A software tool to make objective hospital discharge decisions by analyzing existing patient data. (GSU 2012-01)

About

Introduction: The Centers for Medicare and Medicaid Services (CMS) have identified hospital readmission rates as a critical healthcare quality metric within the United States. Unplanned hospital readmissions still reportedly account for as much as $12 billion of annual Medicare expenditures. Hospitals and physicians are facing increasing pressure to reduce hospital readmission due to many reasons. Currently, hospital discharge decisions are largely subjective, being that they are made by practicing physicians based on their personal knowledge from education and previous experience. It would be desirable to improve hospital discharge decision-making by providing the physicians with objective indications of the likelihood of readmission of each individual patient. Targeting this issue is one of the cornerstones for financing the Patient Protection and Affordable Care Act. Hence, there is a need for an objective assessment tool that informs the hospital discharge decision with decision support software analyzing a large sample of patient data. Technology: Georgia State University researchers, in collaboration with Emory University researchers, have invented software to support more-objective hospital discharge decision-making based on a large sample of previously-successful and -unsuccessful hospital discharges. An econometric model is applied to patient data collected from a population of former hospital patients who had been discharged and whose readmission status is known. This software is able to estimate parameters that are statistically significant determinants of successful discharge (a discharge not followed by readmission within, for example, 30 days). The estimated econometric model then forms the basis of a decision support model that makes recommended �discharge� or �do not discharge� decisions for individual patients.

Key Benefits

A decision support model that can potentially be integrated into electronic medical records software. May assist in a cost-effective reduction in hospital readmission rates while maintaining the current prospective payment system. Able to utilize each patient�s own observable data for computation in the decision support model

Register for free for full unlimited access to all innovation profiles on LEO

  • Discover articles from some of the world’s brightest minds, or share your thoughts and add one yourself
  • Connect with like-minded individuals and forge valuable relationships and collaboration partners
  • Innovate together, promote your expertise, or showcase your innovations