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

Table 3

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 for XGboost model (lambda is the overfitting suppression factor).

lambda	Rtrain/total	0.75					0.5					0.25
	Scenario	A	B	C	D	E	A	B	C	D	E	A	B	C	D	E
0.1	Strain	0.9985	1	1	1	1	1	1	1	1	1	1	1	0.9995	1	1
	Stest	0.9917	0.9878	0.9844	0.9818	0.9873	0.992	0.9898	0.9855	0.9863	0.9899	0.9956	0.9946	0.9899	0.9881	0.9866
	Sauc	0.9806	0.9814	0.9778	0.9801	0.9851	0.9753	0.9823	0.9737	0.9829	0.9869	0.9886	0.987	0.9836	0.9834	0.9812
1	Strain	0.9985	0.9986	0.9987	1	1	0.9992	0.9993	0.9987	0.9988	0.9988	0.9995	0.9991	0.9983	1	0.9992
	Stest	0.9922	0.9869	0.9832	0.9822	0.9873	0.992	0.9892	0.9823	0.9851	0.9872	0.9956	0.9892	0.9886	0.9845	0.9811
	Sauc	0.9823	0.9792	0.9764	0.98	0.9851	0.9753	0.9806	0.9708	0.982	0.9832	0.9886	0.9789	0.9811	0.9763	0.9738
10	Strain	0.9985	0.9946	0.9949	0.994	0.9955	0.9985	0.9959	0.9949	0.9952	0.9961	0.999	0.995	0.9953	0.996	0.9974
	Stest	0.9922	0.9856	0.9828	0.9814	0.9836	0.992	0.9865	0.9823	0.9816	0.9861	0.9942	0.9865	0.9886	0.9834	0.9766
	Sauc	0.9794	0.9724	0.9735	0.9772	0.9802	0.9775	0.9714	0.97	0.9755	0.9824	0.9833	0.9724	0.9827	0.9743	0.9689