Table 5 Model evaluation.

From: Development and validation of a novel risk assessment model to estimate the probability of pulmonary embolism in postoperative patients

Index

Training set

Testing set

AUC

0.949 [0.932–0.966]

0.958 [0.944–0.972]

ACC

0.888 [0.888–0.888]

0.91 [0.91–0.91]

SEN

0.909 [0.864–0.953]

0.895 [0.837–0.954]

SPE

0.887 [0.882–0.892]

0.91 [0.904–0.915]

PLR

8.07 [7.559–8.616]

9.924 [9.065–10.864]

NLR

0.103 [0.064–0.167]

0.115 [0.066–0.201]

PPV

0.077 [0.066–0.089]

0.095 [0.077–0.114]

NPV

0.999 [0.998–0.999]

0.999 [0.998–1]

  1. AUC: Area under the curve; ACC: Accuracy; SEN: Sensitivity; SPE: Specificity; PLR: Positive likelihood ratio; NLR: Negative likelihood ratio; PPV: Positive predictive value; NPV: Negative predictive value.
Back to article page