RESUMEN
Demographic factors have been shown to be moderate predictors of preterm birth in prior studies which used hospital databases and epidemiologic sample surveys. This retrospective study used de-identified 2003 North Carolina birth certificate data (n=73,040) and replicated the statistical and computational methods used in a prior study of an academic medical center's data warehouse. Receiver Operating Characteristics (ROC) curves were used to compare results across methods. Due to differences between the data collected for birth certificates and the original clinical database, five of the seven demographic variables in the clinical database model were available for model testing (maternal age, marital status, race/ethnicity, education and county). Even with a reduced model, multiple methods of statistical and computational modeling supported the earlier findings of demographic predictors for preterm birth. The reduced model AUC results were acceptable (logistic regression = 0.605, neural networks = 0.57, SVM = 0.57, Bayesian classifiers = 0.59, and CART = 0.56), but lower than in the prior study as might be expected for a reduced model. On a population level, these results support a prior demographic predictor preterm birth model generated from a clinical database and the use of computational methods for model formation. Additional testing for stronger predictor models within birth certificate data is suggested as birth certificate data is a parsimonious population dataset already routinely collected.
Asunto(s)
Certificado de Nacimiento , Técnicas de Apoyo para la Decisión , Procesamiento Automatizado de Datos , Cómputos Matemáticos , Trabajo de Parto Prematuro/diagnóstico , Teorema de Bayes , Simulación por Computador , Demografía , Femenino , Humanos , Recién Nacido , Redes Neurales de la Computación , North Carolina , Embarazo , Curva ROC , Estudios Retrospectivos , Factores de RiesgoRESUMEN
This paper investigates whether HIPAA de-identification requirements--as well as proposed AAMC de-identification standards--were met in a large clinical data mining study (1997-2001) conducted at Duke University prior to the publication of the final rule. While HIPAA has improved de-identification standards, the study also shows that privacy issues may persist even in de-identified large clinical databases.
Asunto(s)
Investigación Biomédica/legislación & jurisprudencia , Seguridad Computacional/legislación & jurisprudencia , Confidencialidad/legislación & jurisprudencia , Sistemas de Administración de Bases de Datos/legislación & jurisprudencia , Health Insurance Portability and Accountability Act , Sistemas de Información/organización & administración , Sistemas de Registros Médicos Computarizados/legislación & jurisprudencia , Humanos , Sistemas de Identificación de Pacientes , Estados UnidosRESUMEN
Data mining is a research method that is increasingly being used to predict clinical outcomes, for example, cancer or AIDS survival, diagnostic accuracy in abdominal pain or brain tumors, and much more. In clinical practice, predicting which patients will deliver preterm versus full term remains a complex clinical problem for families and the healthcare system. Exploratory data mining was used for predicting birth outcomes in a racially diverse sample (n = 19,970). Duke University provided data (1622 variables) for data mining methods that found 7 demographic variables yielded .72 area under the curve for receiver operating characteristic (ROC) analyses, suggesting that a parsimonious set of preterm birth outcomes predictors may be possible. Improved prediction is needed for interventions to be appropriately targeted for improved birth outcomes management.