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

Term domain distribution analysis: a data mining tool for text databases.

J A Goldman1, W W Chu, D S Parker

  • 1Computer Science Department, University of California, Los Angeles, USA. jeff@ieee.org

Methods of Information in Medicine
|August 4, 1999
PubMed
Summary

Term Domain Distribution Analysis (TDDA) revealed lung cancer tumors favor the right lung over the left, with a 3:2 ratio. This finding may alter oncologists

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

Effect of stage of lactation and dietary starch content on endocrine-metabolic status, blood amino acid concentrations, milk yield, and composition in Holstein dairy cows.

Journal of dairy science·2021
Same author

Van Hove singularity in the magnon spectrum of the antiferromagnetic quantum honeycomb lattice.

Nature communications·2021
Same author

[Time series analysis on the effect of ambient fine particulate matters and temperature interactions on schizophrenia admission in Tongling City of Anhui Province, 2014-2017].

Zhonghua yu fang yi xue za zhi [Chinese journal of preventive medicine]·2019
Same author

Effect of Surface Morphology and Magnetic Impurities on the Electronic Structure in Cobalt-Doped BaFe<sub>2</sub>As<sub>2</sub> Superconductors.

Nano letters·2017
Same author

Coming in Sportsmedicine.

The Physician and sportsmedicine·2016
Same author

Electronic structure and electron-phonon coupling in TiH2.

Scientific reports·2016

Area of Science:

  • Oncology
  • Data Mining
  • Medical Informatics

Background:

  • Text databases are rich sources of clinical information.
  • Identifying patterns in medical data can lead to new insights.
  • Standard frequency analysis may miss subtle but significant trends.

Purpose of the Study:

  • To illustrate the application of Term Domain Distribution Analysis (TDDA) in a real-world medical context.
  • To introduce TDDA as a novel data mining technique for text databases.
  • To investigate potential biases in primary thoracic lung cancer tumor location.

Main Methods:

  • Applied Term Domain Distribution Analysis (TDDA) to a thoracic lung cancer database.
  • Analyzed term frequencies within the domain {right, left} lung.

Related Experiment Videos

  • Hypothesized significant deviations from a uniform distribution.
  • Verified findings against medical literature using chi-squared statistics.

    • Main Results:

    • Discovered primary thoracic lung cancer tumors occur more frequently in the right lung than the left.
    • Observed a statistically significant right:left lung tumor ratio of 3:2.
    • Developed a theoretical model to explain the observed laterality.

    Conclusions:

    • TDDA is an effective technique for discovering novel hypotheses in medical text data.
    • The right lung exhibits a higher incidence of primary thoracic lung cancer.
    • This discovery may necessitate a re-evaluation of lung cancer mechanisms and oncological perspectives.