Fig. 3

Construction of the FISH-clinical nomogram. A Tuning parameter selection (λ) with 10-fold cross-validation in the LASSO Cox model. The dotted vertical line is drawn at the optimal λ value by minimum criteria, which is 0.030 with log (λ) = − 3.493. B LASSO Cox coefficient profiles of the candidate variates. C Five selected predictors and their corresponding coefficients. D The FISH-clinical nomogram constructed based on the regression model is used to predict the 1, 2, and 3 years RFS rate for NMIBC patients. The risk score can be calculated according to the regression formula