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

Medical textbook summarization and guided navigation using statistical sentence extraction.

Gregory Whalen1

  • 1Department of Computer Science, Columbia University, New York, NY 10027, USA.

AMIA ... Annual Symposium Proceedings. AMIA Symposium
|June 17, 2006
PubMed
Summary

This study introduces automated summarization for medical texts, using semantic analysis to extract relevant sentences for user queries. The method ensures summaries directly address search terms, improving information retrieval from textbooks and encyclopedias.

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

An evaluation of automatically generated briefings of patient status.

Studies in health technology and informaticsยท2004
See all related articles

Area of Science:

  • Medical Informatics
  • Natural Language Processing
  • Information Retrieval

Background:

  • Medical textbooks and encyclopedias contain vast amounts of information.
  • Efficiently retrieving specific, relevant information from these resources is challenging.
  • Existing search functionalities may not always provide concise, targeted answers.

Purpose of the Study:

  • To develop an automated method for summarizing medical textbook and encyclopedia content.
  • To tailor summaries to specific user search queries.
  • To improve the user's ability to find desired information within large medical texts.

Main Methods:

  • Utilized statistical sentence extraction and semantic relationship analysis.
  • Implemented a clustering method using Expectation Maximization (EM) on concepts from the Unified Medical Language System (UMLS).

Related Experiment Videos

  • Extracted sentences containing concepts relevant to the user's query context.

    • Main Results:

    • The system successfully summarizes relevant chapters and sections based on user search terms.
    • Summaries are tailored to include sentences directly addressing the query context.
    • The method was evaluated for its effectiveness in providing suitable answers to user questions.

    Conclusions:

    • Automated summarization using semantic analysis and concept clustering enhances information retrieval from medical literature.
    • The proposed method offers a more targeted approach to accessing information within medical textbooks and encyclopedias.
    • This technique can significantly improve user experience and efficiency in medical knowledge discovery.