Hybrid XGBoost model with hyperparameter tuning for prediction of liver disease with better accuracy

Table 1 Dataset description

No.	Attribute	Information	Type
1	Age	How old is the patient?	Integer
2	Sex	Patient’s sex	String (male/female)
3	Tot_bilirbn	Level of bilirubin compound	Floating
4	Direct_bilirbn	Level of direct bilirubin compound	Floating
5	Alk_phos	Level of alkaline phosphatase compound	Floating
6	Al_amntrfrs	Level of alanine aminotransferase compound	Floating
7	As_amntrfrs	Level of aspartate aminotransferase compound	Floating
8	Total_prot	Level of total protein in the sample	Floating
9	Albmn	Level of albumin in the sample	Floating
10	Ag_ratio	Ratio of compound albumin to globulin	Floating
11	Is_patient	Categorizes the dataset into parts	Categorical

Table 2 Result analysis

No.	Algorithm	Accuracy	AUC	Gini
1	CHAID model	71.36	0.746	0.493
2	CART model	73.24	0.724	0.448
3	Proposed model	93.55	0.987	0.974

AUC: Area under the curve; CART: Classification and regression tree; CHAID: Chi-square automated interaction detection.