Decision Support for Reducing 30-day Readmissions: General Medicine Patients in Community Hospitals

This is to certify that the thesis/dissertation prepared By Entitled For the degree of Is approved by the final examining committee: Chair To the best of my knowledge and as understood by the student in the Research Integrity and Copyright Disclaimer (Graduate School Form 20), this thesis/dissertation adheres to the provisions of Purdue University's " Policy on Integrity in Research " and the use of copyrighted material. ii To my beloved grandfather and loving family iii TABLE OF CONTENTS Health expenditures in United States have experienced a gradual increase in spending with no indication of slowing down. Addressing this problem has been a major area of concern for policy makers, and as a result more consideration has been placed on decreasing health spending and increasing affordability. One major area recognized as being effective in decreasing these financial burdens has been inpatient thirty-day adult readmissions, currently costing $26 billion annually. Centers for Medicare & Medicaid Services (CMS) have determined readmissions to be an indicator of the quality and efficiency of patient care. This research provides a prediction model for patients at 'high-risk' of 30-day readmissions patients in rural and urban hospital settings. These results are integrated into a decision support tool that combines the mathematical design, published discharge interventions, and financial model for use by hospital administrators. This tool was created to give 'control' back to hospital managers and improve the decision making process in reducing hospital readmission rates. Through this work we show the mathematical model, intervention process work flow, and decision support tool.