Decision Support Tool to Estimate and Reduce the Probability of Readmission for Congestive Heart Failure Patients

Abstract

Congestive Heart Failure (CHF) is a condition where blood flow from the heart through the body is inadequate, causing congestion in the lungs and swelling in the body's tissues. An urban university teaching hospital is able to treat and assign post-discharge resources to patients diagnosed with CHF. Despite the current treatment methods and assignment of post-discharge resources, the rate of readmission for patients returning to the hospital within 30 days remains higher than the level expected by the Center for Medicare and Medicaid Services. This project proposes the development of a decision support tool to assist the hospital in reducing the readmission rate for patients diagnosed with CHF. The project initially analyzes medical comorbidities and social factors of patients to identify correlations with a patient's probability of readmission. A discriminant analysis baseline model constructed from an electronic health record database (September 2015 to December 2018) projects the readmission probability for a patient. Subsequently, a correlation study determines which post-discharge resources are associated with reducing the readmission probability in patients with specific combinations of medical comorbidities and social factors. Ultimately, the decision support tool analyzes a patient's unique combination of medical severity and social factors to project the patient's probability of readmission and provides a tailored list of suggested post-discharge resources to reduce the probability of readmission for that patient.