Fig. 1

Predictors selection using the LASSO regression method with 10-fold cross-validation. Binomial deviance was plotted versus log (lambda) (a), and coefficients plots were produced against the log (lambda) sequence (b). A total of 29 variables were included in the LASSO regression method with 10-fold cross-validation. Dotted vertical lines in figures (a, b) were drawn at the optimal values by utilizing the 1-SE criteria, where five nonzero coefficients were filtered, and the corresponding five variables were lesion diagnosis, lesion characteristics, lesion diameter, procedure time, and puncture distance. These five variables were included in the predictive model. Footnotes: LASSO Least absolute shrinkage and selection operator, SE standard error