INTCare A Knowledge Discovery based Intelligent Decision Support System for Intensive Care.pdf

Title of the journal. Volume X – no X/2002, pages 1 to n INTCare: A Knowledge Discovery based Intelligent Decision Support System for Intensive Care Medicine Pedro Gago * — Manuel Filipe Santos** — álvaro Silva*** Paulo Cortez** — José Neves**** — Lopes Gomes *** *Escola Superior de Tecnologia e Gest?o do Instituto Politécnico de Leiria Morro do Lena, Alto Vieiro – Leiria – Portugal pgago@estg.ipleiria.pt **Departamento de Sistemas de Informa??o da Universidade do Minho Campus de Azurém - Guimar?es - Portugal mfs@dsi.uminho.pt pcortez@dsi.uminho.pt ***Instituto de Ciências Biomédicas Abel Salazar Porto – Portugal a.moreira.silva@mail.telepac.pt cardiologia.hgsa@mail.telepac.pt **** Departamento de Informática da Universidade do Minho Braga – Portugal jneves@di.uminho.pt ABSTRACT. This paper introduces the INTCare system, an intelligent information system based on a completely automated Knowledge Discovery process and on the Agents paradigm. The system was designed to work in Hospital Intensive Care Units, supporting the physicians’ decisions by means of prognostic Data Mining models. In particular, these techniques were used to predict organ failure and mortality assessment. The main intention is to change the current reactive behaviour to a pro-active one, enhancing the quality of service. Current applications and experimentations, the functional and structural aspects, and technological options are presented. 2 Title of the journal. Volume X – no X/2002 RéSUMé. Cet article présente INTCare, un système dinformation intelligent basé sur un procédé complètement automatisé de découverte de la connaissance et sur le paradigme dagents. Le système a été con?u pour fonctionner dans les services hospitaliers de réanimation, soutenant les décisions des médecins au moyen de modèles dextraction de données pronostiques. En particulier, ces techniques ont été employées pour prévoir léchec dorganes et lévaluation