Staffing Optimization With AI: A Look Back and Look Forward
The need for frontline caregivers has never been greater than it is at this moment – facilities across the country are struggling to maintain, and use, the resources they have in the most efficient manner possible. To aid in this deficit, Providence taps decision optimization and machine learning to leverage the encounter data at its 40 service lines across 52 hospitals to come up with optimized schedules for front-line managers to accommodate provider preferences and at the same time meet or exceed patient care requirements. This vision gives caregivers back tens of thousands of hours annually so they can focus on top-of-license activities rather than manual schedule creation, and reduces cost without impacting patient care. We are in our third year of this major transformational initiative and will share lessons learned on how to combat pushback through change management and provide quantifiable results.
Learning Objectives
- Design an approach that leverages practical machine learning to optimize service-line schedules and staffing
- Analyze effectiveness of the generated (optimized) schedules in actual hospital departments with nurse managers and executives
- Conclude on the observed impacts and projected potential business benefits
- Discuss how to scale up its implementation to more than 1,000 sites and lessons learned in scaling across a multi-region, multi-facility initiative
- Describe other probable approaches to staffing optimization that could be complementary, especially in change management (i.e., people and process)
Speakers
