The growth in the use of predictive models in health care continues as health systems adopt electronic health records and gain access to real-time digitized clinical data. Although health systems often have substantial experience in quality improvement related to care interventions, they have limited experience in implementing predictive models as part of the care process.
In this publication, authors, including HIP Investigators Dr. Maureen Smith and Dr. Brian Patterson, describe an approach to implementing predictive solutions that adapts the widely used Find-Organize-Clarify-Understand-Select–Plan-Do-Check-Act framework. This process can be used to bring together quality improvement teams and data analytics staff in leading a common process for organizational change and in supporting clinicians in adopting predictive solutions.
To guide health systems through the process of selecting and implementing a predictive model within their system, the UW Health Applied Data Science team and the Health Innovation Program developed Predictive Models: A Toolkit to Guide Implementation in Health Systems to support planning for and implementation of a predictive model. This toolkit should be used by health system quality improvement leaders, project managers, and analytics staff who are responsible for developing and implementing a predictive model within their health system.
View the Toolkit