Development and Validation of a Tool to Predict High-Need, High-Cost Patients Hospitalized with Ischemic Heart Disease

Design: A retrospective cohort study Setting: We identified patients through the State of Florida Agency for Health Care Administration (AHCA) (N=586,518) inpatient dataset. Participants: Adult patients (at least 40 years of age) admitted to the hospital with a diagnosis of ischemic heart disease between January 1, 2007 to December 31, 2016.

Primary Outcome Measures: We identified patients whose healthcare utilization is higher than presumed (analysis of residuals) and used logistic regression (binary and multinomial) in estimating the predictive models to classify individuals as high-need, high-care (HNHC) patients relative to inpatient visits (frequency of hospitalization), cost and hospital length of stay (LOS). Discrimination power, prediction accuracy, and model improvement for the binary logistic model were assessed using Receiver Operating Characteristic (ROC) statistic, the Brier score, and the log-likelihood (LL)-based pseudo R2, respectively.