Fig. 1

Demographic and clinical features selection using the LASSO regression model. (A) LASSO coefficient profiles of the 14 features. A coefficient profile plot was produced against the log (λ) sequence. Vertical line was drawn at the value selected using ten-fold cross-validation. (B) Four risk factors selected using LASSO regression analysis. Optimal tuning parameter (λ) selection in the LASSO regression model used ten-fold cross-validation via minimum criteria. The partial likelihood deviance curve was plotted versus log (λ). In both figure, dotted vertical lines were drawn at the optimal values by using the minimum criteria and 1 standard error (SE) of the minimum criteria (the 1-SE criteria). (At minimum criteria including age, T stage, M stage, peripheral CD3(+)T lymphocytes, CD3(+)CD4(+)T lymphocytes, CD19(+)B lymphocytes, CD19(+)CD5(+)B lymphocytes, CD3(-)CD16(+)CD56(+)NK cells and CD4(+)/CD8(+) ratio; At 1-s.e. criteria including age, total CD19(+)B lymphocytes and CD4(+)/CD8(+) ratio.)