Table 2 Diagnostic performance of different machine models for infected stones in the validation set.

From: Constructing a machine learning model for systemic infection after kidney stone surgery based on CT values

Model

AUC

Accuracy

Sensitivity

Specificity

PPV

NPV

F1

XGB

0.858

0.841

0.877

0.981

0.629

0.852

0.730

LR

0.818

0.721

0.769

0.711

0.330

0.943

0.462

GNB

0.858

0.764

0.846

0.749

0.384

0.963

0.528

SVM

0.690

0.836

0.701

0.791

0.697

0.843

0.511

MLP

0.745

0.796

0.487

0.853

0.381

0.901

0.427

  1. AUC, area under the receiver operating characteristic curve; XGBoost, Extreme Gradient Boosting; LR, logistic regression; GNB, Gaussian Naive Bayes; SVM, Support Vector Machine; MLP, Multilayer Perceptron; PPV, Positive predictive value; NPV, Negative predictive value.
Back to article page