Skip to main content

Table 4 P-value of the log-rank test of lower dimensional representation, generated by Partitioning Around Medoids (PAM) clustering algorithm on the last hidden layers of three Deep Learning-based approaches (testing set only). 12 TCGA (The Cancer Genome Atlas) cancers are being compared. Bolded values indicate the smallest p-value among three Deep Learning approaches, refer to better low dimensional representation

From: Deep learning-based cancer survival prognosis from RNA-seq data: approaches and evaluations

TCGA CancersP-values of log-rank test by models
Cox-nnetDeepSurvAECOX
KIRP7.71E-022.45E-011.40E-01
KIRC2.38E-039.79E-023.01E-01
LIHC3.57E-016.14E-013.86E-01
BRCA4.45E-014.81E-014.85E-01
CESC2.45E-013.26E-013.92E-01
LUAD9.58E-024.07E-011.11E-01
BLCA3.27E-012.67E-014.94E-01
HNSC3.38E-014.06E-016.19E-01
PAAD2.97E-014.04E-012.29E-01
OV2.80E-013.38E-014.42E-01
STAD5.72E-012.67E-017.01E-01
LUSC3.10E-014.14E-016.05E-01
  1. The boldface p-value indicates it is the smallest one among all three algorithms