Background: A classification tree model (CT-PIRP) was developed in 2013 to predict the annual renal function\ndecline of patients with chronic kidney disease (CKD) participating in the PIRP (Progetto Insufficienza Renale\nProgressiva) project, which involves thirteen Nephrology Hospital Units in Emilia-Romagna (Italy). This model\nidentified seven subgroups with specific combinations of baseline characteristics that were associated with a\ndifferential estimated glomerular filtration rate (eGFR) annual decline, but the modelâ??s ability to predict mortality\nand renal replacement therapy (RRT) has not been established yet.\nMethods: Survival analysis was used to determine whether CT-PIRP subgroups identified in the derivation cohort\n(n = 2265) had different mortality and RRT risks. Temporal validation was performed in a matched cohort (n = 2051)\nof subsequently enrolled PIRP patients, in which discrimination and calibration were assessed using Kaplan-Meier\nsurvival curves, Cox regression and Fine & Gray competing risk modeling.\nResults: In both cohorts mortality risk was higher for subgroups 3 (proteinuric, low eGFR, high serum phosphate) and\nlower for subgroups 1 (proteinuric, high eGFR), 4 (non-proteinuric, younger, non-diabetic) and 5 (non-proteinuric,\nyounger, diabetic). Risk of RRT was higher for subgroups 3 and 2 (proteinuric, low eGFR, low serum phosphate), while\nsubgroups 1, 6 (non-proteinuric, old females) and 7 (non-proteinuric, old males) showed lower risk. Calibration was\nexcellent for mortality in all subgroups while for RRT it was overall good except in subgroups 4 and 5.\nConclusions: The CT-PIRP model is a temporally validated prediction tool for mortality and RRT, based on variables\nroutinely collected, that could assist decision-making regarding the treatment of incident CKD patients. External\nvalidation in other CKD populations is needed to determine its generalizability.
Loading....