Regional Differences in Predicting Risk of 30-Day Readmissions for Heart Failure

Many researchers are working toward the goal of data-driven care by predicting the risk of 30-day readmissions for patients with heart failure. Most published predictive models have used only patient level data from either single-center studies or secondary data analysis of randomized control trials. This study describes a hierarchical model that captures regional differences in addition to patient-level data from 1778 unique patients across 31 geographically distributed hospitals from one health system. The model was developed using Bayesian techniques operating on a large set of predictors. It provided Area Under Curve (AUC) of 0.64 for the validation cohort. We confirmed that the regional differences indeed exist in the observed data and verified that our model was able to capture the regional variances in predicting the risk of 30-day readmission for patients in our cohort.