Building knowledge in a complex preterm birth problem domain.

L. Goodwin, S. Maher, L. Ohno-Machado, M. A. Iannacchione, P. Crockett, S. Dreiseitl, S. Vinterbo, W. Hammond

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

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.

Original languageEnglish
Pages (from-to)305-309
Number of pages5
JournalProceedings / AMIA ... Annual Symposium. AMIA Symposium
Publication statusPublished - 2000
Externally publishedYes

Keywords

  • Area Under Curve
  • Artificial Intelligence
  • Decision Support Techniques
  • Female
  • Humans
  • Infant, Newborn
  • Infant, Premature
  • Information Storage and Retrieval
  • Logistic Models
  • Neural Networks, Computer
  • Obstetric Labor, Premature/prevention & control
  • Pregnancy
  • ROC Curve
  • Risk Assessment/methods
  • Statistics as Topic

Fingerprint Dive into the research topics of 'Building knowledge in a complex preterm birth problem domain.'. Together they form a unique fingerprint.

Cite this