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 Videos

Natural language processing and visualization in the molecular imaging domain.

P Karina Tulipano1, Ying Tao, William S Millar

  • 1Department of Biomedical Informatics, Columbia University, 622 West 168th Street, Vanderbilt Clinic Floor 5, NY 10032, USA.

Journal of Biomedical Informatics
|November 7, 2006
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

Ensembles of natural language processing systems for portable phenotyping solutions.

Journal of biomedical informatics·2019
Same author

Crowdsourcing Public Opinion for Sharing Medical Records for the Advancement of Science.

Studies in health technology and informatics·2019
Same author

A two-site survey of medical center personnel's willingness to share clinical data for research: implications for reproducible health NLP research.

BMC medical informatics and decision making·2019
Same author

Validation of the Behavior of a Knowledge Base Implementing Clinical Guidelines for Point-of-Care Antiretroviral Toxicity Monitoring.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2019
Same author

Deep Phenotyping on Electronic Health Records Facilitates Genetic Diagnosis by Clinical Exomes.

American journal of human genetics·2018
Same author

Pharmacogenomic Approaches for Automated Medication Risk Assessment in People with Polypharmacy.

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science·2018

This study adapted a natural language processing (NLP) system, BioMedLEE, for molecular imaging research. The enhanced system effectively extracts key biological and imaging data, improving information organization for researchers.

Area of Science:

  • Biomedical Imaging
  • Genomic Sciences
  • Natural Language Processing

Background:

  • Molecular imaging integrates genomic and medical imaging data, presenting opportunities for enhanced research organization and information retrieval.
  • Existing natural language processing (NLP) systems can extract biological information from scientific literature.
  • The molecular imaging domain requires specialized terminology for effective information extraction.

Purpose of the Study:

  • To adapt and evaluate the BioMedLEE NLP system for the molecular imaging domain.
  • To extend BioMedLEE's capabilities by incorporating a molecular imaging-specific terminology.
  • To assess the performance of the adapted system in extracting relevant information.

Main Methods:

  • Extended an existing molecular imaging terminology.

Related Experiment Videos

  • Integrated the extended terminology into the BioMedLEE NLP system.
  • Conducted a formal evaluation study to measure system performance using recall and precision metrics.

    • Main Results:

    • The adapted BioMedLEE system achieved a recall of 0.74 (95% CI: 0.70-0.76) and a precision of 0.70 (95% CI: 0.63-0.76).
    • The system successfully extracted biomolecular substances and phenotypic data relevant to molecular imaging.
    • A JAVA viewer (PGviewer) was adapted for simultaneous visualization of images and NLP-extracted information.

    Conclusions:

    • The adaptation of BioMedLEE is effective for the molecular imaging domain.
    • The enhanced NLP system facilitates better organization and indexing of molecular imaging literature.
    • This approach supports researchers by linking imaging data with extracted biological and phenotypic information.