Table 1 Significance of adding machine-learned features to baseline clinicopathologic variables

From: Predicting lymph node metastasis from primary tumor histology and clinicopathologic factors in colorectal cancer using deep learning

 

Temporal validation

External validation 1a

External validation 1b

Null model (age, sex, tumor grade, T-category, lymphatic invasion, venous invasion)

Reference

Reference

Reference

P-value for adding 5 machine-learned features

<0.0001

0.00032a

<0.0001

  1. P-values for a likelihood ratio test comparing a null model containing baseline clinicopathologic variables to an alternative model containing the baseline clinicopathologic variables and 5 machine-learned features.
  2. aplanned primary analysis.
Back to article page