Reducing Hospital Readmission Risk Using Predictive Analytics

Arti Mann (), Ben Cleveland (), Dan Bumblauskas () and Shashidhar Kaparthi ()
Additional contact information
Arti Mann: Wilson College of Business, University of Northern Iowa, Cedar Falls, Iowa 50614
Ben Cleveland: UnityPoint Health, West Des Moines, Iowa 50266
Dan Bumblauskas: Missouri Western State University, St Joseph, Missouri 64507; PFC Services, Inc., Marietta, Georgia 30066
Shashidhar Kaparthi: Wilson College of Business, University of Northern Iowa, Cedar Falls, Iowa 50614

Interfaces, 2024, vol. 54, issue 4, 380-388

Abstract: 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.

Keywords: patient readmission risk; machine learning; random forests; predictive analytics; healthcare; hospital management (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://dx.doi.org/10.1287/inte.2022.0086 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:inm:orinte:v:54:y:2024:i:4:p:380-388

Access Statistics for this article

More articles in Interfaces from INFORMS Contact information at EDIRC.
Bibliographic data for series maintained by Chris Asher ().