Breast Cancer Prognosis Risk Estimation Using Integrated Gene Expression and Clinical Data

Table 1

Breast cancer microarray gene expression datasets used in this study.

Data set	Country	Poor/good prognosis	Samples	Platform	IHC	References
GSE1456*	Sweden	41/118	159	HG-U133A, HG-U133B	NA	[2]
GSE2990*	Sweden, UK	37/85	189	HG-U133A	ER	[7]
GSE6532*	Belgium	56/61, 100/150, 9/68	327, 255, 87	HG-U133A, HG-U133B, HG-U133Plus 2.0	ER, PR	[11]
E-TABM-158*	USA	54/63	118	HG-U133A	ER, PR, HER2	[13]
GSE5327*	USA	11/47	58	HG-U133A	ER	[17]
GSE2603*	USA	36/46	121	HG-U133A	ER, PR	[18]
GSE31519*	Germany	52/10	67	HG-U133A	ER, PR, HER2	[22]
GSE3494*	Sweden	60/176	251	HG-U133A, HG-U133B	ER, PR	[27]
GSE4922*	Singapore	91/158	255	HG-U133A, HG-U133B	ER	[28]
GSE19615*	USA	14/0	115	HG-U133Plus 2.0	ER, PR, HER2	[29]
GSE2034*	Netherlands	106/180	286	HG-U133A	ER	[30]
GSE12276*	Netherlands	190/14	204	HG-U133Plus 2.0	NA	[31]
GSE11121*	Germany	47/153	200	HG-U133A	NA	[32]
GSE7390§	Europe	44/154	198	HG-U133A	ER	[33]
van de Vijver§	Netherlands	84/211	295	Agilent Human Genome	ER	[34]
Total: 15	8 countries	1,042/1,694	3,185	4 platforms

∗Represents the training datasets and §represents the testing datasets.