Electronic Healthcare. Third International Conference, eHealth 2010, Casablanca, Morocco, December 13-15, 2010, Revised Selected Papers

Research Article

Predicting Sepsis: A Comparison of Analytical Approaches

Download
432 downloads
  • @INPROCEEDINGS{10.1007/978-3-642-23635-8_12,
        author={Femida Gwadry-Sridhar and Ali Hamou and Benoit Lewden and Claudio Martin and Michael Bauer},
        title={Predicting Sepsis: A Comparison of Analytical Approaches},
        proceedings={Electronic Healthcare. Third International Conference, eHealth 2010, Casablanca, Morocco, December 13-15, 2010, Revised Selected Papers},
        proceedings_a={E-HEALTH},
        year={2012},
        month={10},
        keywords={},
        doi={10.1007/978-3-642-23635-8_12}
    }
    
  • Femida Gwadry-Sridhar
    Ali Hamou
    Benoit Lewden
    Claudio Martin
    Michael Bauer
    Year: 2012
    Predicting Sepsis: A Comparison of Analytical Approaches
    E-HEALTH
    Springer
    DOI: 10.1007/978-3-642-23635-8_12
Femida Gwadry-Sridhar1,*, Ali Hamou1,*, Benoit Lewden1,*, Claudio Martin2,*, Michael Bauer2,*
  • 1: Lawson Health Research Institute
  • 2: University of Western Ontario
*Contact email: femida.gwadry-sridhar@lhsc.on.ca, ali.hamou@sjhc.london.on.ca, benoit.lewden@lawsonresearch.com, cmartin@lhsc.on.ca, bauer@csd.uwo.ca

Abstract

Sepsis is a significant cause of mortality and morbidity and is often associated with increased hospital resource utilization, prolonged intensive care unit and hospital stay. With advances in medicine, there is now aggressive goal oriented treatments that can be used to help patients that may be at risk for sepsis. To predict this risk, we hypothesized that commonly used univariate and multivariate models could be enhanced by using multiple analytic methods to providing greater precision. As a first step, we analyze data about patients with and without sepsis using multiple regression, decision trees and cluster analysis. We compare the predictive accuracy of the three different approaches in predicting which patients are likely (or not likely) to develop sepsis. The precision analysis suggests that decision trees may provide a better predictive model than either regression methods or cluster analysis.