Severe sepsis mortality prediction with relevance vector machines

• Published in: 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society Vol. 2011; pp. 100 - 103
• Main Authors: Ribas, Vicent J., Lopez, Jesus Caballero, Ruiz-Sanmartin, Adolf, Ruiz-Rodriguez, Juan Carlos, Rello, Jordi, Wojdel, Anna, Vellido, Alfredo
• Format: Conference Proceeding Journal Article
• Language: English
• Published: United States IEEE 01.01.2011
• Subjects: Accuracy; Electric shock; Hospitals; Humans; Incidence; Logistics; Pathology; Prognosis; Proportional Hazards Models; Reproducibility of Results; Risk Assessment - methods; Risk Factors; Sensitivity and Specificity; Sepsis - mortality; Support Vector Machine; Support vector machines; Survival Analysis; Survival Rate; Training
• ISBN: 9781424441211; 1424441218
• ISSN: 1094-687X; 1557-170X; 1558-4615
• DOI: 10.1109/IEMBS.2011.6089906

Sepsis is a transversal pathology and one of the main causes of death at 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 45.7% 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 paper, such a method is presented. It is based on a variant of the well-known support vector machine (SVM) model and provides an automated ranking of relevance of the mortality predictors. The reported results show that it outperforms in terms of accuracy alternative techniques currently in use, while simultaneously assessing the relative impact of individual pathology indicators.