Development of iChoose Kidney Risk Estimates

The iChoose Kidney tool uses data from more than 700,00 incident, adult ESRD patients in the national cohort of United States Renal Data System (USRDS) surveillance data from January 1, 2005 through September 30, 2010, with follow-up through September 30, 2011. Logistic regression models were used to predict 1 and 3-year risk of death for dialysis patients vs. transplant patients. Predictive accuracy of the model was assessed using a validation data set by the use of the c-statistic of the associated receiver operating characteristic (ROC) curve, which estimates the probability of concordance between the observed number of deaths and the predicted number of deaths based on the model. Model calibration was assessed by comparing the observed and expected number of deaths for each model.

Translation of Risk Estimates into a Shared Decision Making Tool   

We used the following equation to translate model coefficients for 1-year and 3-year mortality estimates into an individualized, estimated risk of mortality represents the sum of the individual's risk factors (risk score) and is the estimated Y-intercept (or baseline risk).

For example, 3-year mortality risk for a dialysis patient is derived from the formula below,

-2.8457 (Baseline risk) + 0.0067(Sex) + 0.0388(Age) + -0.2990(Black race) + -0.6111(Other Race) + -.05253(Hispanic ethnicity) + 0.4737(Cardiovascular disease)+-0.4696(Hypertension) + 0.0169(Diabetes) + 0.3619(Low albumin)

and 3-year mortality among transplant patients is derived from the formula below,

-5.4292  (Baseline risk) + -0.0475(Sex) + 0.0382(Age) + -0.0261(Black race) + -0.508 (Other race) + -0.4034(Hispanic ethnicity) + 0.3369(Cardiovascular disease)+-0.2(Hypertension) + 0.4013 (Diabetes) + 0.2102(Low albumin) + 0.136 (6-12 months on dialysis) + 0.4906 (>12 months on dialysis)

where Baseline risk=1; Sex=1 for Male, Sex=2 for Female; 1=yes and 0=no for Black race, Other race, Hispanic ethnicity, Cardiovascular disease, Hypertension, Diabetes, and Low albumin, 6-12 months on dialysis, and >12 months on dialysis

In this case, a 41 year old African American male with a history of diabetes and hypertension who has been on dialysis for 8 months has a risk of dying over the next year of 5.3% on dialysis and 0.9% with a kidney transplant (relative risk of dying on dialysis vs. transplant is 5.9). This patient’s three year risk of dying on dialysis is 11.9%, and 2.7% with a transplant (Relative Risk=4.4). Risk of dying within the next three years with a deceased donor transplant (3.4%) is 2.1 times higher than risk of dying with a living donor transplant (1.6%).

Prediction Model Discrimination and Performance

We performed external validation of the risk prediction models for dialysis and transplantation at 3 years using the validation cohorts from USRDS. The discriminatory ability of the model for 3-year mortality was moderate for dialysis (c-statistic = 0.7047 [95% CI: 0.7029-0.7065] and for transplant (c-statistic = 0.7015 [95% CI: 0.6875-0.7155]).  The c-statistic was 0.6640 (95% CI: 0.6458-0.6822) for deceased donor (DD) transplant and 0.7209 (95% CI: 0.6954-0.7463) for living donor (LD) transplant.  The c-statistics were similar among the derivation and validation datasets, indicating that the predictive models were generalizable among the U.S. ESRD patients and kidney transplant recipients.