Deriving a Retrospective Kidney Cohort

We used the Alberta Kidney Disease Network (AKDN) database to derive a retrospective, population-based cohort using linked administrative health, laboratory, and kidney failure datasets from Alberta, Canada [13 (link)]. These data were used to derive and internally validate our multivariable risk prediction models. We conducted this study using a prespecified protocol in accordance with the transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD) Checklist for Prediction model development (Supplementary Table 1). The University of Calgary and the University of Alberta granted ethics approval and waived the need for informed consent.