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

Knowledge-based temporal abstraction in clinical domains

Y Shahar1, M A Musen

  • 1Section on Medical Informatics, School of Medicine, Stanford University, CA 94305-5479, USA. shahar@camis.stanford.edu

Artificial Intelligence in Medicine
|July 1, 1996
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

Restoration of energy homeostasis by SIRT6 extends healthy lifespan.

Nature communications·2021
Same author

Challenges in Medical Informatics. A Discipline Coming of Age.

Yearbook of medical informatics·2016
Same author

Knowledge-Based Systems: Enhancing the Quality of Care.

Yearbook of medical informatics·2016
Same author

Challenges for Medical Informatics as an Academic Discipline: Workshop Report.

Yearbook of medical informatics·2016
Same author

Knowledge Processing.

Yearbook of medical informatics·2016
Same author

[Mining medical knowledge from time-oriented clinical data using existing clinical knowledge].

Harefuah·2013
Same journal

Real-time EEG-based epileptic seizure prediction using artificial intelligence: A systematic review.

Artificial intelligence in medicine·2026
Same journal

R-peak detection and ECG data compression scheme based on empirical mode decomposition and wavelet transform.

Artificial intelligence in medicine·2026
Same journal

CastNet: A three-channel EEG-based deep learning model for cross-subject depression detection.

Artificial intelligence in medicine·2026
Same journal

State-of-the-art TinyML approaches for colorectal cancer detection: Current advances, challenges, and future directions.

Artificial intelligence in medicine·2026
Same journal

JRadiEvo: A Japanese radiology report generation model enhanced by evolutionary optimization of model merging.

Artificial intelligence in medicine·2026
Same journal

Causally-informed deep learning towards explainable and generalizable outcome prediction in critical care.

Artificial intelligence in medicine·2026
See all related articles

The knowledge-based temporal-abstraction (KBTA) method creates abstract concepts from clinical data. The RESUME system implementing KBTA achieved 80% expert agreement and 97% validity in diabetes patient monitoring.

Area of Science:

  • Clinical Informatics
  • Artificial Intelligence in Medicine
  • Data Science

Background:

  • Clinical data is often time-stamped, requiring specialized methods for interpretation.
  • Abstract concepts derived from temporal data are crucial for clinical decision-making.
  • Existing methods may lack explicit knowledge representation for temporal data abstraction.

Purpose of the Study:

  • To introduce a knowledge-based framework for abstract, interval-based concept creation from time-stamped clinical data.
  • To present the knowledge-based temporal-abstraction (KBTA) method and its implementation in the RESUME system.
  • To evaluate the effectiveness of the KBTA method in a clinical monitoring domain.

Main Methods:

  • Defined a five-subtask framework for temporal abstraction.

Related Experiment Videos

  • Developed formal solving mechanisms for each subtask.
  • Implemented the framework in the RESUME system, emphasizing explicit knowledge representation.
  • Acquired diabetes-therapy temporal-abstraction knowledge from an expert.

    • Main Results:

    • Tested the RESUME system in clinical monitoring, including insulin-dependent diabetes.
    • Two experts validated temporal abstractions from approximately 800 data points.
    • RESUME generated 80% of abstractions agreed upon by both experts.
    • Generated abstractions demonstrated a 97% validity rate.

    Conclusions:

    • The KBTA method provides a robust framework for temporal data abstraction in clinical settings.
    • The RESUME system effectively implements KBTA, showing high agreement and validity.
    • Explicit knowledge representation facilitates the acquisition, maintenance, reuse, and sharing of temporal-abstraction knowledge.