Data mining for real-time intelligent decision support system in intensive care medicine

Abstract

The introduction of Intelligent Decision Support Systems (IDSS) in critical areas like Intensive Medicine is a complex and difficult process. The professionals of Intensive Care Units (ICU) haven’t much time to register data because the direct care to the patients is always mandatory. In order to help doctors in the decision making process, the INTCare system has been deployed in the ICU of Centro Hospitalar of Porto, Portugal. INTCare is an IDSS that makes use of data mining models to predict the outcome and the organ failure probability for the ICU patients. This paper introduces the work carried out in order to automate the processes of data acquisition and data mining. The main goal of this work is to reduce significantly the manual efforts of the staff in the ICU. All the processes are autonomous and are executed in real-time. In particular, Decision Trees, Support Vector Machines and Naïve Bayes were used with online data to continuously adapt the predictive models. The data engineering process and achieved results, in terms of the performance attained, will be presented.