Research Paper Volume 13, Issue 6 pp 8762—8776

An immunoscore nomogram for predicting survival in patients with oesophageal cancer

Immune feature selection based on the LASSO Cox regression model. (A) Optimal feature subsets based on the minimum criteria with 10-fold cross-validation of the LASSO regression. The vertical dashed lines represent the optimal values using the minimum criteria and the 1-standard error (SE) of the minimum criteria. The λ selected with 10-fold cross-validation (minimum criteria) was 0.039, and log (λ) was -3.245. (B) Regression coefficient profiles of 22 immune signatures in the LASSO model. The vertical dotted line is the optimal λ selected with 10-fold cross-validation, which resulted in 12 non-zero coefficients.

Figure 3. Immune feature selection based on the LASSO Cox regression model. (A) Optimal feature subsets based on the minimum criteria with 10-fold cross-validation of the LASSO regression. The vertical dashed lines represent the optimal values using the minimum criteria and the 1-standard error (SE) of the minimum criteria. The λ selected with 10-fold cross-validation (minimum criteria) was 0.039, and log (λ) was -3.245. (B) Regression coefficient profiles of 22 immune signatures in the LASSO model. The vertical dotted line is the optimal λ selected with 10-fold cross-validation, which resulted in 12 non-zero coefficients.