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

Building knowledge in a complex preterm birth problem domain.

L Goodwin1, S Maher, L Ohno-Machado

  • 1Duke University, Durham, NC, USA. linda.goodwin@duke.edu

Proceedings. AMIA Symposium
|November 18, 2000
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

Laboratory results from an ultra-stable MID IR spectrometer for exo-planet atmosphere characterization.

The Review of scientific instruments·2025
Same author

Storage of evidence and delayed reporting after sexual assault: Rates and impact factors on subsequent reporting.

Journal of forensic and legal medicine·2024
Same author

An automated micro solid phase extraction gas chromatography-mass spectrometry (μSPE-GC-MS) detection method for geosmin and 2-methylisoborneol in drinking water.

Scientific reports·2023
Same author

Preliminary findings of performing aerosol generating procedures using a novel innovative mask in times of COVID-19 pandemic.

The Medical journal of Malaysia·2021
Same author

The prevalence of hazardous and harmful drinking in the UK Police Service, and their co-occurrence with job strain and mental health problems.

Epidemiology and psychiatric sciences·2021
Same author

Morphological Re-description of Camallanus polypteri) Nematoda: Camallanidae) Infecting the African Sharptooth Catfish Clarias gariepinus (Clariidae).

Archives of Razi Institute·2021
Same journal

Progressive display of very high resolution images using wavelets.

Proceedings. AMIA Symposium·2002
Same journal

The Chronus II temporal database mediator.

Proceedings. AMIA Symposium·2002
Same journal

Gene expression levels in different stages of progression in oral squamous cell carcinoma.

Proceedings. AMIA Symposium·2002
Same journal

An assessment of the visibility of MeSH-indexed medical web catalogs through search engines.

Proceedings. AMIA Symposium·2002
Same journal

Filtering for medical news items using a machine learning approach.

Proceedings. AMIA Symposium·2002
Same journal

Enriching the structure of the UMLS semantic network.

Proceedings. AMIA Symposium·2002
See all related articles

Predictive accuracy in pregnant women can be achieved using just seven demographic variables. Adding more clinical data offered minimal improvement, suggesting demographic factors are key for diverse populations.

Area of Science:

  • Medical Informatics
  • Public Health
  • Biostatistics

Background:

  • Electronic patient records contain vast amounts of data for health research.
  • Predictive modeling in healthcare requires identifying key patient variables.
  • Understanding demographic impacts on health outcomes is crucial for equitable care.

Purpose of the Study:

  • To evaluate the predictive accuracy of demographic versus clinical variables in a large, diverse pregnant population.
  • To compare the performance of different data mining and statistical methods for health prediction.
  • To identify parsimonious sets of variables for predicting outcomes in pregnant women.

Main Methods:

  • Utilized data mining and statistical methods on a racially diverse sample (n=19,970) of pregnant women.

Related Experiment Videos

  • Analyzed 1,622 variables from Duke's TMR electronic patient record over 10 years.
  • Employed receiver operating characteristic (ROC) curves to compare model performance and area under the curve (AUC).

    • Main Results:

    • Seven demographic variables achieved an area under the curve (AUC) of 0.72.
    • Adding hundreds of clinical variables to demographic data yielded only a marginal AUC increase of 0.03.
    • Different data mining methods showed similar predictive performance, indicating data-driven results.

    Conclusions:

    • Demographic variables alone offer significant predictive accuracy in a racially diverse pregnant population.
    • A small set of demographic variables can be parsimonious and effective for prediction.
    • Further research is ongoing to identify additional variables for enhanced predictive accuracy.