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

Context-sensitive medical information retrieval.

Mordechai Auerbuch1, Tom H Karson, Benjamin Ben-Ami

  • 1Tel-Aviv Sourasy Medical Center, Tel-Aviv University, Tel-Aviv, Israel.

Studies in Health Technology and Informatics
|September 14, 2004
PubMed
Summary
This summary is machine-generated.

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

Investigating the anticancer activity of eravacycline in pancreatic cancer via target-based deep learning and experimental validation.

Briefings in bioinformatics·2026
Same author

Vitamin D Supplementation and Treatment-Free Survival in Early-Stage CLL: A Real-World Validation Study.

EJHaem·2026
Same author

Artificial Intelligence-Enabled Serial Electrocardiograms for Prediction of All-Cause Mortality in Secondary Care Settings.

JACC. Advances·2026
Same author

Effect of cumulative blood pressure exposure on long-term cardiovascular outcomes in the community, a nationwide cohort study.

The American journal of medicine·2026
Same author

CMML2AML: machine-learning discovery of co-mutations and specific single mutations predictive of blast transformation in chronic myelomonocytic leukemia.

Blood cancer journal·2026
Same author

CPX-351 (Liposomal Cytarabine and Daunorubicin) versus venetoclax plus hypomethylating agent therapy in newly diagnosed acute myeloid leukemia: a retrospective comparison involving 600 Mayo Clinic patients.

Blood cancer journal·2026

This study developed an algorithm to understand medical text context, significantly improving information retrieval accuracy by nearly 100% for clinical and research data. It accurately identifies negated findings, reducing irrelevant search results.

Area of Science:

  • Medical Informatics
  • Natural Language Processing
  • Clinical Data Management

Background:

  • Vast amounts of critical medical data exist as unstructured text in reports.
  • Searching these free-text narratives is crucial for clinical care and research.
  • Identifying negated findings (e.g., 'ruled out') is vital for accurate information retrieval.

Purpose of the Study:

  • To develop a method for automatically learning negative context patterns in medical narratives.
  • To evaluate the impact of context identification on medical information retrieval performance.

Main Methods:

  • Developed an algorithm for automated learning of negative context patterns.
  • Tested the algorithm's effect on information retrieval from medical narratives.

Related Experiment Videos

  • Compared context-insensitive retrieval with context-sensitive retrieval.

    • Main Results:

    • The algorithm significantly improved information retrieval performance.
    • Precision increased from approximately 60% to nearly 100%.
    • Recall was only minimally affected; new search capabilities were introduced.

    Conclusions:

    • Automated identification of negative context in medical narratives greatly enhances information retrieval.
    • Context-aware searching improves precision and offers advanced search functionalities.
    • This methodology is essential for accurate clinical and research data analysis.