[ Neo Home | New | Clinical | Computers | Jobs | Diversions | Links ]

Title Building Knowledge in a Complex Preterm Birth Problem Domain
Author(s) LK. Goodwin, RNC, PhD , SG. Maher, MS , L. Ohno-Machado, MD, PhD, M.A. Iannacchione BSN, P. Crockett, PhD, S. Dreiseitl, PhD, S. Vinterbo, PhD, W. E. Hammond, PhD
Source Proceedings of the AMIA 2000 Annual Symposium, Pages 305-309
ISBN 1-56053-480-X
Publisher AMIA
Publication Date November, 2000
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 character istic (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.


Return to Citation Index Page

This page was last modified on 11-11-2000.
Citation database was last rebuilt on 02-18-2012.
Neonatology on the Web / webmaster@neonatology.org