Email updates

Keep up to date with the latest news and content from Critical Care and BioMed Central.

Open Access Research

Identification of complex metabolic states in critically injured patients using bioinformatic cluster analysis

Mitchell J Cohen1*, Adam D Grossman2, Diane Morabito3, M Margaret Knudson1, Atul J Butte4 and Geoffrey T Manley3

Author Affiliations

1 Department of Surgery, University of California, 505 Parnassus Avenue, San Francisco, CA 94143, USA

2 Department of Bioengineering, Stanford University, 450 Serra Mall, Stanford, CA 94305, USA

3 Department of Neurosurgery, University of California, 505 Parnassus Avenue, San Francisco, CA 94143, USA

4 Departments of Medicine and Pediatrics (Medical Informatics), Stanford University, 450 Serra Mall, Stanford, CA 94305, USA

For all author emails, please log on.

Critical Care 2010, 14:R10  doi:10.1186/cc8864


See related commentary by Buchman, http://ccforum.com/content/14/2/217

Published: 2 February 2010

Abstract

Introduction

Advances in technology have made extensive monitoring of patient physiology the standard of care in intensive care units (ICUs). While many systems exist to compile these data, there has been no systematic multivariate analysis and categorization across patient physiological data. The sheer volume and complexity of these data make pattern recognition or identification of patient state difficult. Hierarchical cluster analysis allows visualization of high dimensional data and enables pattern recognition and identification of physiologic patient states. We hypothesized that processing of multivariate data using hierarchical clustering techniques would allow identification of otherwise hidden patient physiologic patterns that would be predictive of outcome.

Methods

Multivariate physiologic and ventilator data were collected continuously using a multimodal bioinformatics system in the surgical ICU at San Francisco General Hospital. These data were incorporated with non-continuous data and stored on a server in the ICU. A hierarchical clustering algorithm grouped each minute of data into 1 of 10 clusters. Clusters were correlated with outcome measures including incidence of infection, multiple organ failure (MOF), and mortality.

Results

We identified 10 clusters, which we defined as distinct patient states. While patients transitioned between states, they spent significant amounts of time in each. Clusters were enriched for our outcome measures: 2 of the 10 states were enriched for infection, 6 of 10 were enriched for MOF, and 3 of 10 were enriched for death. Further analysis of correlations between pairs of variables within each cluster reveals significant differences in physiology between clusters.

Conclusions

Here we show for the first time the feasibility of clustering physiological measurements to identify clinically relevant patient states after trauma. These results demonstrate that hierarchical clustering techniques can be useful for visualizing complex multivariate data and may provide new insights for the care of critically injured patients.