Towards an optimal data set for intensive care

The use of Artificial Neural Network technology offers an objective way for determining the significance of primary medical evidence. Of interest in this paper is an application in an intensive care setting, an environment which is well known for its problems in dealing with data information explosion. To tame this complexity and provide assistance to the uninitiated physician, a contextual method to demonstrate the relative importance of each clinical variable is offered. Emergent from this work is the generation of an optimal data set, that is, the minimal set of data to provide evidence that still allows determination of patient state and safe practice. Current status and results from an initial study are reported