Developing a gene expression model for predicting ventilator-associated pneumonia in trauma patients

A pilot study

Joseph Swanson, G Christopher Wood, Lijing Xu, Lisa E. Tang, Bernd Meibohm, Ramin Homayouni, Martin Croce, Timothy Fabian

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Background: Ventilator-associated pneumonia (VAP) carries significant mortality and morbidity. Predicting which patients will become infected could lead to measures to reduce the incidence of VAP. Methodology/Principal Findings: The goal was to begin constructing a model for VAP prediction in critically-injured trauma patients, and to identify differentially expressed genes in patients who go on to develop VAP compared to similar patients who do not. Gene expression profiles of lipopolysaccharide stimulated blood cells in critically injured trauma patients that went on to develop ventilator-associated pneumonia (n = 10) was compared to those that never developed the infection (n = 10). Eight hundred and ten genes were differentially expressed between the two groups (ANOVA, P<0.05) and further analyzed by hierarchical clustering and principal component analysis. Functional analysis using Gene Ontology and KEGG classifications revealed enrichment in multiple categories including regulation of protein translation, regulation of protease activity, and response to bacterial infection. A logistic regression model was developed that accurately predicted critically-injured trauma patients that went on to develop VAP (VAP+) and those that did not (VAP-). Five genes (PIK3R3, ATP2A1, PI3, ADAM8, and HCN4) were common to all top 20 significant genes that were identified from all independent training sets in the cross validation. Hierarchical clustering using these five genes accurately categorized 95% of patients and PCA visualization demonstrated two discernable groups (VAP+ and VAP-). Conclusions/Significance: A logistic regression model using cross-validation accurately predicted patients that developed ventilator-associated pneumonia and should now be tested on a larger cohort of trauma patients.

Original languageEnglish (US)
Article numbere42065
JournalPloS one
Volume7
Issue number8
DOIs
StatePublished - Aug 15 2012

Fingerprint

Ventilator-Associated Pneumonia
ventilators
Gene expression
pneumonia
Genes
Gene Expression
gene expression
Wounds and Injuries
Logistics
Logistic Models
genes
Functional analysis
Analysis of variance (ANOVA)
Cluster Analysis
Principal component analysis
Ontology
Lipopolysaccharides
Blood
Peptide Hydrolases
Visualization

All Science Journal Classification (ASJC) codes

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Developing a gene expression model for predicting ventilator-associated pneumonia in trauma patients : A pilot study. / Swanson, Joseph; Wood, G Christopher; Xu, Lijing; Tang, Lisa E.; Meibohm, Bernd; Homayouni, Ramin; Croce, Martin; Fabian, Timothy.

In: PloS one, Vol. 7, No. 8, e42065, 15.08.2012.

Research output: Contribution to journalArticle

@article{11b7ed9dbd1240be965f1649299a320c,
title = "Developing a gene expression model for predicting ventilator-associated pneumonia in trauma patients: A pilot study",
abstract = "Background: Ventilator-associated pneumonia (VAP) carries significant mortality and morbidity. Predicting which patients will become infected could lead to measures to reduce the incidence of VAP. Methodology/Principal Findings: The goal was to begin constructing a model for VAP prediction in critically-injured trauma patients, and to identify differentially expressed genes in patients who go on to develop VAP compared to similar patients who do not. Gene expression profiles of lipopolysaccharide stimulated blood cells in critically injured trauma patients that went on to develop ventilator-associated pneumonia (n = 10) was compared to those that never developed the infection (n = 10). Eight hundred and ten genes were differentially expressed between the two groups (ANOVA, P<0.05) and further analyzed by hierarchical clustering and principal component analysis. Functional analysis using Gene Ontology and KEGG classifications revealed enrichment in multiple categories including regulation of protein translation, regulation of protease activity, and response to bacterial infection. A logistic regression model was developed that accurately predicted critically-injured trauma patients that went on to develop VAP (VAP+) and those that did not (VAP-). Five genes (PIK3R3, ATP2A1, PI3, ADAM8, and HCN4) were common to all top 20 significant genes that were identified from all independent training sets in the cross validation. Hierarchical clustering using these five genes accurately categorized 95{\%} of patients and PCA visualization demonstrated two discernable groups (VAP+ and VAP-). Conclusions/Significance: A logistic regression model using cross-validation accurately predicted patients that developed ventilator-associated pneumonia and should now be tested on a larger cohort of trauma patients.",
author = "Joseph Swanson and Wood, {G Christopher} and Lijing Xu and Tang, {Lisa E.} and Bernd Meibohm and Ramin Homayouni and Martin Croce and Timothy Fabian",
year = "2012",
month = "8",
day = "15",
doi = "10.1371/journal.pone.0042065",
language = "English (US)",
volume = "7",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "8",

}

TY - JOUR

T1 - Developing a gene expression model for predicting ventilator-associated pneumonia in trauma patients

T2 - A pilot study

AU - Swanson, Joseph

AU - Wood, G Christopher

AU - Xu, Lijing

AU - Tang, Lisa E.

AU - Meibohm, Bernd

AU - Homayouni, Ramin

AU - Croce, Martin

AU - Fabian, Timothy

PY - 2012/8/15

Y1 - 2012/8/15

N2 - Background: Ventilator-associated pneumonia (VAP) carries significant mortality and morbidity. Predicting which patients will become infected could lead to measures to reduce the incidence of VAP. Methodology/Principal Findings: The goal was to begin constructing a model for VAP prediction in critically-injured trauma patients, and to identify differentially expressed genes in patients who go on to develop VAP compared to similar patients who do not. Gene expression profiles of lipopolysaccharide stimulated blood cells in critically injured trauma patients that went on to develop ventilator-associated pneumonia (n = 10) was compared to those that never developed the infection (n = 10). Eight hundred and ten genes were differentially expressed between the two groups (ANOVA, P<0.05) and further analyzed by hierarchical clustering and principal component analysis. Functional analysis using Gene Ontology and KEGG classifications revealed enrichment in multiple categories including regulation of protein translation, regulation of protease activity, and response to bacterial infection. A logistic regression model was developed that accurately predicted critically-injured trauma patients that went on to develop VAP (VAP+) and those that did not (VAP-). Five genes (PIK3R3, ATP2A1, PI3, ADAM8, and HCN4) were common to all top 20 significant genes that were identified from all independent training sets in the cross validation. Hierarchical clustering using these five genes accurately categorized 95% of patients and PCA visualization demonstrated two discernable groups (VAP+ and VAP-). Conclusions/Significance: A logistic regression model using cross-validation accurately predicted patients that developed ventilator-associated pneumonia and should now be tested on a larger cohort of trauma patients.

AB - Background: Ventilator-associated pneumonia (VAP) carries significant mortality and morbidity. Predicting which patients will become infected could lead to measures to reduce the incidence of VAP. Methodology/Principal Findings: The goal was to begin constructing a model for VAP prediction in critically-injured trauma patients, and to identify differentially expressed genes in patients who go on to develop VAP compared to similar patients who do not. Gene expression profiles of lipopolysaccharide stimulated blood cells in critically injured trauma patients that went on to develop ventilator-associated pneumonia (n = 10) was compared to those that never developed the infection (n = 10). Eight hundred and ten genes were differentially expressed between the two groups (ANOVA, P<0.05) and further analyzed by hierarchical clustering and principal component analysis. Functional analysis using Gene Ontology and KEGG classifications revealed enrichment in multiple categories including regulation of protein translation, regulation of protease activity, and response to bacterial infection. A logistic regression model was developed that accurately predicted critically-injured trauma patients that went on to develop VAP (VAP+) and those that did not (VAP-). Five genes (PIK3R3, ATP2A1, PI3, ADAM8, and HCN4) were common to all top 20 significant genes that were identified from all independent training sets in the cross validation. Hierarchical clustering using these five genes accurately categorized 95% of patients and PCA visualization demonstrated two discernable groups (VAP+ and VAP-). Conclusions/Significance: A logistic regression model using cross-validation accurately predicted patients that developed ventilator-associated pneumonia and should now be tested on a larger cohort of trauma patients.

UR - http://www.scopus.com/inward/record.url?scp=84865048413&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865048413&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0042065

DO - 10.1371/journal.pone.0042065

M3 - Article

VL - 7

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 8

M1 - e42065

ER -