Skip to main content

Table 2 Predictive performance comparison of different machine learning models in the test set

From: A non-invasive preoperative prediction model for predicting axillary lymph node metastasis in breast cancer based on a machine learning approach: combining ultrasonographic parameters and breast gamma specific imaging features

ML model

Accuracy

Kappa

Sensitivity

Specificity

PPV

NPV

AUC

GLM

0.758

0.453

0.487

0.933

0.826

0.737

0.774

RF

0.778

0.508

0.564

0.917

0.815

0.764

0.78

SVM

0.737

0.445

0.641

0.8

0.676

0.774

0.794

NNET

0.768

0.507

0.667

0.833

0.722

0.794

0.768

GBM

0.737

0.435

0.59

0.833

0.697

0.758

0.784

XGB

0.737

0.435

0.59

0.833

0.697

0.758

0.782

  1. ML: machine learning; GLM: generalized linear model; RF: random forest; SVM: support vector machine; NNET: neural network; GBM: gradient boosting machine; XGB: extreme boosting machine; PPV: Positive predictive value; NPV: Negative predictive value; AUC: the area under the ROC curve.
Back to article page

Radiation Oncology

ISSN: 1748-717X

Contact us