Skip to main content

Table 2 Survival analysis results with different feature encoding algorithms

From: A deep learning-based framework for lung cancer survival analysis with biomarker interpretation

MethodEvaluation IEvaluation II
 p-valuec-indexp-valuec-index
Cellular voting0.02900.51030.03200.5739
Aggregate statistic [6, 7]0.00830.67980.22000.6750
BoW encoding0.02900.65910.00450.6770
LLC-sum encoding0.01100.68740.02600.6751
LLC-max encoding0.00310.69110.04700.6770
  1. Note that lower p-values are better, whereas higher c-index values are better