Background: The 4-variable kidney failure risk equation (KFRE) is a well-validated tool for patients with GFR <60 ml/min/1.73 m2 that incorporates age, sex, GFR, and urine albumin-to-creatinine ratio (ACR) to forecast individual risk of kidney failure. Implementing the KFRE in the electronic medical record is challenging, however, due to low ACR testing in clinical practice. The aim of this study was to determine, when ACR is missing, whether to impute ACR from PCR or dipstick protein for use in the 4-variable KFRE or to use the 3-variable KFRE that does not require ACR. Methods: Using electronic health records from OptumLabs® Data Warehouse, patients with eGFR <60 ml/min/1.73 m2 were categorized based on the availability of ACR testing within the previous 3 years. For patients missing ACR, we extracted urine protein-to-creatinine (PCR) and dipstick protein results, comparing the discrimination of the 3-variable KFRE (age, sex, GFR) with the 4-variable KFRE estimated using imputed ACR from PCR and dipstick protein levels. Results: There were 976,299 patients in 39 health care organizations; 59.0% were women, mean age was 72 years and mean eGFR was 47 ml/min/1.73m2. The proportion with ACR testing was 19.3% within the previous 3 years. An additional 1.7% had an available PCR and 36.3% had a dipstick protein; the remaining 42.8% had no form of albuminuria testing. The 4-variable KFRE had significantly better discrimination than the 3-variable KFRE among patients with ACR testing, PCR testing and urine dipstick protein levels, even with imputed ACR for the latter two groups. Calibration of the 4-variable KFRE was acceptable in each group, but the 3-variable equation showed systematic bias in the groups that lacked ACR or PCR testing. Conclusion: Implementation of the KFRE in electronic medical records should incorporate ACR even if only imputed from PCR or urine dipstick protein levels.