Skip to main content

Table 3 Evaluation of XGBoost model performance in the training set and testing set

From: Machine learning prediction model of prolonged delay to loop ileostomy closure after rectal cancer surgery: a retrospective study

 

Training set

Testing set

AUC

0.744(0.686–0.802)

0.809(0.728–0.889)

Sensitivity

0.939(0.907–0.971)

0.945(0.898–0.992)

Specificity

0.312(0.220–0.405)

0.415(0.264–0.565)

PPV

0.753(0.701–0.805)

0.782(0.705–0.859)

NPV

0.698(0.560–0.835)

0.773(0.598–0.948)

F1 score

0.836

0.856

  1. AUC: area under the receiver operating characteristic curve. PPV: Positive predictive value. NPV: Negative predictive value
Back to article page

World Journal of Surgical Oncology

ISSN: 1477-7819

Contact us