Information Modeling for Real-Time Decision Support in Intensive Medicine

Intensive medicine is a very attractive field for applying knowledge discovery in databases due to the great amount of data that is gathered everyday in intensive care units. It is known that one can extract previously unknown knowledge from that data in order to create prediction and decision models. The challenge is to per-form those tasks in real-time, in order to assist the doctors in the decision making process. Moreover, the models can be continuously assessed and optimized, if necessary, to maintain a certain accuracy. In this paper we present an adjustment to the INTCare system, an intelligent decision support system for intensive medicine and propose an information model to support it. We focus on the automatization of data acquisition avoiding human intervention, describing its steps and some requirements.