A Predictive Model to Identify Patients at Risk of Unplanned 30-Day Acute Care Hospital Readmission

摘要

We tested an all-cause unplanned 30-day readmission risk model that produces timely risk scores from claims data and using the ACG predictive modeling framework. Our model achieves and AUC of. 75 on a test set. The major components of the model include fixed patient attributes such as maternity and disability, morbidity burden (ACG), count of hospital dominant morbidity types, cardiovascular, malignancy, neurologic and other condition clusters, count of ED episodes, and inpatient utilization measures including the number of previous acute care hospital stays, accumulated days, number of 30-day readmissions, and whether the patient had a major inpatient procedure.