Predicitve Staffing
The Predictive Staffing module helps you manage active schedules and proactively anticipates staffing demands across multiple departments or clusters. Predicitive Staffing provides census forecasts, sicks calls, and makes it easy to direct float pool resources where they are needed most, ensuring smooth day of operations and streamlining workflows between charge RNs and staffing offices.
Role
Project
Year
Product Designer
Aya Healthcare - Predictive Staffing
2024 - Present
03
My Role
User Research
UX/UI Design
Timeline
2024 - Present
Tools Used
Figma
Miro
ChatGPT
Mobbin
Vision
Give healthcare teams the time they need to stay ahead, with real-time insights and forecasting that help act hours in advance, easing the pressure of last minute desicions.
Workforce AI is set to revolutionize Healthcare Staffing with Predictive Intelligence. Our vision is to transform healthcare staffing by integrating advanced predictive analytics seamlessly
into every phase of the scheduling process.
Designed with a user-centric focus for simplicity and efficiency, and scalable to meet the diverse needs of various healthcare facilities, Workforce AI synergizes with existing systems and leverages Aya's extensive product offerings.
We are dedicated to empowering healthcare providers to optimize staff utilization, reduce external staffing dependencies, and elevate patient care. Committed to delivering real-time, actionable insights, Workforce AI fosters a more efficient, responsive, and cost-effective healthcare environment, adaptable to evolving staffing demands.
Unique Value Proposition
Take the guess work out of scheduling and staffing with the most accurate demand forecast. When combined with your staffing model, we can predict exact hiring needs,
automatically optimize schedules and help fill staffing gaps with our industry leading workforce management solutions and staffing network.
06
Final Design
Identifying the Challenges
01
Job to be done:
The "Active Schedule" flow (from schedule publication to the start of a shift) illustrates an automated open shift recruitment process. It begins with historical data and forecasts being used to feed workload predictions, which inform the published schedule. Once active, the schedule is updated in real-time using demand inputs and allows for modifications. Open shifts are generated automatically based on templates and pushed to internal staff for claiming or, if unfilled, escalated to external labor pools. Users can search and claim shifts, which are then approved and integrated into the schedule. If needed, external labor is engaged to fill remaining gaps, ensuring complete coverage before shift start.
Job to be done:
The "Day of Staffing" flow (within 24 hours to shift start) focuses on real-time schedule adjustments to ensure adequate coverage. It starts with schedule updates for last-minute changes such as call-offs and shift claims. Charge nurses or managers update unit schedules to reflect staffing requests like sitters or float pool needs. These needs are communicated to a central staffing team, which builds and updates staffing plans in real time. The finalized plan is sent back to unit leadership, and staffers can then take necessary actions like assigning float pool staff, notifying nurses, or recruiting last-minute coverage. The schedule is ultimately updated to reflect all staffing decisions just before the shift begins.
Primary End Users
Target Market/Customer Segment
P1: In-patient health systems with existing MSP Relationships
P2: New potential in-patient health systems customers (MSP or SAAS)
These personas are typically either the main user group or users directly impacted by the tool. Similarly to purchasers, they have distinct needs, priorities ans concerns. Understanding these personas is crucial for ensuring the tool is designed to meet their specific needs and challenges. Examples of design considerations:
- User-Centric Design: Understanding these personas ensures that he software is designed with a user-centric approach, addressing the practical needs and pain points experienced by those who will use the tool daily.
- Enhanced User Experience: Insights into these personas contribute to creating an intuitive and efficient user interface, leading to better adoption and satisfaction among users.
- Feedback Loop for improvement: These personas are a valuable source of feedback for ongoing improvements and updates to the software, ensuring it continues to meet evolving user needs.
02
Design and Development
To tackle these challenges, Aya Healthcare embarked on creating Workforce AI, an AI-driven solution designed to forecast patient demand and optimize workforce allocation. The development process encompassed several critical steps:
User-Centric Research: Engaging with healthcare administrators, HR personnel, and clinical staff to understand their pain points and requirements in workforce management.
Integration of Advanced Technologies: Leveraging predictive analytics, machine learning, and AI to develop models capable of forecasting patient volumes and corresponding staffing needs months in advance.
Modular Design Approach: Creating three distinct yet interconnected modules—Workforce Planning, Predictive Scheduling, and Predictive Staffing—to address various facets of workforce management.
Seamless System Integration: Ensuring compatibility with existing HRIS, VMS, and scheduling tools to facilitate smooth data flow and user adoption.
Iterative Testing and Feedback: Conducting pilot programs and gathering feedback to refine algorithms and user interfaces, ensuring the solution effectively meets user needs.
03
Solution Overview
Weekly Schedule Prototype
Job to be done:
- Organize staff shifts over a seven-day period, ensuring proper nurse coverage for each day and time slot. Helps managers assign shifts based on availability, skill sets, and patient needs, while also supporting compliance with labor rules and minimizing scheduling conflicts.
Job to be done:
- Forecast future staffing needs by analyzing upcoming patient demand, scheduled time off, sick calls, and historical trends. Help managers proactively adjust schedules to prevent staffing gaps, reduce last-minute changes, and maintain optimal coverage.
Lookahead Prototype
Unit Staffing Prototype
Job to be done:
- Manage and assign nurses to specific hospital units (like ICU, ER, or Med-Surg) based on patient acuity, census, and nurse qualifications. Ensures each unit has the appropriate number and mix of staff to deliver safe, effective care while optimizing resource use across the facility.
Central Staffing Prototype
Job to be done:
- Coordinate staffing across multiple units or departments from a single, centralized team or dashboard. Enable efficient resource allocation, fills staffing gaps quickly, and supports hospital-wide visibility and balance of nursing staff based on overall demand.
Let's work
together.
04
Impact and Benefits
Predictive staffing in nursing software uses data analytics to forecast future staffing needs, helping healthcare organizations plan more effectively.
Improved Patient Outcomes: Ensures appropriate nurse-to-patient ratios based on anticipated demand, leading to safer, more consistent care.
Cost Efficiency: Reduces unnecessary overtime and reliance on last-minute staffing, lowering labor costs.
Proactive Scheduling: Allows managers to plan ahead and adjust staffing before issues arise, avoiding reactive, crisis-based decisions.
Higher Staff Satisfaction: Provides more stable and predictable work schedules, improving morale and retention.
Operational Agility: Enables quick adaptation to seasonal trends, census changes, or emergencies with data-driven staffing plans.
Manage active schedules to meet real-time staffing demands.
Manage active schedules and view open shifts across multiple departments or clusters
Forecast call-offs and no-shows to address critical staffing needs weeks in advance
View trends for open beds, volume and ADT by department
Automate staffing plan creation with recommendation for the next to float, cancel or place on standby
