Skip to main content

Table 4 The results of each evaluation parameter for each model test set

From: Study on medical dispute prediction model and its clinical-application effectiveness based on machine learning

Model

Best cutoff

Accuracy

Sensitivity

Specificity

PPV

AP

F1 score

Logistic regression

0.450

0.774

0.756

0.732

0.725

0.666

0.740

Random forest

0.495

0.887

0.887

0.886

0.879

0.834

0.880

Decision Tree classifier

0.500

0.828

0.835

0.821

0.814

0.773

0.834

Gaussian NB

0.423

0.696

0.413

0.959

0.905

0.657

0.567

Bagging classifier

0.550

0.840

0.817

0.862

0.847

0.783

0.821

AdaBoost classifier

0.500

0.854

0.822

0.878

0.863

0.795

0.842