Biomarkers of lung epithelial injury and inflammation distinguish severe sepsis patients with acute respiratory distress syndrome

Abstract

Introduction: Despite recent modifications, the clinical definition of the acute respiratory distress syndrome (ARDS) remains non-specific, leading to under-diagnosis and under-treatment. This study was designed to test the hypothesis that a biomarker panel would be useful for biologic confirmation of the clinical diagnosis of ARDS in patients at risk of developing ARDS due to severe sepsis.

Methods: This was a retrospective case control study of 100 patients with severe sepsis and no evidence of ARDS compared to 100 patients with severe sepsis and evidence of ARDS on at least two of their first four ICU days. A panel that included 11 biomarkers of inflammation, fibroblast activation, proteolytic injury, endothelial injury, and lung epithelial injury was measured in plasma from the morning of ICU day two. A backward elimination model building strategy on 1,000 bootstrapped data was used to select the best performing biomarkers for further consideration in a logistic regression model for diagnosis of ARDS.

Results: Using the five best-performing biomarkers (surfactant protein-D (SP-D), receptor for advanced glycation end-products (RAGE), interleukin-8 (IL-8), club cell secretory protein (CC-16), and interleukin-6 (IL-6)) the area under the receiver operator characteristic curve (AUC) was 0.75 (95% CI: 0.7 to 0.84) for the diagnosis of ARDS. The AUC improved to 0.82 (95% CI: 0.77 to 0.90) for diagnosis of severe ARDS, defined as ARDS present on all four of the first four ICU days.

Conclusions: Abnormal levels of five plasma biomarkers including three biomarkers generated by lung epithelium (SP-D, RAGE, CC-16) provided excellent discrimination for diagnosis of ARDS in patients with severe sepsis. Altered levels of plasma biomarkers may be useful biologic confirmation of the diagnosis of ARDS in patients with sepsis, and also potentially for selecting patients for clinical trials that are designed to reduce lung epithelial injury.

Figure 1

Receiver operator characteristic (ROC) curve analysis of the plasma biomarker panels for differentiating ARDS (cases) from controls. Predicted probability of ARDS for each subject was computed from a logistic regression model that includes the top five biomarkers (SP-D, RAGE, IL-8, CC-16 and IL-6). Specificity and sensitivity were computed at each possible cutoff of the predicted probability. Three ROC analyses are shown. The solid line shows the ROC analysis for all 200 patients in the study (100 cases, 100 controls). The AUC is 0.75 (95% CI: 0.7 to 0.84). The dashed line shows the ROC analysis using only the 91 cases who had ARDS at the time of the blood draw for biomarker measurement as well as their matched controls. The AUC for this model is 0.78 (95% CI: 0.74 to 0.87). The dotted line shows the ROC analysis using only the 66 patients who had the most severe ARDS (ARDS on all study days) and their matched controls. The AUC for this model is 0.82 (95% CI: 0.77 to 0.90). ROC, receiver operator characteristic curve; ARDS, acute respiratory distress syndrome; SP-D, surfactant protein D; RAGE, receptor for advanced glycation endproducts; IL-8, interleukin 8; CC16, club cell protein-16; IL-6, interleukin 6; AUC, area under the receiver operator characteristic curve; CI, confidence interval.

Figure 2

The multivariable logistic regression model was used to create a prediction model nomogram for the probability of ARDS. A value in each biomarker predictor variable corresponds to a point scale at the top. The sum of the individual predictor variable points corresponds to the total points and the probability of ARDS shown at the bottom. For each predictor variable, the shown values are approximately 1st, 5th, 25th, 50th, 75th, 95th, and 99th percentiles. ARDS, acute respiratory distress syndrome.