Table 5 Performance of different machine learning classifiers on the independent test set using the three key predictors (Maximum height, neck inflow rate, and Non-sphericity Index). Shown are the values for accuracy, precision, sensitivity, specificity, and F1-score.

From: Predictive modeling and machine learning show poor performance of clinical, morphological, and hemodynamic parameters for small intracranial aneurysm rupture

Classifier

Accuracy

Precision

Sensitivity

Specificity

F1-score

AdaBoost classifier

0.631

0.339

0.359

0.359

0.347

Support vector machine

0.752

0.556

0.154

0.154

0.229

K-nearest neighbors

0.702

0.398

0.231

0.231

0.287

Stochastic gradient descent

0.695

0.265

0.205

0.205

0.224