Intelligent Management of Sepsis in the Intensive Care Unit

View Sample PDF

Author(s): Vicent J. Ribas (Universitat Politècnica de Catalunya, Spain), Juan Carlos Ruiz-Rodríguez (Institut de Recerca Vall d’ Hebron (VHIR). Universitat Autònoma de Barcelona, Spain)and Alfredo Vellido (Universitat Politècnica de Catalunya, Spain)
Copyright: 2012
Pages: 16
Source title: Medical Applications of Intelligent Data Analysis: Research Advancements
Source Author(s)/Editor(s): Rafael Magdalena-Benedito (Intelligent Data Analysis Laboratory, University of Valencia, Spain), Emilio Soria-Olivas (Intelligent Data Analysis Laboratory, University of Valencia, Spain), Juan Guerrero Martínez (Intelligent Data Analysis Laboratory, University of Valencia, Spain), Juan Gómez-Sanchis (Intelligent Data Analysis Laboratory, University of Valencia, Spain)and Antonio Jose Serrano-López (Intelligent Data Analysis Laboratory, University of Valencia, Spain)
DOI: 10.4018/978-1-4666-1803-9.ch001

Keywords: Health Information Systems / Medical Information Science Reference / Medicine & Healthcare

Purchase

View Intelligent Management of Sepsis in the Intensive Care Unit on the publisher's website for pricing and purchasing information.

Abstract

Sepsis is a transversal pathology and one of the main causes of death in the Intensive Care Unit (ICU). It has in fact become the tenth most common cause of death in western societies. Its mortality rates can reach up to 60% for Septic Shock, its most acute manifestation. For these reasons, the prediction of the mortality caused by Sepsis is an open and relevant medical research challenge. This problem requires prediction methods that are robust and accurate, but also readily interpretable. This is paramount if they are to be used in the demanding context of real-time decision making at the ICU. In this brief contribution, three different methods are presented. One is based on a variant of the well-known support vector machine (SVM) model and provides and automated ranking of relevance of the mortality predictors while the other two are based on logistic-regression and logistic regression over latent Factors. The reported results show that the methods presented outperform in terms of accuracy alternative techniques currently in use in clinical settings, while simultaneously assessing the relative impact of individual pathology indicators.

The IRMA Community

Research IRM

Intelligent Management of Sepsis in the Intensive Care Unit

Purchase

Abstract

Related Content

IRMA Sponsors