Prediction of Early Recurrence of Liver Cancer by a Novel Discrete Bayes Decision Rule for Personalized Medicine

Table 4

Optimal combinations of markers per number of markers and their discrimination performances obtained using training samples.

Number of markers	Sensitivity	Specificity	Youden index	Combination of markers
3	0.79	0.50	0.29	Tumor number × tumor size	vp	Liver damage
4	0.80	0.50	0.30	Tumor number × tumor size	vp	ICG	Liver damage
5	0.75	0.50	0.25	ALB	Tumor number × tumor size	vv	Degree of differentiation	Liver damage
6	0.74	0.51	0.24	ALB	Tumor number × tumor size	vp	ICG	Degree of differentiation	Liver damage
7	—	—	—
8	—	—	—
9	—	—	—