Building knowledge in a complex preterm birth problem domain.
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.
Duke Scholars
Published In
ISSN
Publication Date
Start / End Page
Location
Related Subject Headings
- Statistics as Topic
- Risk Assessment
- ROC Curve
- Pregnancy
- Obstetric Labor, Premature
- Neural Networks, Computer
- Logistic Models
- Information Storage and Retrieval
- Infant, Premature
- Infant, Newborn
Citation
Published In
ISSN
Publication Date
Start / End Page
Location
Related Subject Headings
- Statistics as Topic
- Risk Assessment
- ROC Curve
- Pregnancy
- Obstetric Labor, Premature
- Neural Networks, Computer
- Logistic Models
- Information Storage and Retrieval
- Infant, Premature
- Infant, Newborn