Classification of the Onset of Respiratory Difficulties in Ventilation Assisted Neonates

Intensive care units are designed to sustain the lives of the people being treated within them. However, often treatment decisions are made on a second by second basis and warning signs for other developing problems are missed. This paper describes a system which uses a multi-layer perceptron network to detect the deterioration in respiratory function of neonates who require artificial ventilation. It presents some results from the system and discusses the implications of using such a system in its current form.