Skip to main content
. 2019 Feb 13;9(1):20. doi: 10.3390/diagnostics9010020

Table 1.

Mean test set AUROC for the Machine Learning Diagnostic (MLD) and comparators when used to diagnose sepsis for patients aged ≥45 years and with stays of ≥96 h. Abbreviations: DOR = diagnostic odds ratio; PPV = positive predictive value; NPV = negative predictive value. To facilitate comparison with the MLD, the diagnosis score thresholds for SIRS, MEWS, and qSOFA were chosen so as to produce a sensitivity nearest 0.80. Performance metrics were averaged over 10-fold cross-validation.

Metric MLD SIRS MEWS qSOFA
AUROC 0.917 0.468 0.639 0.653
Sensitivity 0.799 0.835 0.774 0.663
Specificity 0.860 0.036 0.317 0.531
PPV 0.566 0.166 0.206 0.244
NPV 0.949 0.489 0.860 0.873
DOR 24.4 0.190 1.59 2.23
Accuracy 0.848 0.185 0.402 0.556