Skip to main content

Table 1 Overview about employed breast datasets

From: Regularized logistic regression with network-based pairwise interaction for biomarker identification in breast cancer

Dataset Publication # patients Classification # patients of each class
GSE2034 [62] 242 time to relapse ≤5 y & relapse =True 95
    time to relapse >7 y & relapse =False 147
GSE1456 [63] 111 time to relapse ≤5 y & relapse =True 35
    time to relapse >7 y & relapse =False 76
GSE11121 [64] 125 t.dmfs ≤5 y & e.dmfs =True 28
    t.dmfs >7 y & e.dmfs =False 97
GSE6532 [65] 178 t.dmfs ≤5 y & e.dmfs =True 51
    t.dmfs >7 y & e.dmfs =False 127
GSE4922 [66] 204 DFS.time ≤5 y & DFS.status =True 70
    DFS time >7 y & DFS.status =False 134
GSE12093 [67] 79 DFS.time ≤5 y & DFS.status =True 12
    DFS.time >7 y & DFS.status =False 67
  1. t.dmfs denotes the time for distant metastasis-free survival and e.dmfs is the corresponding event indicator. DFS.time denotes the time for disease-free survival and DFS.status is the corresponding event indicator