Nurse Scheduling You Can Trust Through Healthcare Predictive Analytics
Ernest Hemingway once said, "The best way to find out if you can trust somebody is to trust them." That's easier said than done when the topic at hand is the scheduling of your entire workforce, and that workforce is nurses and others who care for patients.
That trust may be even harder to give when it means putting your confidence in a technology that might seem too futuristic to be real.
A recent survey of nurse managers by AMN Healthcare and Avantas, Predictive Analytics in Healthcare 2016: Optimizing Nurse Staffing in an Era of Workforce Shortages, found that nearly all respondents said that predictive analytics to accurately forecast patient demand months in advance would be helpful to them in the scheduling and staffing of nurses. But, 80% also said they did not know that such technology-enabled products are available to them right now.
Today, many executives and managers outside of healthcare would not dream of scheduling the use of expensive resources and authorizing spending without first knowing what demand might be. And, if accurate data were available about future demand for products and services, it would be put to immediate use to forecast need and approve expenditures.
But in the healthcare industry, the link between the utilization of its most important resource – care providers – and predictive analytics to accurately forecast demand is rarely engaged.
The healthcare workforce is not only the most important resource but also the most expensive one; labor makes up over half the budget of nearly all healthcare organizations. Yet, scheduling and staffing of nurses and other practitioners are still conducted with little or no data about patient demand. In hospitals and other healthcare organizations, the scheduling of nurses and other clinical and nonclinical personnel is mostly accomplished through adherence to antiquated practices without any forecasting of patient demand.
Earning Trust through Data and Outcomes
One provider organization, a multiple hospital system in the South, was cautious about stepping back and letting the data provided by the Avantas predictive model drive its clinician scheduling process. Such concern is understandable, since each organization is unique, so forecasting based on industry norms likely would not be helpful.
But the Avantas predictive model provides data that are unique to each organization, which result in unique forecasts for each unit or department within a provider organization. It is the unique data that are harnessed to forecast future patient volumes on unit, facility or system levels.
This provider organization worked with the strategic account managers at Avantas to develop a trial of the forecasting tool within two units, med-surg and ICU. One of the units being an ICU provided a degree of risk to the trial, as ratios are much tighter, typically one nurse to two patients, so an inaccurate projection could have serious consequences.
The result of the trial was an 98% accuracy rate at predicting staffing needs 30 days out from the shift.
Improving Work Environments and the Bottom Line
Accurate forecasts of staffing needs can solve a wide range of problems that afflict most hospitals and other healthcare organizations. The same Predictive Analytics Survey showed that most nurse managers are very concerned about the impact of scheduling and staffing problems on staff morale, patient experience, and quality of care.
The survey report quoted a nurse manager as saying that scheduling and staffing problems result in nurses feeling like "nobody cares how hard they work, and I see how this impacts patient care." A registered nurse with many years of experience said that when scheduling and staffing problems result in understaffing, "patients do not get the quality care they deserve."
Healthcare enterprises that have adopted predictive analytics and advanced labor management strategies have realized outcomes that include reductions in agency nursing, increased staff satisfaction scores, improved nurse retention, reductions in open shift incentives and bonus pay, and signiﬁcant annual savings in labor spending