Skip to main content

Table 4 Performance of ML models for stratified 10-fold cross validation. Showing area under the receiver operating characteristic curve (AUC), J-statistic (J stat), sensitivity, and specificity at a classification threshold of 0.5

From: Machine learning pipeline for blood culture outcome prediction using Sysmex XN-2000 blood sample results in Western Australia

ML model

AUC

J stat at 0.5 threshold

Sensitivity at 0.5 threshold

Specificity at 0.5 threshold

XG/CBC/DIFF/CPD/1.5/boruta

\(0.76 \pm 0.04\)

\(0.39 \pm 0.06\)

\(0.74 \pm 0.07\)

\(0.65 \pm 0.02\)

RF/CBC/DIFF/1/boruta

\(0.75 \pm 0.04\)

\(0.34 \pm 0.08\)

\(0.61 \pm 0.08\)

\(0.73 \pm 0.02\)