Background: Acute respiratory distress syndrome (ARDS) is a clinical syndrome characterized by acute hypoxemia and bilateral infiltrates in the lung after a triggered injury. A major obstacle in ARDS prevention is the identification of patients at risk of ARDS. The goal of this study was to assess the validity of lung injury prediction score (LIPS) as a predictor of ARDS in the intensive care unit (ICU).
Patients and methods: This is a retrospective observational study conducted in the ICU of Sanglah General Hospital (Bali, Indonesia) in 2019 with 451 subjects were eligible after a systematic random sampling method. Receiver operating characteristics (ROC) analysis was used to assess the ability of LIPS to predict ARDS and determine the best cutoff point for LIPS in predicting ARDS.
Results: The area under ROC curve (AUC) value was 0.86 (95% CI 0.81-0.91). The best cutoff point was at LIPS ≥5 (sensitivity 85.71%, specificity 80.77%). From a cross tabulation calculation, we obtained a relative risk of 18.6 (95% CI 7.4-46.77). A logistic regression analysis obtained an odds ratio of 1.71 (95% CI 1.45-2.03).
Conclusion: LIPS is valid for predicting the incidence of ARDS in ICU patients. It can be used as a screening tool to identify those with a high risk of developing ARDS.