Table 1.

Grid search parameters in hyperparameter tuning.

Classifiera	Parameters_grid	Selected value
LogisticRegression	Penalty: [“l1,” “l2,” “elasticnet,” “none”] C: {1, 0.1, 0.01} Solver: [“lbfgs,” “newton-cg,” “liblinear,” “sag,” “saga”]	Penalty=“11” C=0.1 Solver=“liblinear”
SVMb (kernel = “rbf,” degree = 3)	C: [0.1, 1, 10, 100] Gamma: [1, 0.1, 0.01, 0.001]	C=1 Gamma=1
DecisionTree	criterion: [“gini,” “entropy”] max_depth: [None, 4, 5, 6, 7, 8] min_samples_split: {2, 4, 8, 10, 20, 30, 40}	Criterion=“entropy” Max_depth=None Min_samples_split=2
RandomForest	n_estimators: {30, 100, 200} max_depth: {4, 5, 6, 7, 8} min_samples_split: {2, 4, 6, 8} min_samples_leaf: {1, 2, 3}	n_estimators=100 Max_depth=8 Min_samples_split=2 Min_samples_leaf=1
KNeighborsClassifier	n_neighbors: {5, 10, 15, 20, 30} weights: [“uniform,” “distance”] metric: [“minkowski,” “euclidean,” “manhattan”]	n_neighbors=5 weight=“distance” metric=“manhattan”
AdaBoostClassifier	n_estimators: {5, 10, 30, 50, 100, 500} learning_rate: [0.01, 0.05, 0.1, 0.15, 0.2, 0.3, 0.5, 1.0] algorithm: [“SAMME,” “SAMME.R”]	n_estimator=500 learning_rate=1.0 algorithm=“SAMME.R”
XGBClassifier (eval_metric = “aucpr,” n_estimators = 100, booster = “gbtree,” colsample_bytree = 1, learning_rate = 0.3)	eta: [0.01, 0.05, 0.1, 0.15, 0.2, 0.3] gamma: {0, 1, 5} max_depth: {5, 6, 8, 10} min_child_weight: {0, 1, 2, 5, 10}	min_child_weight=0 max_depth=5 gamma=0 eta=0.2
MLPClassifier (hidden_layer_sizes = (64, 64, 64), activation = “relu”)	solver: [“adam,” “lbfgs”] alpha: [0.0001, 0.001, 0.01, 0.05, 0.1] learning_rate: [“constant,” “adaptive”] learning_rate_init: [0.01, 0.005, 0.001] batch_size: {150, 300, 500}	Solver=“lbfgs” Alpha=0.1 Learning_rate=“constant” Batch_size=150 Learning_rate_init=0.01

^aThe algorithms were performed using the Python package Scikit-learn 0.24.2, and all other parameters not shown in this table were set to their default values.

^bSVM: support vector machine.