Reducing costs by forecasting demand for nursing resources
SAS Analytics helps OhioHealth plan and care for its patients.
$2.2 million saved
in the first fiscal year, while maintaining high-quality patient care
OhioHealth turns to SAS® Analytics to ensure that hospitals are adequately staffed to provide optimal medical care
When patients check in to a hospital, they’re focused on their health and personal outcomes. They don’t think about the task of orchestrating the schedules of the nurses, doctors or technicians to provide the necessary care. For any health care organization, getting the right resources to care for patients can be a time-consuming and costly effort.
Nationally recognized OhioHealth employs 29,000 people across 11 hospitals and over 200 other health care facilities in Ohio. It’s a complex undertaking to manage the diverse network of facilities, resources and staff. The not-for-profit company prides itself on an employee-first mentality and has been recognized in the Fortune list of “100 Best Companies to Work For” for 12 years.
With the increasing costs of modern medicine, OhioHealth turned to its data to make sure the right staff is available to provide the best medical care as cost-effectively as possible. Starting with Riverside Methodist Hospital, analysts began examining data to forecast staffing needs in a pilot project. The goal: Maintain or improve patient care while keeping costs down.
We’ve put a framework in place to design, deploy and measure initiatives that improve our core business and support the delivery of high-quality care that is also affordable. Chris Clinton System Vice President of Value Transformation OhioHealth
The impact of staffing on health care costs
One challenge facing OhioHealth – and many other health care organizations – was optimizing workflow and staffing. Associates can leave for other jobs or move to other departments or facilities within the network. This leads to shortfalls in staffing. An unforeseen shortage in a critical role, such as a registered nurse, usually means overtime for existing staff or the use of staffing agency services – both of which are 1.5 to 2 times more expensive than the cost of the average full-time employee (FTE).
“OhioHealth is on a transformational journey to provide more value to our patients,” says Chris Clinton, System Vice President of Value Transformation at OhioHealth. “We’ve put a framework in place to design, deploy and measure initiatives that improve our core business and support the delivery of high-quality care that is also affordable. We created a workforce innovation team, which focuses on resources and having the right number of staff in place at the right time. We knew if we focused on optimizing the system, the dollars would take care of themselves.”
OhioHealth – Facts & Figures
associates, physicians and volunteers
health care facilities
Shankar Mani, Senior Performance Analytics Consultant at OhioHealth, began to dig into the data at Riverside Methodist Hospital to find hidden trends. His objective: Anticipate future demands based on this historical data.
“I tried to map this as a supply-and-demand problem,” Mani says. “The demand is patient volume. The supply is the right number of FTEs to meet that demand. The question became, ‘Can you accurately forecast the staffing needs based on this anticipated patient load?’”
A key insight came early in the process. Mani found that, on average, it took about six months from the time the facility posts a job until it brings the new person on board. That gave him the forecast window. To prepare for staffing needs in July, for example, hiring managers should start planning in January.
“We also had to break down our supply metric into both people that we have hired as well as jobs that are posted and yet to be filled,” Mani says. “Once we have this data in place, we could start mapping the demand against the supply. But we needed a model to forecast all of this and help us start to make better decisions in the future.”
Analytics is causing a shift in mindset to make sure that we have the right people in place when the patient enters the hospital. Shankar Mani Senior Performance Analytics Consultant OhioHealth
OhioHealth turned to SAS® Analytics to delve into historical data to forecast staffing needs at the Riverside facility. The team built a model that used elements of machine learning to refine and streamline the model. The techniques relied on ensemble modeling to combine different algorithms, ultimately returning a result that fits future demands.
Getting the right people at the right time
The decision to hire additional staff in advance of a personnel shortage was a departure from standard procedure. Using costlier efforts – such as overtime pay or agency services – was the accepted way to handle staffing shortages while maintaining a high level of care.
The model began to show some interesting results about staffing costs. Contrary to expectations, Mani discovered that the facility saved money when it focused on proactively hiring new staff. In fact, getting the right people in place saved money later.
After starting a pilot project at Riverside, Mani and his staff began to advise unit managers on their hiring plans. While the level of patient care remained constant, SAS Analytics helped the facility save around $2.2 million in the first fiscal year.
“We found that starting the hiring process in advance was a way to stay more budget-conscious,” Mani says. “You’re hiring for those positions because you know that people will leave or move to another department before the new person actually starts.”
Not only is Riverside saving money, more FTEs are available to work their shifts, leading to a more stable, less burdened staff – and happier administrators.
“For example, one of the most stressful things for a nurse manager is making sure you have the right hands with the right competency to take care of the patients in your unit,” says Lisa Gossett, Vice President of Patient Care and Chief Nursing Officer. “The analytics helped validate what we already knew instinctively in regards to our turnover and proactive staffing needs – the data brought credibility to what the nurse managers were requesting. It was eye opening to my executive team peers. Changing our approach to staffing has improved morale for our nursing team.”
OhioHealth is evolving, and staff members throughout the organization are changing their approach to hiring. Whether they’re in nursing, surgery or other areas, people are now proactively planning for their FTE positions and getting them approved.
“Analytics turned our risk conversation on its head,” Clinton says. “It’s all about controlling risk and making sure we don't inappropriately post positions or get out of budget. When a nurse gives her two-week notice that she’s leaving, the data shows us it's going to take six months to fill that position. This means we're committing to five-and-a-half months of overtime or agency services. Do we want to make a conscious decision to do that? No. It's actually far less risky to change the control system. And that’s what using advanced analytics has done – it’s allowed us to step back and think about what’s actually happening. You begin to approach things differently, using data to make the case.”
Ultimately, what does analytics mean to the patient who walks in the door? “It means we've got the right staff with the right competencies to deliver the best care,” Gossett says. “In fact, our patient satisfaction scores are now consistently in the top quartile at Riverside.”
Establishing a culture of analytics is helping the hospital change from reactive responses to proactive decision making. “Analytics is causing a shift in mindset to make sure that we have the right people in place when the patient enters the hospital,” Mani says. “I think that demonstrates the power and the value that analytics can bring to the table.”
... the data brought credibility to what the nurse managers were requesting. It was eye opening to my executive team peers. Changing our approach to staffing has improved morale for our nursing team. Lisa Gossett Vice President of Patient Care and Chief Nursing Officer OhioHealth
Les résultats présentés dans cet article sont spécifiques à des situations, problématiques métiers et données particulières, et aux environnements informatiques décrits. L'expérience de chaque client SAS est unique et dépend de variables commerciales et techniques propres, de ce fait les déclarations ci-dessus doivent être considérées dans un contexte. Les gains, résultats et performances peuvent varier selon les configurations et conditions de chaque client. SAS ne garantit ni ne déclare que chaque client obtiendra des résultats similaires. Les seules garanties relatives aux produits et services de SAS sont celles qui sont expressément stipulées dans les garanties contractuelles figurant dans l’accord écrit conclu avec SAS pour ces produits et services. Aucune information contenue dans le présent document ne peut être interprétée comme constituant une garantie supplémentaire. Les clients ont partagé leurs succès avec SAS dans le cadre d’un accord contractuel ou à la suite de la mise en œuvre réussie du progiciel SAS. Les noms de marques et de produits sont des marques déposées de leurs sociétés respectives.