Severe sepsis mortality prediction with logistic regression over latent factors

Authors:
Vicent J. Ribas;Alfredo Vellido;Juan Carlos Ruiz-Rodríguez;Jordi Rello
Affiliations:
Dept. de Llenguatges i Sistemes Informítics, Universitat Politècnica de Catalunya, Edifici Omega, Campus Nord, 08034 Barcelona, Spain;Dept. de Llenguatges i Sistemes Informítics, Universitat Politècnica de Catalunya, Edifici Omega, Campus Nord, 08034 Barcelona, Spain;Grup de Recerca en Shock, Disfunció Orgínica i Ressuscitació (SODIR) Servei de Medicina Intensiva, Hospital Universitari Vall d' Hebron, Universitat Autònoma de Barcelona, Spai ...;CRIPS Research Group, Servei de Medicina Intensiva, Hospital Universitari Vall d' Hebron, Universitat Autònoma de Barcelona, Spain and (CIBERES) Centro de Investigación Biomédica en ...
Venue:
Expert Systems with Applications: An International Journal
Year:
2012

Citing 4
Cited 0

Bagging predictors

Machine Learning
Comparing performances of logistic regression, classification and regression tree, and neural networks for predicting coronary artery disease

Expert Systems with Applications: An International Journal
Review: Neural networks and statistical techniques: A review of applications

Expert Systems with Applications: An International Journal
Application notes: data mining in cancer research

IEEE Computational Intelligence Magazine

Quantified Score

Hi-index	12.05

Visualization

Abstract

Sepsis is one of the main causes of death for non-coronary ICU (Intensive Care Unit) patients and has become the 10th most common cause of death in western societies. This is a transversal condition affecting immunocompromised patients, critically ill patients, post-surgery patients, patients with AIDS, and the elderly. In western countries, septic patients account for as much as 25% of ICU bed utilization and the pathology affects 1-2% of all hospitalizations. Its mortality rates range from 12.8% for sepsis to 45.7% for septic shock. The prediction of mortality caused by sepsis is, therefore, a relevant research challenge from a medical viewpoint. The clinical indicators currently in use for this type of prediction have been criticized for their poor prognostic significance. In this study, we redescribe sepsis indicators through latent model-based feature extraction, using factor analysis. These extracted indicators are then applied to the prediction of mortality caused by sepsis. The reported results show that the proposed method improves on the results obtained with the current standard mortality predictor, which is based on the APACHE II score.