Abstract
BACKGROUND: Heart failure (HF) is a leading contributor to cardiovascular morbidity and mortality in the population with chronic kidney disease (CKD). HF risk prediction tools that use readily available clinical parameters to risk-stratify individuals with CKD are needed. METHODS: We included Black and White participants aged 30-79 years with CKD stages 2-4 who were enrolled in the Chronic Renal Insufficiency Cohort (CRIC) study and were without self-reported cardiovascular disease. We assessed model performance of the Pooled Cohort Equations to Prevent Heart Failure (PCP-HF) to predict incident hospitalizations due to HF and refit the PCP-HF in the population with CKD by using CRIC data-derived coefficients and survival from CRIC study participants in the CKD population (PCP-HF(CKD)). We investigated the improvement in HF prediction with inclusion of estimated glomerular filtration rate (eGFR) and urine albumin-to-creatinine ratio (UACR) into the PCP-HF(CKD) equations by change in C-statistic, net reclassification improvement (NRI), and integrated discrimination improvement index (IDI). We validated the PCP-HF(CKD) with and without eGFR and UACR in Multi-Ethnic Study of Atherosclerosis (MESA) participants with CKD. RESULTS: Among 2328 CRIC Study participants, 340 incident HF hospitalizations occurred over a mean follow-up of 9.5 years. The PCP-HF equations did not perform well in most participants with CKD and had inadequate discrimination and insufficient calibration (C-statistic 0.64-0.71, Greenwood-Nam-D'Agostino (GND) chi-square statistic P value < 0.05), with modest improvement and good calibration after being refit (PCP-HF(CKD): C-statistic 0.61-0.78), GND chi-square statistic P value > 0.05). Addition of UACR, but not eGFR, to the refit PCP-HF(CKD) improved model performance in all race-sex groups (C-statistic [0.73-0.81], GND chi-square statistic P value > 0.05, delta C-statistic ranging from 0.03-0.11 and NRI and IDI P values < 0.01). External validation of the PCP-HF(CKD) in MESA demonstrated good discrimination and calibration. CONCLUSIONS: Routinely available clinical data that include UACR in patients with CKD can reliably identify individuals at risk of HF hospitalizations.