Ventilator-associated pneumonia in injured patients: do you trust your Gram's stain?

Abstract

Background: The results of sputum or bronchoalveolar lavage (BAL) fluid Gram's stain have been used to guide presumptive antibiotic therapy for ventilator-associated pneumonia (VAP) in injured patients, despite reported variability in sensitivity, specificity, positive predictive value, negative predictive value, and accuracy. Our aim was to evaluate the utility of Gram's stain of BAL fluid in the diagnosis of VAP.

Methods: We conducted a retrospective chart review of all mechanically ventilated trauma patients who developed pneumonia over a 5-year period in whom Gram's stain and final culture data were available.

Results: One hundred fifty-five records with complete data sets were reviewed. VAP was diagnosed by Centers for Disease Control and Prevention criteria and confirmed by BAL and quantitative culture in all patients. Overall accuracy of Gram's stain in diagnosing VAP for any organism was 88% (137 true-positives). When assessed for the ability to predict pneumonia caused by a specific organism, the accuracy decreased significantly, with only 63% of Gram-negative VAPs and 72% of Gram-positive VAPs accurately identified by Gram's stain. However, the absence of Gram-positive organism of Gram's stain excludes Gram-positive VAP in 80% of patients.

Conclusion: All trauma patients should be covered presumptively for gram-negative organisms, as they encompass 70% of infections, but are not reliably identified by Gram's stain. As 88% of VAP can be identified by the presence of any organism on Gram's stain, it may be useful in the early diagnosis of VAP but cannot reliably be used to guide presumptive therapy.