A seven-gene CpG-island methylation panel predicts breast cancer progression

BMC Cancer

Table 2 Accuracy rates of individual selected genes and aggregated models^a

Model	Sensitivity	Specificity	Positive predictive value	Negative predictive value	Area under the ROC curve
All 7 genes^b	0.93	1.00	1.00	0.93	0.97
BRCA1^c	0.74	0.74	0.74	0.74	0.87
DAPK1^c	0.79	0.84	0.83	0.80	0.89
MSH2^c	0.74	0.84	0.83	0.76	0.89
CDKN2A^c	0.68	0.53	0.59	0.63	0.76
PGR^c	0.74	0.58	0.64	0.69	0.77
PRKCDBP^c	0.63	0.68	0.67	0.65	0.80
RANKL^c	0.68	0.68	0.68	0.68	0.75

^a:comprehensive accuracy rates and individual parameters are listed
^b: global contribution of all selected genes was assessed using JMP Genomics software
^c: individual gene contributions were assessed using R statistics

ISSN: 1471-2407