Reducing Hospital Readmission Risk Using Predictive Analytics

Hospitals are responsible for ensuring not only that the patients heal when in the hospital but also that the patients are not readmitted within 30 days of discharge. Additionally, the penalization of hospitals from the Hospital Readmissions Reduction Program in the Affordable Care Act of 2010 and the emergence of value-based, patient-centered reimbursement models continue to pressure health organizations to minimize hospital readmissions. In the face of limited staffing resources, readmission strategies are driven by three foundational components: which patients to focus on, what type of intervention should occur, and when an intervention should occur. Previous modeling work has crudely grouped patients into a few segments. With the combination of advanced analytical modeling and widely used electronic health records (EHRs), patients’ risk levels and the timings of the readmission issues can be finely predicted. This provides an opportunity for creating personalized care plans (when and what intervention should occur) for patients. This study describes developing and implementing a predictive analytics-based system in a Midwestern hospital system for profiling readmission risk. Results indicate that models, such as the ones detailed in this article, that combine patient stratification and readmission risk timing can effectively extend a personalized care plan to determine when intervention timing should occur and optimize resource allocation of the care team. This comprehensive suite of predictive models would allow care teams across the continuum to offer personalized care transition plans and dynamically pivot strategies to address emerging events throughout a patient’s trajectory.

History: This paper was refereed.