HIMSS23: How Can Healthcare Organizations Find Solutions to Best Support Their Workforce?

Virtual Nursing Can Offer Much-Needed Relief

HCA Healthcare Vice President and Chief Nursing Informatics Officer Sherri Hess said that nursing recruitment and retention were top priorities for her organization and that the shortage is a major concern for the industry.

Health systems need to develop and deploy innovative care models to better support nurses. It’s also crucial to get real-time data and the right alerts to nurses, Hess added.

“We’re working with our partners at Microsoft to come up with the ability to put that data in front of our charge nurses in a much easier way, instead of searching through multiple dashboards,” Hess said.

WATCH: CISA’s deputy director talks healthcare cybersecurity at HIMSS23.

Virtual nurses in acute-care areas have been a great help at HCA Healthcare, Hess said. All those things that the bedside nurse would normally do, the virtual nurse is doing, she said, such as admissions, discharge teaching, hourly rounding and pain reassessment.

The program can also attract retired or academic nurses who may not want to be on the floor for 12 hours but want to provide care. “The nurses love it. We’ve seen the satisfaction go up in the units where we’ve implemented it. The patients absolutely love it,” Hess said.

Returning Hours Back to Patient Care through Automation

An overview of the predictive scheduler tool developed by Providence and IBM (courtesy of HIMSS)

In another session, Providence shared its journey in building and adopting a predictive scheduling tool that automated and streamlined a laborious manual process.

Natalie Edgeworth, senior manager of workforce optimization and innovation at Providence, and Brittany Bogle, principal data scientist and healthcare provider use case specialist at IBM, talked about their experiences from when they started in 2019 to now.

Providence identified the workforce crisis as a top concern, Edgeworth said, and created a roadmap “focused on caregivers and how we can help them to get back into those patient care settings and focus less time on administrative tasks.”

With slim margins, an increase in retirements, unfilled job listings and clinician burnout, Bogle said that “doing more with the people, the tools and the talent that you have is increasingly important and prioritized.”

DIVE DEEPER: Learn about Banner Health's unified data model journey. 

Providence needed a way to automate staffing plans. The manual process used previously involved cumbersome Excel spreadsheets and too many variations across planning development.

The predictive scheduler automatically generates data-driven recommended scheduling plans that are optimized to each department’s own data, responds to workforce needs, provides staffing forecasts and allows for shift flexibility.

With the administrative burden reduced, Edgeworth said, the time saved can be reallocated to patient care. Next, the health system is working to improve integration, increase implementation and adoption, and forecast additional service lines.

Innovating Care in Machine Learning

Phoenix Children’s Hospital Executive Vice President and Chief Innovation Officer David Higginson offered his insights on the practical applications of machine learning at his organization.

“We don’t use vendors to do this. We build these products ourselves,” Higginson said. ML models are bound to local data, so taking a vendor’s model that worked in California won’t necessarily work in Arizona. Plus, trying and failing with a vendor’s solution would be costly.

So far, Higginson said, his team has built systems that help diagnose malnutrition in children, predict when a patient could be a no-show, offer support for staff retention, and identify people who might donate money to the hospital.

“Not every cool idea can be implemented,” he said. “If you don’t have the end in mind, it’s all for nothing.”

The automated ML tools he and his team use come with a price tag, so they need to show concrete benefits for the organization. “You really have to think about the problems — how am I going to extract value, either clinically or financially? — or don’t do it at all,” he said.

LEARN MORE: Catch up on the opening HIMSS23 keynote discussion on AI and health equity.

The key is finding the right problem that can be addressed with an ML model. “You have to reframe problems as a prediction problem for this to work. Many, many problems don’t lend themselves to being predicted,” Higginson said.

Get used to failure and stay away from issues that require high accuracy, he said, but added that many problems exist that don’t require that.

“I cannot tell you the number of times I’ve stopped wasted work by asking people, ‘If you had a prediction that was 85-plus percent accurate, what the heck would you do with it?’ Most people can’t figure that out,” Higginson said.

Keep this page bookmarked for our ongoing coverage of HIMSS23. Follow us on Twitter at @HealthTechMag and join the conversation at #HIMSS23.