Development and validation of a predictive mortality scoring model for bloodstream infections due to Escherichia coli in the PROBAC cohort

Introduction Escherichia coli is the most frequent cause of bacteraemia and has a major impact on morbidity and mortality. The aim of this study is to define and internally validate a predictive risk score of 30-day all-cause mortality. Methods A prospective, multicentre, cohort study conducted in 26 Spanish hospitals between October 2016 and March 2017 was performed. All monomicrobial E. coli bloodstream infections (BSIs) were included. The primary outcome was 30-day all-cause mortality. Cases were randomized to a derivation cohort (DC) and a validation cohort (VC). The predictive score was calculated from a multivariable model performed by logistic regression in the DC and subsequently applied to the VC. The predictive ability of the model was estimated by calculating the area under the ROC curve (AUROC) and the goodness of fit by Hosmer-Lemeshow test and calibration plot. Results Overall, 1435 cases were included in the DC and 715 in the VC. The final multivariable model for mortality in DC included (adjusted OR; 95% CI) age over 55 years (2.10; 1.01-4.36), dementia (2.08; 1.24-3.50), liver disease (1.81; 0.99-3.28), healthcare-associated acquisition (2.29; 1.52-3.44), Pitt index > 3 (3.59; 2.30-5.61), SOFA >= 2 (1.66; 1.04-2.64), and urinary tract source (0.37; 0.24-0.56). The predictive score showed an AUROC of 0.78 (95% CI 0.74-0.83) in the DC and 0.78 (95% CI 0.73-0.84) in the VC. Conclusion We developed and internally validated a predictive scoring model to identify patients with E. coli bacteraemia at high and low risk of crude mortality on day 30 of BSI.