AI takes on hospital staffing to help battle burnout

 

The Providence Health System has developed an artificial intelligence (AI) algorithm to help make staffing schedules more flexible. Creating schedules can be a very time consuming task for managers and adding in many variables such as child care can be very difficult. That is where AI can help with the task and minimize scheduling headaches, which are among the factors impacting clinician burnout. 

Health Exec spoke with Natalie Edgeworth, MHSA, senior manager, workforce optimization and Innovation, Providence Health System, so she could explain more about the AI and how it has helped. She presented on the topic at the Healthcare Information Management Systems Society (HIMSS) 2023 meeting. 

"The AI is really focused on giving flexibility and assigning staffing to our patient volume to create additional capacity and efficiencies. With the workforce crisis situation everyone is experiencing, we are having a hard time managing our resources to the most optimal level. So this tool we built takes a look at the electronic medical record and billing data to forecast both volume and acuity to be able to assign people to the right places at the right times. It also provides them options to pick different lengths of shifts, so we are giving the control back to the caregiver," Edgeworth explained. 

Facilities across the country are struggling to maintain and efficiently use the resources they have. Providence uses this machine learning decision optimization software to leverage the encounter data at its 40 service lines across 52 hospitals to come up with optimized schedules for front-line managers. Edgeworth said the AI has given caregivers back tens of thousands of hours annually so they can focus on top-of-license activities rather than manually going through schedule creation. She said this has reduced costs without impacting patient care. The health system is now in its third year of this major IT transformation initiative. 

"Caregivers that have worked in the field the past 10 years usually worked from 7 a.m. to 7 p.m. Well, if you have to pick up your child or if you have to make a doctor's appointment, this allows you to say, 'I would only like to work eight hours' so you can have that balance with real life," Edgeworth said. 

She said the AI has taken the manual task of completing staff schedules from four to 20 hours down to 15 minutes at most. 

"We are really excited to have streamlined this process and given back so much time to focus on patient care," she said.

Providence has hospitals in seven different states, and different state laws impact staff schedules. She used the example of Oregon, which mandates children cannot be left in childcare for more than 10 hours. Edgeworth said this presents clear issues with clinicians working 12-hour shifts, but the AI allows clinicians there to modify their schedules to accommodate real-life concerns and get more of a work-life balance. 

She said allowing staff to enter all the times they are and are not available and the shifts they prefer greatly reduces the number of call ins with people saying they cannot work a shift or needing to leave a shift early.

Providence built the system in partnership with its clinicians to get their feedback and buy-in. Edgeworth said she expected pushback from employees, which is typical for significant changes, but everyone this new system was widely embraced right away. 

One key benefit of the new tool is that nurse managers and others who build department schedules can use search queries to find people who can work during specific times or certain days; they type in what they need and the AI provides a list of options.

The AI factors in a lot of things that impact the numbers of patients that go to hospitals, even looking at weather condition predictions. This is designed to prevent last-minute schedule scrambles.

Edgeworth has said the AI works well so far. Her team is currently running with a 98% accuracy rate when it comes to estimating which patients will be at any facility on any given day.

Dave Fornell is a digital editor with Cardiovascular Business and Radiology Business magazines. He has been covering healthcare for more than 16 years.

Dave Fornell has covered healthcare for more than 17 years, with a focus in cardiology and radiology. Fornell is a 5-time winner of a Jesse H. Neal Award, the most prestigious editorial honors in the field of specialized journalism. The wins included best technical content, best use of social media and best COVID-19 coverage. Fornell was also a three-time Neal finalist for best range of work by a single author. He produces more than 100 editorial videos each year, most of them interviews with key opinion leaders in medicine. He also writes technical articles, covers key trends, conducts video hospital site visits, and is very involved with social media. E-mail: dfornell@innovatehealthcare.com

Around the web

When drugs are on the FDA’s shortage list, outsourcing facilities can produce their own compounded versions. When the FDA removed tirzepatide from that list with no warning, it created a considerable amount of chaos both behind the scenes and in pharmacies all over the country. 

If passed, this bill would help clinician-led clinical registries explore Medicare data for research purposes. The Society of Thoracic Surgeons and American College of Cardiology both shared public support for the bipartisan legislation. 

Cardiologists and other physicians may soon need to provide much more information when ordering remote patient monitoring for Medicare patients.

Trimed Popup
Trimed Popup