A Risk Stratification Model for Lung Cancer Based on Gene Coexpression Network and Deep Learning

Figure 4

Subgroup analysis using NetScore. (a) Predictive value of our risk stratification model was tested in subgroups classified by clinicopathological characteristics of the training set. A trend of association between the risk group and overall survival was found in all subgroups. (b, c) The same subgroup survival analysis was also performed in both test sets. (b) The risk group was associated with overall survival regardless of clinicopathological variables except female, stage II, and KRAS mutation subgroups in test set 1. (c) Regardless of subgroups, a trend of poor prognosis in high-risk group was also found in test set 2.

(a)

(b)

(c)