Mercy reduces nurse turnover 9% and improves fill rate with AI-powered workforce management platform

Mercy, a 50-hospital system, faced escalating nurse staffing shortages, rising labor costs, and nurse burnout driven by post-pandemic attrition and an aging nursing workforce. Manual scheduling processes managed across spreadsheets and email made it impossible to efficiently allocate nurses across all labor pools. Agency dependency had skyrocketed during the pandemic, and nurse managers were burdened with last-minute phone outreach to fill shifts.

Mercy implemented Works, a digital workforce management platform, to centralize scheduling across all nurse labor pools—core, flex/gig, and agency—in a single system. The platform uses AI-powered dynamic pricing to automatically calculate incentive rates based on real-time supply and demand, match credentialed nurses to open shifts, and push notifications via mobile app. Scheduling flexibility was extended to include 4-, 6-, 8-, 10-, and 12-hour shift options matched to patient census demand.

Within one year of implementation, bedside FTEs increased by 3.5% and nurse turnover dropped by 9%. Mercy improved overall fill rate, reduced agency labor dependency, and lowered total premium spend. The platform's AI continuously refined its incentive calculations over two years, reducing wasted spend on unfilled shifts and eliminating manual manager intervention for last-minute staffing needs.

• Involving frontline nurses in technology selection and implementation drove adoption and ensured the solution addressed real workflow pain points.
• A platform strategy that consolidates all labor pools (core, flex, agency) in one place is essential for achieving full workforce visibility and efficient allocation.
• AI-driven dynamic pricing modeled on ride-sharing economics (supply/demand incentives) can reduce premium labor spend while improving fill rates without manager intervention.