Research Paper Volume 13, Issue 7 pp 9927—9947

Development and validation of routine clinical laboratory data derived marker-based nomograms for the prediction of 5-year graft survival in kidney transplant recipients

Predictive variable selection results in model 1 (clinical variables + months 0-6 lab-derived variables) and model 2 (clinical variables + months 0-12 lab-derived variables) by LASSO regression and multivariate Cox regression analyses. (A) Preliminary selected variables in model 1 and model 2 by 5-fold cross-validation LASSO analysis. (B) Hazard ratio forest plots of final predictors in model 1 and model 2.

Figure 2. Predictive variable selection results in model 1 (clinical variables + months 0-6 lab-derived variables) and model 2 (clinical variables + months 0-12 lab-derived variables) by LASSO regression and multivariate Cox regression analyses. (A) Preliminary selected variables in model 1 and model 2 by 5-fold cross-validation LASSO analysis. (B) Hazard ratio forest plots of final predictors in model 1 and model 2.