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 engineering using retrospective review of data: a useful technique or merely data dredging?

T D East1, S Henderson, N L Pace

  • 1Pulmonary Division, LDS Hospital, Salt Lake City, UT 84143.

International Journal of Clinical Monitoring and Computing
|January 1, 1991
PubMed
Summary

Extracting medical decision rules from past ICU patient data proved difficult. Physician decision-making varies significantly, making retrospective knowledge engineering for hemodynamic stability unreliable.

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

Review of chest injuries in a trauma centre without local cardiothoracic surgery.

The surgeon : journal of the Royal Colleges of Surgeons of Edinburgh and Ireland·2026
Same author

A Catalyst to Better Searching: Tackling Health Inequities with a Novel Interactive eResource.

Medical reference services quarterly·2025
Same author

The genomic landscape of familial glioma.

Science advances·2023
Same author

Genome sequencing reveals underdiagnosis of primary ciliary dyskinesia in bronchiectasis.

The European respiratory journal·2022
Same author

Magseed localisation of non-palpable breast lesions: experience from a single centre.

Clinical radiology·2022
Same author

Improved Constraints on Primordial Gravitational Waves using Planck, WMAP, and BICEP/Keck Observations through the 2018 Observing Season.

Physical review letters·2021

Area of Science:

  • Medical Informatics
  • Clinical Decision Support
  • Intensive Care Medicine

Background:

  • Knowledge engineering aims to extract rules for medical decision-making from historical data.
  • Defining hemodynamic stability is crucial for managing critically ill patients, particularly those with adult respiratory distress syndrome on mechanical ventilation.

Purpose of the Study:

  • To derive rules for defining hemodynamic stability using retrospective data from intensive care unit (ICU) patients.
  • To assess the feasibility of knowledge engineering for clinical decision rules through analysis of past medical decisions.

Main Methods:

  • Retrospective analysis of 97 ICU patients with adult respiratory distress syndrome managed by computerized protocols.
  • Utilized the HELP system database to identify therapy instructions not followed due to hemodynamic reasons, with controls for followed instructions.

Related Experiment Videos

  • Employed stepwise logistic regression on corresponding hemodynamic data to identify rules for hemodynamic instability.

    • Main Results:

    • Key hemodynamic parameters anticipated to be important were frequently unmeasured.
    • Blood pressure and heart rate showed minimal differences between stable and unstable hemodynamic states.
    • Significant variability was observed in physician decision-making, both between and within individual physicians.

    Conclusions:

    • Retrospective knowledge engineering for clinical decision rules, especially for hemodynamic stability, is prone to errors due to inconsistent physician practices.
    • The inherent variability in clinical judgment complicates the extraction of reliable decision-making rules from historical data.
    • Further research may be needed to develop more robust methods for capturing and codifying clinical expertise.