Title :
Predictive Models for Long Term Survival after Premature Rupture of Membranes
Author :
Ameye, Lieveke ; De Brabanter, Jos ; Suykens, Johan A K ; Cadron, Isabelle ; Devlieger, Roland ; Timmerman, Dirk ; Spitz, Bernard ; Van Huffel, Sabine
Author_Institution :
Dept. of Electr. Eng., Katholieke Univ., Leuven, Heverlee
Abstract :
Premature rupture of the membranes complicates 30 to 40% of the preterm deliveries. The purpose of this study is to assess the outcome of preterm prelabor rupture of the membranes (PPROM) before 26 weeks of gestation and to develop a predictive model for survival. We apply four statistical methods in order to construct a predictive model: Cox´s proportional hazards model, logistic regression, least squares - support vector machines and generalized estimating equations. The obtained predictive models are tested on a prospective set and have a very good performance of > 95% for the area under the ROC-curve
Keywords :
biomechanics; biomembranes; fracture; least squares approximations; obstetrics; physiological models; regression analysis; sensitivity analysis; support vector machines; 26 week; Cox proportional hazards model; ROC curve; generalized estimating equations; gestation; least squares; logistic regression; long term survival; predictive models; premature membrane rupture; preterm deliveries; preterm prelabor membrane rupture; statistical methods; support vector machines; Amniotic fluid; Biomedical engineering; Biomembranes; Hazards; Least squares approximation; Pediatrics; Predictive models; Pregnancy; Time measurement; Volume measurement;
Conference_Titel :
Engineering in Medicine and Biology Society, 2005. IEEE-EMBS 2005. 27th Annual International Conference of the
Conference_Location :
Shanghai
Print_ISBN :
0-7803-8741-4
DOI :
10.1109/IEMBS.2005.1615500
