Fig. 1

Feature selection using the LASSO–Cox regression model. (a) Tuning parameter λ selection in the LASSO–Cox regression model. Partial likelihood deviance was plotted against the log (λ) sequence. Error bars represent 95% CIs. Identification of the optimal penalization coefficient λ in the LASSO model used tenfold cross-validation and minimum criterion. As a result, a λ value of 0.127 with log (λ) = − 2.061 was selected. The dotted vertical line was plotted at the selected value using tenfold cross-validation, for which the optimal λ resulted in eight, nonzero coefficients. The numbers on the top axis represent the quantity of the features. (b) LASSO coefficient profiles of 1209 features (represented by different-colored curves) selected using univariate Cox regression analysis were plotted against the log (λ) sequence. CI, confidence interval; LASSO, least absolute shrinkage and selection operator