Figure 1.

The second step of features selection using the least absolute shrinkage and selection operator (LASSO) logistic regression from ten features selected by the lowest probability of classification error and average correlation coefficients (POE + ACC). (A,B) Ten-fold cross-validation based on 1se was used to select the tuning parameter (λ) in the LASSO regression model. An optimal λ value of 0.0288 was selected. (C) The four selected features and coefficients of the Rad-score were indicated by the y-axis and x-axis, respectively.