Real-time prediction of organ failure and outcome in intensive medicine

Nowadays, there is a trend to use Data Mining models in the context of decision support for intensive medicine. Previous research has used offline data for predicting organ failure and outcome for the next day. This paper presents the INTCare system, an Intelligent Decision Support System for intensive medicine. Advances in INTCare led to a new goal, the prediction for the next hour, with real-time data, gathered in the Intensive Care Unit of Hospital Geral de Santo António, Oporto, Portugal. Interesting results were achieved, proving that it is possible to use online and real-time data to make accurate predictions for the next hour. This new approach represents an advance in intensive medicine, for hourly prediction will allow doctors to have a proactive attitude, with timely intervention, in order to avoid serious complications in the patients' clinical condition.