Table 11 Optimal hyperparameters were calculated for each model with all three algorithms (RF, SVM, and XGBoost)

1

Choice of initial treatment

Random forest classifier

RandomForestClassifier(bootstrap = True, ccp_alpha = 0.0,class_weight = 'balanced',

criterion = 'gini', max_depth = None, max_features = 'log2', max_leaf_nodes = None, max_samples = None,

min_impurity_decrease = 0.0, min_impurity_split = None,

min_samples_leaf = 1, min_samples_split = 2,

min_weight_fraction_leaf = 0.0, n_estimators = 100,n_jobs = − 1, oob_score = False, random_state = 123, verbose = 0,warm_start = False)

2

Distant recurrence

Kernel Support vector Machine(KSVM)

SVC(C = 1, break_ties = False, cache_size = 200, class_weight = None, coef0 = 0.0, decision_function_shape = 'ovr', degree = 1, gamma = 1, kernel = 'rbf', max_iter = − 1,probability = False, random_state = None, shrinking = True, tol = 0.001,verbose = False)

3

Locoregional recurrence

Kernel Support Vector Machine(KSVM)

SVC(C = 1, break_ties = False, cache_size = 200, class_weight = None, coef0 = 0.0, decision_function_shape = 'ovr', degree = 1, gamma = 1, kernel = 'rbf', max_iter = − 1,probability = False, random_state = None, shrinking = True, tol = 0.001,verbose = False)

4

New primary

Kernel Support Vector Machine(KSVM)

SVC(C = 1, break_ties = False, cache_size = 200, class_weight = None, coef0 = 0.0, decision_function_shape = 'ovr', degree = 1, gamma = 1, kernel = 'rbf', max_iter = -1,probability = False, random_state = None, shrinking = True, tol = 0.001,verbose = False)

5

Residual

Kernel Support Vector Machine(KSVM)

SVC(C = 10, break_ties = False, cache_size = 200, class_weight = None, coef0 = 0.0, decision_function_shape = 'ovr', degree = 1, gamma = 0.001, kernel = 'rbf',

max_iter = − 1, probability = False, random_state = None, shrinking = True, tol = 0.001, verbose = False)