Using Machine Learning Algorithms to Predict Hepatitis B Surface Antigen Seroclearance

Table 2

Summary of parameter values in each model for predicting HBsAg seroclearance.

Model	Parameter	Value
Extreme gradient boosting	n_estimators	153
	max_depth	4
	min_child_weight	2
	Subsample	0.5
	colsample_bytree	0.8
	colsample_bylevel	0.8
	reg_alpha	2.0
	reg_lambda	0.3
Random forest	max_features	Auto
	min_samples_leaf	1
	n_estimators	40
Decision tree	max_depth	29
	max_features	log2
	min_samples_leaf	23
Logistic regression	C	0.001
	Penalty	L1