Related Experiment Video
Updated: Jul 5, 2026
14:43
A Novel Method for Involving Women of Color at High Risk for Preterm Birth in Research Priority Setting
Published on: January 12, 2018
Predictors of preterm birth in birth certificate data.
Karen L Courtney1, Sara Stewart, Mihail Popescu
1School of Nursing, University of Pittsburgh, PA 15261 USA. karen.courtney@alumni.duke.edu
Studies in Health Technology and Informatics
|May 20, 2008
Summary
Demographic factors predict preterm birth risk. This study validated these predictors using North Carolina birth certificate data and computational methods, confirming their population-level utility.
Area of Science:
- Public Health
- Biostatistics
- Data Science
Background:
- Prior studies identified demographic factors as moderate predictors of preterm birth using hospital databases.
- Replication of these findings is crucial for population-level understanding and intervention.
Purpose of the Study:
- To validate demographic predictors of preterm birth using North Carolina birth certificate data.
- To assess the utility of computational modeling methods on a large, routinely collected dataset.
Main Methods:
- Retrospective analysis of 73,040 North Carolina birth certificate records from 2003.
- Replication of statistical and computational modeling techniques (logistic regression, neural networks, SVM, Bayesian classifiers, CART) from a prior study.
- Comparison of model performance using Receiver Operating Characteristics (ROC) curves and Area Under the Curve (AUC) values.
Main Results:
- Demographic variables (maternal age, marital status, race/ethnicity, education, county) remained significant predictors of preterm birth.
- Computational models demonstrated acceptable predictive performance (AUC range: 0.56-0.605) on birth certificate data.
- Model performance was lower than the original study, likely due to data limitations (reduced variable set).
Conclusions:
- Findings support the use of demographic factors as preterm birth predictors on a population level.
- Computational methods are viable for modeling preterm birth risk using birth certificate data.
- Further research is recommended to develop stronger predictive models using comprehensive birth certificate data.
Related Concept Videos
01:52Regression Toward the Mean
Regression toward the mean (“RTM”) is a phenomenon in which extremely high or low values—for example, and individual’s blood pressure at a particular moment—appear closer to a group’s average upon remeasuring. Although this statistical peculiarity is the result of random error and chance, it has been problematic across various medical, scientific, financial and psychological applications. In particular, RTM, if not taken into account, can interfere when researchers try to extrapolate results...
01:49Probability Laws
Overview
01:28Development of the Oral Microbiota
The establishment of the oral microbiome begins before birth, challenging the long-held belief that the fetal oral cavity is sterile. The presence of oral microbes such as Streptococcus and Fusobacterium in amniotic fluid suggests that microbial exposure may occur in utero, potentially through translocation from the maternal oral or gastrointestinal tract. This early colonization primes the neonatal immune system and sets the stage for subsequent microbial succession. Maternal health,...