Neural networks are new methodological tools based on nonlinear models. They appear to be better at prediction and classification in biological systems than do traditional strategies such as logistic regression. This paper provides a practical example that contrasts both approaches within the setting of suspected sepsis in the emergency room.
Department of Internal Medicine, Escuela de Investigaciones Médicas Aplicadas (EIMA - GRAEPI), School of Medicine, Universidad de Antioquia, Medellín, Colombia. fjaimes@catios.udea.edu.co
