Leukemia can be Effectively Early Predicted in Routine Physical Examination with the Assistance of Machine Learning Models

Table 2

Accuracy scores of model performances on different scenarios, train-set/test-set ratios, and regularizations. (S_train and S_test are accuracy scores of models on train data subset and test data subset respectively according to the score() function of sklearn; S_auc is the area under the curve score of model according to the roc_auc_score() function of sklearn; R_train/total is the ratio of train data to the total data) for random forest model.

Rtrain/total	Scenario	A	B	C	D	E
0.75	Strain	1	1	1	1	1
	Stest	0.9951	0.9878	0.987	0.9834	0.9844
	Sauc	0.9855	0.9747	0.9779	0.9797	0.9808
0.5	Strain	1	1	1	1	1
	Stest	0.9949	0.9871	0.9855	0.9816	0.9855
	Sauc	0.9859	0.9744	0.9745	0.9767	0.9808
0.25	Strain	1	1	1	1	1
	Stest	0.9956	0.9851	0.9899	0.9869	0.9822
	Sauc	0.9886	0.9692	0.9836	0.9803	0.9755