Building knowledge in a complex preterm birth problem domain.

Journal Article (Journal Article)

Data mining methods used a racially diverse sample (n = 19,970) of pregnant women and 1,622 variables that were collected in Duke's TMR electronic patient record over a 10-year period. Different statistical and data mining methods were similar when compared using receiver operating characteristic (ROC) curves. Best results found that seven demographic variables yielded .72 and addition of hundreds of other clinical variables added only .03 to the area under the curve (AUC). Similar results across methods suggest that results were data-driven and not method-dependent, and that demographic variables may offer a small set of parsimonious variables with predictive accuracy in a racially diverse population. Work to determine relevant variables for improved predictive accuracy is ongoing.

Full Text

Duke Authors

Cited Authors

  • Goodwin, L; Maher, S; Ohno-Machado, L; Iannacchione, MA; Crockett, P; Dreiseitl, S; Vinterbo, S; Hammond, W

Published Date

  • 2000

Published In

Start / End Page

  • 305 - 309

PubMed ID

  • 11079894

Pubmed Central ID

  • PMC2243761

International Standard Serial Number (ISSN)

  • 1531-605X


  • eng

Conference Location

  • United States