Table 2 Performance evaluation of eight machine learning algorithms.

From: Development and validation of a prediction tool for intraoperative blood transfusion in brain tumor resection surgery: a retrospective analysis

 

CE

AUC

ACC

PRAUC

Precision

KNN

0.217

0.776

0.783

0.585

0.643

LDA

0.193

0.826

0.807

0.678

0.706

LR

0.185

0.828

0.815

0.682

0.736

Naïve Bayes

0.204

0.815

0.796

0.617

0.653

SVM

0.199

0.799

0.801

0.646

0.721

Ranger

0.196

0.825

0.804

0.689

0.732

Xgboost

0.244

0.755

0.756

0.596

0.547

Nnet

0.199

0.775

0.802

0.610

0.728

  1. ACC Accuracy, AUC Area under the curve, CE Classification error, Xgboost Extremely gradient boosting machine, KNN K near neighbor algorithm, LDA Linear discriminant analysis, LR Logistic regression, PRAUC Precision and recall area under the curve, Nnet Neural net, SVM Support vector machine.
Back to article page