Table 1.

Clinical characteristics of patients involved in the study.

Characteristics	Training cohort TCGA-LUAD, n = 500)	Validation cohort one (GSE72094, n = 398)	Validation cohort two (GSE68465, n = 442)
Age
<65	219 (43.8%)	107 (26.88%)	214 (48.42%)
>=65	271 (54.2%)	291 (73.12%)	228 (51.58%)
Unknown	10 (2%)	0	0
Gender
Female	270 (54%)	222 (55.78%)	219 (49.55%)
Male	230 (46%)	176 (44.22%)	223 (50.45%)
Race
White	386 (77.2%)	377 (94.72%)	294 (66.52%)
Non-White	60 (12%)	18 (4.52%)	19 (4.29%)
Unknown	54 (10.8%)	3 (0.75%)	129 (29.19%)
Ethnicity
Hispanic or Latino	7 (1.4%)	9 (2.26%)	NA
Non-Hispanic or Latino	381 (76.2%)	381 (95.73%)	NA
Unknown	112 (22.4%)	8 (2.01%)	NA
Tumor stage
Stage I	268 (53.6%)	254 (63.82%)	NA
Stage II	119 (23.8%)	67 (16.83%)	NA
Stage III	80 (16%)	57 (14.32%)	NA
Stage IV	25 (5%)	15 (3.77%)	NA
Unknown	8 (1.6%)	5 (1.26%)	NA
T classification
T1	167 (33.4%)	NA	150 (33.94%)
T2	267 (53.4%)	NA	251 (56.79%)
T3	45 (9%)	NA	28 (6.33%)
T4	18 (3.6%)	NA	11 (2.49%)
Unknown	3 (0.6%)	NA	2 (0.45%)
Prior malignancy
Yes	79 (15.8%)	NA	NA
No	421 (84.2%)	NA	NA
Tissue origin
Upper lobe lung	291 (58.2%)	NA	NA
Non-upper lobe lung	209 (41.8%)	NA	NA
Smoking history
Ever	415 (83%)	300 (75.38%)	300 (67.87%)
Never	71 (14.2%)	31 (7.79%)	49 (11.09%)
Unknown	14 (2.8%)	67 (16.83%)	93 (21.04%)
KRAS mutation
Yes	NA	139 (34.92%)	NA
No	NA	259 (65.08%)	NA
TP53 mutation
Yes	NA	97 (24.37%)	NA
No	NA	301 (75.63%)	NA
EGFR mutation
Yes	NA	41 (10.3%)	NA
No	NA	357 (89.7%)	NA
STK11 mutation
Yes	NA	64 (16.08%)	NA
No	NA	334 (83.92%)	NA
Vital status
Alive	318 (63.6%)	285 (71.61%)	206 (46.61%)
Dead	182 (36.4%)	113 (28.39%)	236 (53.39%)