Prediction of Mortality in ELBW Infants using Logistic and Linear Regression versus Neural Networks 1198

INTRO: Neural network models are nonparametric pattern recognition techniques. Compared to techniques such as regression, neural networks offer theoretical advantages, including the ability to detect complex non-linear relationships between independent and dependent variables.

HYPOTHESES: (1) Demographic variables in extremely low birth weight (ELBW; Birth weight <1000g) infants predict mortality before discharge. (2) Neural network models are superior to multiple logistic and linear regression in predicting mortality.

Log in or create a free account to read this content

Gain free access to this article, as well as selected content from this journal and more on nature.com

Access through your institution

or

Sign in or create an account

Continue with Google

Continue with ORCiD