TABLE 3.

Analyses of the GILncSig by Univariate and Multivariate Cox regression models in the three LUAD sets from TCGA

Variables		Univariable model			Multivariable model
		HR	95% CI	p‐value	HR	95% CI	p‐value
Training set (n = 246)
GILncSig	High/low	1.037	1.019–1.055	<0.001	1.033	1.015–1.051	<0.001
Age	>65/<=65	1.001	0.981–1.022	0.906
Gender	Male/female	1.268	0.826–1.946	0.277
Stage	(III+IV)/(I+II)	1.816	1.473–2.239	<0.001	1.778	1.439–2.197	<0.001
Testing set (n = 244)
GILncSig	High/low	1.073	1.019–1.128	0.007	1.057	1.004–1.112	0.034
Age	>65/<=65	1.007	0.984–1.031	0.544
Gender	Male/female	0.941	0.616–1.439	0.780
Stage	(III+IV)/(I+II)	1.500	1.238–1.817	<0.001	1.481	1.219–1.799	<0.001
TCGA set (n = 490)
GILncSig	High/low	1.029	1.019–1.039	<0.001	1.026	1.016–1.036	<0.001
Age	>65/<=65	1.005	0.989–1.020	0.553
Gender	Male/female	1.113	0.825–1.500	0.484
Stage	(III+IV)/(I+II)	1.641	1.425–1.890	<0.001	1.623	1.408–1.871	<0.001