Table 1.

Clinical information statistics of three sets of datasets.

Characteristic		TCGA training datasets (n = 247)	TCGA all datasets (n = 494)	GSE42127 (n = 43)
Age (years)	≤50	8	19	0
	>50	238	470	43
Survival status	Living	144	282	22
	Dead	103	212	21
Gender	Female	62	128	18
	Male	185	366	25
Smoke years	≤20	11	21
	>20	94	199
pathologic_T	T 1	54	114
	T 2	146	287
	T 3	36	70
	T 4	11	23
pathologic_N	N 0	158	316
	N 1	67	127
	N 2	18	40
	N 3	1	5
pathologic_M	M 0	194	406
	M 1/M X	50	84
Tumor stage	Stage I	120	242	23
	Stage II	81	158	10
	Stage III	41	83	10
	Stage IV	4	7