Table 1.

Summary of parameter values in each model for predicting hepatitis B virus (HBV) infection. Decision tree (DT), random forest (RF), and extreme gradient boosting (XGBoost).

Algorithms	Parameter	Value	Meaning
XGBoost	nrounds	120	The number of rounds for boosting.
	max_depth	8	Maximum depth of a tree.
	eta	0.09	Step size shrinkage used in update to prevent overfitting.
	gamma	0.04	Minimum loss reduction required to make a further partition on a leaf node of the tree.
	colsample_bytree	0.8	The subsample ratio of columns when constructing each tree.
	min_child_weight	18	Minimum sum of instance weight (hessian) needed in a child. If the tree partition step results in a leaf node with the sum of instance weight less than the value, then the building process will give up further partitioning.
	subsample	0.89	Subsample ratio of the training instances.
	n_estimators	600	Number of base learners in the integrated model.
	max_delta_step	9	Maximum delta step we allow each leaf output to be. If it is set to a positive value, it can help making the update step more conservative.
DT	minispilt	20	The minimum number of observations that must exist in a node for a split to be attempted.
	minibucket	20	The minimum number of observations in any terminal node.
	maxdepth	10	The maximum depth of any node of the final tree.
	xval	5	Number of cross-validations.
	cp (complexity parameter)	0.001	The minimum improvement in the model needed at each node.
RF	mtry	6	Number of variables available for splitting at each tree node.
	ntree	700	Number of trees to grow.