Background: Ventilator-associated pneumonia (VAP) is the most frequent infection with high mortality rates in intensive care units (ICUs) and the prediction of outcome is important in the decision-making process. Objective: To assess the value of the Acute Physiology and Chronic Health Evaluation II (APACHE II), Sequential Organ Failure Assessment ( SOFA) and Clinical Pulmonary Infection Score (CPIS) in the prediction of mortality during VAP episodes in pulmonary patients. Methods: This study was a prospective observational cohort study. Sixty-three patients who were admitted to the ICU and developed VAP were included in the study consecutively. Clinical and laboratory data conforming to the APACHE II and SOFA scores were recorded on admission and APACHE II, SOFA and CPIS scores on the day of the diagnosis of VAP. The outcome measure was the ICU mortality. Logistic regression and receiver operating characteristic (ROC) curve analyses and the area under the curve (AUC) were used to estimate the predictive ability of the scoring systems. Results: Mortality rate was 54%. The mean APACHE II (21 +/- 6, 14 +/- 5; p = 0.001), SOFA (7 +/- 3, 4 +/- 2; p = 0.002) and CPIS (8 +/- 2, 7 +/- 3; p = 0.025) scores determined at the time of VAP diagnosis were significantly higher in nonsurvivors than in survivors. Discrimination was excellent for APACHE II (ROC AUC: 0.81; p = 0.001) and acceptable for SOFA ( ROC AUC: 0.71; p = 0.005) scores. Of the three scores only APACHE II 1 16 was an independent predictor of the mortality ( OR: 5; 95% CI: 1.3 - 18; p = 0.019) in the logistic regression analysis. Conclusion: These results suggest that APACHE II determined at the time of VAP diagnosis may be useful in predicting mortality in the pulmonary ICU patient population who develops VAP. Copyright (C) 2006 S. Karger AG, Basel.