The value of five scoring systems in predicting the prognosis of patients with sepsis associated-acute respiratory failure

Abstract

Abstract This study aims to find the optimal scoring system to predict the prognosis of patients with sepsis associated-acute respiratory failure (SA-ARF). All data were taken from the fourth version of the Markets in Intensive Care Medicine (MIMIC-IV) database. Independent risk factors for death in hospital were confirmed by regression analysis. The predictive value of five scoring systems was evaluated by Receiving Operating Characteristic Curves (ROC). Kaplan-Meier curves elucidated the impact of APSIII scores on patient survival and prognosis. Decision curve analysis (DCA) identified a scoring system with the highest net clinical benefit. ROC curve analysis showed that APSIII (AUC: 0.755, 95%Cl: 0.714–0.768) and LODS (AUC: 0.731, 95%Cl: 0.717–0.7745) were better than SAPS II (AUC: 0.727, 95% CI: 0.713–0.741), OASIS (AUC: 0.706, 95% CI: 0.691–0.720) and SOFA (AUC: 0.606, 95% CI: 0.590–0.621) in assessing in-hospital mortality. Kaplan-Meier survival analysis revealed that the high APS III score group had a considerably poorer median survival day. DCA curve showed that APS III has the greatest net clinical net benefit. APS III is a better predictor of in-hospital mortality than SAPS II, LODS, OASIS, and SOFA. APS III is the excellent one for predicting death in hospital for patients with SA-ARF.