Table 6.

Inclusion of biomarkers increases the predictive performance of the RAI

ModelAUC Increase in AUC
(95% Confidence Interval)P ValueAIC
RAI0.80135.39
RAI+NGAL0.850.05 (0.01 to 0.09)0.01132.77
RAI+MMP-80.840.04 (0.001 to 0.07)0.04133.23
RAI+Ela-20.870.06 (0.01 to 0.12)0.03125.14
RAI+NGAL+MMP-80.860.06 (0.01 to 0.11)0.03128.97
RAI+NGAL+Ela-20.880.07 (0.01 to 0.14)0.02123.45
RAI+MMP-8+Ela-20.870.06 (0.01 to 0.12)0.03126.93
  • The prediction model of the RAI for day 3 AKI was used as the reference model for evaluating the models incorporating biomarkers NGAL, MMP-8, and Ela-2 individually and in combination. The AUC (c-statistic) and the Akaike information criterion (AIC) were calculated for each model.