Fig. 1

Filtering candidate variables by LASSO. A Shows the Lasso variable coefficient plot. Each curve in the figure represents the trajectory of a variable's coefficient. The vertical axis represents the values of the variable coefficients. The bottom horizontal axis, λ, is the parameter controlling the severity of the penalty, and the top horizontal axis represents the number of non-zero coefficients in the model under the penalty parameter. B Shows the parameter adjustments in LASSO. Fine-tuning the LASSO model's regularization parameters involves screening λ using a tenfold cross-validation approach. A dashed vertical line is positioned at 1 standard error (1-SE standard) from the minimum and maximum values of λ. λ.1se represents the parameter value associated with a model that delivers optimal performance while utilizing the fewest number of variables