concept recognition is crucial for diverse applications.
  • Challenges exist in mapping ontological concepts to textual expressions.
  • A generalized approach for concept recognition remains an open research problem.

Purpose of the Study:

  • To evaluate and establish performance baselines for dictionary-based concept recognition systems.
  • To identify optimal system-ontology parameter configurations for biomedical text.
  • To provide guidance on selecting parameters based on ontology characteristics.

Main Methods:

  • Evaluated three systems: MetaMap, NCBO Annotator, and ConceptMapper.
  • Utilized the Colorado Richly Annotated Full-Text (CRAFT) Corpus with eight biomedical ontologies.
  • Examined over 1,000 parameter combinations for each system-ontology pair.

Main Results:

  • Established F-measure baselines ranging from 0.14 to 0.83 across system-ontology pairs.
  • ConceptMapper achieved the highest F-measure for seven out of eight ontologies.
  • Parameter optimization increased F-measures by up to 0.4, demonstrating the impact of tuning.

Conclusions:

  • ConceptMapper demonstrated superior performance in biomedical concept recognition compared to MetaMap and NCBO Annotator.
  • Default system parameters are often suboptimal; significant performance gains are achievable through parameter tuning.
  • Recommendations for parameter selection based on specific ontology features are provided to enhance concept recognition accuracy.