M. Szomszor and P. Kostkova (Eds.): E-Health 2010, LNICST 69, pp. 95–102, 2011. © Springer-Verlag Berlin Heidelberg 2011 Predicting Sepsis: A Comparison of Analytical Approaches Femida Gwadry-Sridhar 1 , Ali Hamou 1 , Benoit Lewden 1 , Claudio Martin 2 , and Michael Bauer 3 1 I-THINK Research Lab, Lawson Health Research Institute, London, ON Canada 2 Dept of Medicine and Physiology, University of Western Ontario, London, ON Canada 3 Dept of Computer Science, University of Western Ontario, London, ON Canada 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. 1 Introduction Sepsis is defined as infection plus systematic manifestations of infection [1]. Severe sepsis is considered present when sepsis co-exists with sepsis-induced organ dysfunction or tissue hypo-perfusion [1]. Sepsis can result in mortality and morbidity, especially when associated with shock and/or organ dysfunction [2]. This can be associated with increased hospital resource utilization, prolonged intensive care unit (ICU) and hospital stay, decreased long-term health related quality of life and an economic burden estimated at US $17 billion each year in the United States alone [3]. In Canada, there is limited data on the burden of severe sepsis; however, costs in Quebec may be as high as $73M per year [4], which contribute to estimates of total Canadian cost of approximately $325M per year. Patients with severe sepsis generally receive their care in the ICU. A multinational study of sepsis in teaching hospitals found that severe sepsis or septic shock is present or develops in 15% of ICU patients [5]. However, diagnosing sepsis is difficult because there is no “typical” presentation despite published definitions for sepsis [6- 7]. In the Canadian Sepsis Treatment and Response (STAR) registry [8] the total rate for severe sepsis was 19%. Of these, 63% occurred after hospitalization.