Predicting the risk of newborns based on fuzzy clustering method with prediction risk assessment

Abstract

The role of the cervix in the pathogenesis of premature delivery is controversial. In a prospective, multicenter study of pregnant women, we used vaginal ultrasonography to measure the length of the cervix; we also documented the incidence of spontaneous delivery before 35 weeks' gestation. We performed vaginal ultrasonography at approximately 24 and 28 weeks of gestation in women with singleton pregnancies. We then assessed the relation between the length of the cervix and the risk of spontaneous preterm delivery. We examined 2915 women at approximately 24 weeks of gestation and 2531 of these women again at approximately 28 weeks. Spontaneous preterm delivery (at less than 35 weeks) occurred in 126 of the women (4.3 percent) examined at 24 weeks. The length of the cervix was normally distributed at 24 and 28 weeks (mean [SD], 35.28.3 mm and 33.78.5 mm, respectively). The relative risk of preterm delivery increased as the length of the cervix decreased. The paper discusses approximation properties of other possible types of nonlinearities that might be implemented by artificial neural networks. The daily registration has N cases that each of the well-known stimulus-answer couples represents. The objective of this work is to develop a function that allows finding the vector of entrance variables t to the vector of exit variables P. F is any function, in this case the electric power consumption. Their modeling with Artificial Neural Network (ANN) is Multi a Perceptron Layer (PMC). Another form of modeling it is using Interpolation Algorithms (AI). For the lengths measured at 28 weeks, the corresponding relative risks were 2.80, 3.52, 5.39, 9.57, 13.88, and 24.94 (P0.001 for values at or below the 50th percentile; P0.003 for values at the 75th percentile). The risk of spontaneous preterm delivery is increased in women who are found to have a short cervix by vaginal ultrasonography during pregnancy.