Title : Using predictive models in Post-Acute care: Reducing readmissions in the IRF setting
Abstract:
Reducing readmissions after discharge from IRF: Differentiating IRF from other post-acute care settings:
Increased attention and scrutiny of inpatient rehabilitation hospitals (IRFs) has expanded since initiation of the IMPACT Act in 2008. With the advent of Accountable Care Organizations (ACOs) and harsh penalties to acute care hospitals if patients are readmitted after discharge, it is vital for IRFs to provide exceptional value-based care. In this session, we will explore different strategies that have been successfully used to distinguish IRF level care from other post-acute settings, including subacute care and home health services. Strategies discussed will include an overview of a predictive analytical models we developed to improve clinical outcomes. These include an algorithm to identify patients at high risk of readmission to acute care hospital while hospitalized at IRF, an algorithm developed to identify patients at high risk of readmission after discharge from IRF and strategies to mitigate those risks; and a fall risk model to identify patients at high fall risk while at IRF and strategies implemented to improve this risk. We will discuss how education and reinforcement are necessary to maintain best practices across the enterprise when these clinical quality improvement projects are implemented.
Audience Take Away:
- Attendees will learn how development of a unique algorithm to identify patients at high risk for acute care transfer was successfully developed in conjunction with data scientists.
- Attendees will learn how to share best practices to reduce fall risk of patients in the IRF setting.
- Attendees will learn about social determinants of health and how identifying risk factors for readmission after discharge from the rehabilitation hospital can be mitigated prior to discharge.