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

Machine learning for an expert system to predict preterm birth risk

L K Woolery1, J Grzymala-Busse

  • 1School of Nursing, University of Missouri, Columbia 65211.

Journal of the American Medical Informatics Association : JAMIA
|November 1, 1994
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

Data mining issues for improved birth outcomes.

Biomedical sciences instrumentation·1997
Same author

Machine learning for development of an expert system to predict premature birth.

Biomedical sciences instrumentation·1995
Same author

A demonstration of the virtual nursing college.

Medinfo. MEDINFO·1995
Same author

Clinical knowledge base development for preterm-birth risk assessment.

Applied nursing research : ANR·1994
Same author

Point of care documentation: a viable alternative.

Missouri medicine·1994
Same author

Improving prediction of preterm birth using a new classification scheme and rule induction.

Proceedings. Symposium on Computer Applications in Medical Care·1994

This study developed an expert system to predict preterm birth risk. The system achieved 53-88% accuracy, outperforming traditional methods for early identification of high-risk pregnancies.

Area of Science:

  • Medical Informatics
  • Machine Learning in Healthcare
  • Obstetrics and Gynecology

Background:

  • Preterm birth affects 8-12% of US newborns, causing significant individual and healthcare system burdens.
  • Accurate risk assessment is crucial for managing complications associated with prematurity.

Purpose of the Study:

  • To develop a prototype expert system for assessing preterm birth risk in pregnant women.
  • To improve the accuracy of preterm birth prediction compared to existing methods.

Main Methods:

  • Utilized a knowledge-base development methodology incorporating machine learning, statistical analysis, and validation.
  • Analyzed three large datasets comprising 18,890 subjects and 214 variables.
  • Employed the Learning from Examples using Rough Sets (LERS) machine learning program to induce predictive rules.

Related Experiment Videos

Main Results:

  • Generated 520 usable rules for the prototype expert system.
  • The expert system demonstrated a prediction accuracy of 53-88% for preterm delivery in a validation set of 9,419 patients.

Conclusions:

  • The developed prototype expert system shows superior accuracy in predicting preterm birth compared to traditional manual assessment techniques.
  • This AI-driven approach offers a promising tool for early identification and management of high-risk pregnancies.