Predicting Sepsis: A Comparison of Analytical Approaches
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.
KeywordsIntensive Care Unit Decision Tree Septic Shock Severe Sepsis Intensive Care Unit Patient
Unable to display preview. Download preview PDF.
- 6.American College of Chest Physicians/Society of Critical Care Medicine Consensus Conference: definitions for sepsis and organ failure and guidelines for the use of innovative therapies in sepsis. Crit. Care Med. 20(6), 864–74 (1992)Google Scholar
- 8.Martin, C., Priestap, F., Fisher, H., et al.: A prospective, observational registry of patients with severe sepsis: The Canadian Sepsis Treatment And Response (STAR) Registry. Crit. Care Med. (2009) (in press)Google Scholar
- 16.Quinlan, J.R.: Induction of decision trees. Machine Learning 1, 81–106 (1986)Google Scholar