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

Learning and discovery from a clinical database: an incremental concept formation approach

V W Soo1, J S Wang, S P Wang

  • 1Department of Computer Science, National Tsing-Hua University, Hsin-Chu, Taiwan.

Artificial Intelligence in Medicine
|June 1, 1994
PubMed
Summary

This study introduces D-UNIMEM, a novel model for analyzing Percutaneous Transluminal Coronary Angioplasty (PTCA) data. It uncovers clinical insights by identifying correlations within PTCA patient data through advanced concept formation.

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

Evidence of Spin-Interference Effects in Exclusive J/ψ→e^{+}e^{-} Photoproduction in Ultraperipheral Heavy-Ion Collisions.

Physical review letters·2026
Same author

First Observation of Deuteron-Λ Correlations at RHIC.

Physical review letters·2026
Same author

[Clinical analysis of 4 cases of McCune-Albright syndrome presenting with infantile cholestasis].

Zhonghua er ke za zhi = Chinese journal of pediatrics·2026
Same author

Observation of Charmonium Sequential Suppression in Heavy-Ion Collisions at the Relativistic Heavy Ion Collider.

Physical review letters·2026
Same author

Energy Independence of the Collins Asymmetry in p^{↑}p Collisions.

Physical review letters·2026
Same author

Associations of N-Terminal Pro-Brain Natriuretic Peptide with Incident Chronic Kidney Disease and All-Cause Mortality in Patients with No History of Heart Failure and Diabetes.

Nigerian journal of clinical practice·2025

Area of Science:

  • Cardiology
  • Artificial Intelligence
  • Data Mining

Background:

  • Large datasets in Percutaneous Transluminal Coronary Angioplasty (PTCA) offer potential for clinical discovery.
  • Extracting meaningful clinical implications from complex PTCA data remains a challenge.

Purpose of the Study:

  • To develop and propose a novel case-based concept formation model, D-UNIMEM, for analyzing PTCA databases.
  • To discover clinical implications and correlations from a large PTCA dataset.

Main Methods:

  • A modified UNIMEM model, termed D-UNIMEM, was developed, integrating feature-disjunction and index-conjunction class memberships.
  • The model employs a two-stage concept formation process: polythetic clustering followed by relevance-based instance clustering.
  • Applied to a large PTCA database to identify patterns and relationships.

Related Experiment Videos

Main Results:

  • D-UNIMEM successfully extracted a concept hierarchy from the PTCA data.
  • The model identified interesting correlations among various features within the learned hierarchy.
  • Demonstrated the capability of the model to derive clinical insights from complex medical data.

Conclusions:

  • D-UNIMEM is an effective model for discovering clinical implications from large PTCA databases.
  • The integrated class membership approach enhances concept formation and correlation discovery.
  • This research highlights the potential of AI-driven methods in advancing cardiovascular research.