Fig. 4.

Model identifies 7 variables strongly associated with EFS. (A) Variable importance by permutation in our random survival forest model, highlighting the top 7 variables that were identified by elbow analysis. (B) Pairwise subtree analysis showing weak interactions between most of the top 7 variables. (C) Linear models of the sum of the top 7 variables (polygenic score) in our random survival forest versus patient outcomes. Event = red; no event = teal. (D) Kaplan-Meier curves of patients with polygenic score > 0.5 (n = 43) and ≤ 0.5 (n = 66). (For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)