Improving prediction of preterm birth using a new classification scheme and rule induction.
Proc Annu Symp Comput Appl Med Care
; : 730-4, 1994.
Article
em En
| MEDLINE
| ID: mdl-7950021
ABSTRACT
Prediction of preterm birth is a poorly understood domain. The existing manual methods of assessment of preterm birth are 17%-38% accurate. The machine learning system LERS was used for three different datasets about pregnant women. Rules induced by LERS were used in conjunction with a classification scheme of LERS, based on "bucket brigade algorithm" of genetic algorithms and enhanced by partial matching. The resulting prediction of preterm birth in new, unseen cases is much more accurate (68%-90%).
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Algoritmos
/
Recém-Nascido Prematuro
/
Inteligência Artificial
/
Classificação
/
Medição de Risco
/
Trabalho de Parto Prematuro
Tipo de estudo:
Etiology_studies
/
Prognostic_studies
/
Risk_factors_studies
Limite:
Female
/
Humans
/
Male
/
Newborn
/
Pregnancy
Idioma:
En
Revista:
Proc Annu Symp Comput Appl Med Care
Ano de publicação:
1994
Tipo de documento:
Article