Patients with chronic renal failure (CRF) are at high risk of being readmitted to hospitals within 30 days. Routinely collected electronic health record (EHR) data may enable hospitals to predict CRF readmission and target interventions to increase quality and reduce readmissions. We compared the ability of manually extracted variables to predict readmission compared with EHR-based prediction using multivariate logistic regression on 1 year of admission data from an academic medical center. Categorizing three routinely collected variables (creatinine, B-type natriuretic peptide, and length of stay) increased readmission prediction by 30% compared with paper-based methods as measured by C-statistic (AUC). Marginal effects analysis using the final multivariate model provided patient-specific risk scores from 0% to 44.3%. These findings support the use of routinely collected EHR data for effectively stratifying readmission risk for patients with CRF. Generic readmission risk tools may be evidence-based but are designed for general populations and may not account for unique traits of specific patient populations-such as those with CRF. Routinely collected EHR data are a rapid, more efficient strategy for risk stratifying and strategically targeting care. Earlier risk stratification and reallocation of clinician effort may reduce readmissions. Testing this risk model in additional populations and settings is warranted.