A Markov analysis of patients developing sepsis using clusters

Authors:
Femida Gwadry-Sridhar;Michael Bauer;Benoit Lewden;Ali Hamou
Affiliations:
I-THINK Research Lab, Lawson Health Research Institute, London, ON, Canada;University of Western Ontario, London, ON, Canada;I-THINK Research Lab, Lawson Health Research Institute, London, ON, Canada;I-THINK Research Lab, Lawson Health Research Institute, London, ON, Canada
Venue:
KR4HC'10 Proceedings of the ECAI 2010 conference on Knowledge representation for health-care
Year:
2010

Citing 2
Cited 1

A Data Mining Alternative to Model Hospital Operations: Filtering, Adaption and Behaviour Prediction

ISMDA '00 Proceedings of the First International Symposium on Medical Data Analysis
The Analysis of Hospital Episodes

ISMDA '01 Proceedings of the Second International Symposium on Medical Data Analysis

Analysis of treatment compliance of patients with diabetes

KR4HC'11 Proceedings of the 3rd international conference on Knowledge Representation for Health-Care

Quantified Score

Hi-index	0.00

Visualization

Abstract

Sepsis is a significant cause of mortality and morbidity. There are now aggressive goal oriented treatments that can be used to help patients suffering from sepsis. By predicting which patients are more likely to develop sepsis, early treatment can potentially reduce their risks. However, diagnosing sepsis is difficult since there is no "standard" presentation, despite many published definitions of this condition. In this work, data from a large observational cohort of patients - with variables collected at varying time periods - are observed in order to determine whether sepsis develops or not. A cluster analysis approach is used to form groups of correlated datapoints. This sequence of datapoints is then categorized on a per person basis and the frequency of transitioning from one grouping to another is computed. The result is posed as a Markov model which can accurately estimate the likelihood of a patient developing sepsis. A discussion of the implications and uses of this model is presented.