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

An inductive algorithm approach to knowledge acquisition for expert system development. A pilot study

S B Henry1

  • 1University of California, San Francisco 94143-0608, USA.

Computers in Nursing
|September 1, 1995
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

Hematological complications and quality of life in hospitalized AIDS patients.

AIDS patient care and STDs·2000
Same author

The Client Adherence Profiling-Intervention Tailoring (CAP-IT) intervention for enhancing adherence to HIV/AIDS medications: a pilot study.

The Journal of the Association of Nurses in AIDS Care : JANAC·2000
Same author

Validation of the Sign and Symptom Check-List for Persons with HIV Disease (SSC-HIV).

Journal of advanced nursing·1999
Same author

Representing nursing judgements in the electronic health record.

Journal of advanced nursing·1999
Same author

Predictors of self-reported adherence in persons living with HIV disease.

AIDS patient care and STDs·1999
Same author

Quality of life and self-care management strategies of PLWAs with chronic diarrhea.

The Journal of the Association of Nurses in AIDS Care : JANAC·1999
Same journal

Using online learning in a traditional face-to-face environment.

Computers in nursing·2002
Same journal

The "big bang" implementation: not for the faint of heart.

Computers in nursing·2002
Same journal

Homebound older adults' experiences with the Internet and e-mail.

Computers in nursing·2002
Same journal

A study of factors related to the use of online resources by nurse educators.

Computers in nursing·2002
Same journal

Toward comparable nursing data: American Nurses Association criteria for data sets, classification systems, and nomenclatures.

Computers in nursing·2002
Same journal

Deep versus surface learning with multimedia in nursing education development and evaluation of WoundCare.

Computers in nursing·2001
See all related articles

Inductive algorithms like C4 and CART were tested for knowledge acquisition in expert systems but did not significantly improve outcome prediction accuracy for Pneumocystis pneumonia patients. Further research is needed for effective nursing knowledge transformation.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Expert Systems

Background:

  • Knowledge acquisition is a critical challenge in expert system design.
  • Traditional methods rely heavily on knowledge engineering.
  • Inductive algorithms offer a potential alternative for automated knowledge acquisition.

Purpose of the Study:

  • To evaluate the feasibility of using machine learning inductive algorithms for knowledge elicitation and representation.
  • To assess the effectiveness of C4 and Classification and Regression Trees (CART) in an expert system context.
  • To explore the transformation of nursing data into nursing knowledge using inductive approaches.

Main Methods:

  • Applied two inductive algorithms, C4 and CART, to a database of 201 patients with Pneumocystis carinii pneumonia.

Related Experiment Videos

  • Generated decision trees to represent knowledge and predict patient outcomes.
  • Compared algorithm accuracy against a baseline prediction accuracy.

    • Main Results:

    • Neither C4 nor CART algorithms significantly improved prediction accuracy over the 71.3% baseline.
    • The mean accuracy for C4 decision trees was below baseline.
    • CART decision trees achieved a mean accuracy of 74.6%, deemed comprehensible but inadequate by experts who noted missing variables.

    Conclusions:

    • Inductive algorithms, while comprehensible, were not adequate for this nursing knowledge acquisition task.
    • The study highlights the need for further investigation into the appropriate application of inductive algorithms for transforming nursing data into knowledge.
    • Additional research is required to refine these techniques for expert system development in nursing.