Skip to main content

Table 5 Best hyperparameters selected to be fed into the classifiers

From: Optimizing prognostic factors of five-year survival in gastric cancer patients using feature selection techniques with machine learning algorithms: a comparative study

Num

ML Models

Hyper-parameters

F1-score

1

HGB classifier

(‘verbose’:2,’random_state’:999,’n_estimators’:14,’max_deph’:7’criterion’: gini’)

81.32

4

SVM (kernel = RBF)

C = 15, G = 0.004

76.14

5

XG Boost Classifier

‘min_chid_weigh’ = 1’max_depht’ = 16,’learning_rate’ = 0.4, ‘gamma’ = 0.1, ‘colsample_bytree’ = 0.4

83.7