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

Using classification trees to assess low birth weight outcomes.

Panagiota Kitsantas1, Myles Hollander, Lei Li

  • 1George Mason University, Department of Health Administration and Policy, The College of Health and Human Services, 4400 University Drive, Fairfax, VA 22030, USA. kitsantap@ecu.edu

Artificial Intelligence in Medicine
|May 30, 2006
PubMed
Summary

Classification trees effectively identify high-risk mothers for low birth weight (LBW) outcomes. Both classification trees and logistic regression offer valuable insights into LBW risk factors.

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

Needle immersed vitrification can lower the concentration of cryoprotectant in human ovarian tissue cryopreservation.

Fertility and sterility·2010
Same author

A proteomics based approach to assessing the toxicity of bisphenol A and diallyl phthalate to the abalone (Haliotis diversicolor supertexta).

Chemosphere·2010
Same author

Maternal control of early mouse development.

Development (Cambridge, England)·2010
Same author

Characterization of EndoTT, a novel single-stranded DNA-specific endonuclease from Thermoanaerobacter tengcongensis.

Nucleic acids research·2010
Same author

Association study between three polymorphisms and myocardial infarction and ischemic stroke in Chinese Han population.

Thrombosis research·2010
Same author

Arabidopsis IWS1 interacts with transcription factor BES1 and is involved in plant steroid hormone brassinosteroid regulated gene expression.

Proceedings of the National Academy of Sciences of the United States of America·2010

Area of Science:

  • Public Health
  • Biostatistics
  • Maternal and Child Health

Background:

  • Low birth weight (LBW) is a significant public health concern linked to adverse infant outcomes.
  • Identifying risk factors for LBW is crucial for targeted interventions.
  • Previous research has identified numerous LBW risk factors, but their interactive nature requires further investigation.

Purpose of the Study:

  • To identify high-risk subgroups of women for LBW outcomes in seven Florida regions using classification trees.
  • To compare the predictive performance of classification trees against logistic regression models for LBW prediction.

Main Methods:

  • Utilized a dataset of 181,690 singleton births from Florida birth certificates (1998).
  • Employed classification trees and logistic regression models, analyzing LBW (< 2500 g) versus normal birth weight (> or = 2500 g).

Related Experiment Videos

  • Compared model performance using Receiver Operating Characteristic (ROC) curves, sensitivity, and specificity analyses.

    • Main Results:

    • Classification trees identified specific high-risk subgroups, such as White, Hispanic, or Other non-white mothers who smoked and had low weight gain.
    • Parity and marital status were significant predictors for non-smoker subgroups.
    • Black mothers constituted a high-risk subgroup, with further defining characteristics in Southern regions; predictive performance was similar between tree and logistic models.

    Conclusions:

    • Classification trees are effective tools for identifying maternal subgroups at high risk for LBW.
    • Exploratory tree analyses revealed distinct variable interactions across geographical areas, with consistent variable selection.
    • Both classification trees and logistic regression models provided valuable, comparable analyses for LBW risk assessment.