Digital Transformation in Healthcare: Real-time and predictive staff scheduling and management

For over two decades, professionals and researchers have increasingly recognized that healthcare nursing staff management has an important impact on patient care outcomes1.

Subsequent research has established that understaffing tends to result in higher incidence of negative nursing-sensitive outcomes such as bed sores, failure to rescue, and falls; more staff and richer skill mix (a higher proportion of RNs to NAs and LVNs/LPNs) tend to reduce the occurrence of these outcomes2. Much the same is true of the relationship between nurse staffing and indicators of workforce satisfaction and cost-efficiency, such as burnout and nurse turnovers that can cost upwards of $80,0003

The importance of nurse staffing to safe patient care raises a simple issue with complex consequences: the number of physical beds in a unit may be greater than the number of patients who can safely be accommodated by the unit’s nursing staff. A unit that has 20 beds might only have the nursing staff to care for 10 patients. If patient movement throughout the health system does not account for staffing and vice versa, there is potential for units to become understaffed or overstaffed, with potentially disastrous consequences.

At the same time that the importance of workforce staffing has gained recognition, the number of nurses in the American healthcare system has generally decreased while the percentage of bed occupancy has increased4. Health systems simply do not have infinite nurses to throw at the problem; in a reality in which labor costs make up 50% or more of hospital operating expenses, they can’t afford to, either5.

Under these circumstances, efficient staff deployment becomes key. Given staffing and budgetary constraints, how do health systems keep an adequate number of staff relative to the number of patients? A variety of nursing methodologies provide guidelines for the efficient use of staff, ensuring that enough staff are scheduled without wasting nursing resources. 

Some of the most common methodologies involve variations of staffing according to patient care workload volume, such as nurse-to-patient ratios (which have become legislated requirements in California), full-time equivalents (FTEs) per patient day, or hours per patient day (HPPD)6. Each of these methodologies specifies a certain number of nurses (or nurse hours worked) per patient (or unit of patient care workload). These methodologies must also take into account variations in individual patient acuity and care requirements, as well as differences in nursing workload between different unit types, for example an ICU vs. extended care unit vs. spinal cord injury unit. Nurse managers thus attempt to schedule staff to ensure that their staffing is just right - the correct ratio of nurses to patients, or within a certain degree of variance of their HPPD target. 

Any given staffing methodology, however, is only effective if it is implemented reliably. This is the crux of the issue. Nursing staff schedules have to be produced and communicated to staff weeks ahead of time, meaning that nurse managers use their staffing methodology to schedule nurses according to a best guess of how many patients might require care during a given shift. But patient numbers and care workloads can change frequently, and managers often rely upon historical data to estimate patient census in the future7. The past does not always accurately reflect the future, however, and individual shifts can see unexpected influxes of new patients or patient discharges that leave staff idle. Moreover, the number of nurses in the schedule does not always equal the number of nurses available for patient care on a given shift, particularly at shift changes as nurses call out sick or are assigned training and other tasks that take them away from direct patient care.

Hospitals are extremely dynamic environments, so if nurse managers and other nursing administrators cannot track real-time changes to patient volume and nurse staffing, and if they don’t have visibility into upcoming changes, then a unit can easily deviate from its staffing methodology requirements. In hospitals where staffing is managed primarily using pen and paper or Excel spreadsheets, real-time and predictive insights within and between units are impossible. Some methodologies, such as those based upon HPPD, involve complex calculations: the number of nursing hours worked has to account for direct vs. indirect care hours, specific patient acuities, and other care characteristics. Nurse managers cannot reasonably be expected to run these calculations every time something changes in their unit, and even if they do, they don’t always have ready access to solutions for staffing shortfalls.

This presents yet another complexity: if an understaffed unit cannot conjure additional staff into being on the spot, it has only a few options. A nurse manager might ask staff to stay past the end of their shift, but this incurs overtime premium pay and drives nurse burnout. The unit may be able to bring in nursing agency personnel, but these nurses once again charge high hourly rates. Finally, the unit can “float” in nurses from other units. 

As patients are dynamically admitted and discharged throughout a hospital, some units might scramble to manage more patients than they have the staff to care for, but other units might have idle nurses - “float pool” nurses - who could help out in other units. The movement of float staff between units is often directed by command centers or nursing supervisor’s offices whose bird’s eye view of the hospital allows them to shuffle staff. But float pooling is plagued by many of the same issues that nurse managers face. With staffing details confined to paper schedules or Excel spreadsheets, float pool supervisors have to call individual units to figure out who needs additional nurses, who can provide them, and whether or not a given float nurse has the qualifications and cross-training to work in other units. And when managers aren’t sure of their own unit’s status with regard to staffing methodology requirements, they might not even recognize that they can spare a nurse. Without visibility into the staffing needs of other units - data proving that another unit needs help - managers may be inclined to hang on to extra staff to ensure that they can handle unexpected patient admissions, staff call-outs, or other issues. 

If those responsible for managing staffing and patient dispositions for the hospital cannot see all of this disparate information in one place, and if that information is not reliably up-to-date, it becomes practically impossible to dynamically move staff around the hospital. Allowing a unit to remain understaffed can be disastrous for patients and taxing for staff, but without an integrated, reliable mechanism to provide visibility into staffing throughout the hospital and to facilitate float pooling, the alternative solutions are costly.

The fundamental problem is data. Bad data cannot facilitate good staffing. Datasets might be inaccurate, incomplete, or simply inaccessible, stuck on paper or siloed so that they cannot be used quickly or at all. Bed management information may be separate from staff scheduling information, and both might not be updated frequently. In a dynamic and hectic hospital environment, managers need a tool that can pull granular, up-to-date data to provide real-time and predictive staffing guidance, sparing them the time and human error involved in trying to simultaneously calculate staffing methodology requirements and manage patient care. Operations personnel, command centers, and nursing supervisors need to be able to access all of this information in one centralized view that breaks down which of their units need nurses now, who has nurses to spare, and where issues might arise in coming hours.

Issio provides the solution: a secure cloud workforce optimization platform that provides a single source of workforce scheduling truth. By capturing staffing and patient census information on a unit-by-unit level and updating to reflect changes in real-time, Issio not only facilitates adherence to staffing methodology requirements for individual units, but also provides visibility into the entire hospital or health system. Issio runs complex nursing methodology calculations so that nurse managers don’t have to, it flags current issues, and it predicts future days, shifts, and hours in which understaffing might arise. If a patient admission renders a unit understaffed for only an hour, Issio not only captures this information and alerts command center and nursing supervisor personnel, but also provides convenient tools for finding qualified, cross-trained staff from other units who can cover. The data collected in Issio for each individual unit are collated together into operations and analytical tools that provide real-time and historical insight into staffing throughout a facility or health system. And because Issio is a highly reliable cloud service that meets FedRAMP security requirements, not only is workforce information always available, it is cyber-secure, making Issio a reliable backbone that increases efficiency, reduces costs, and ensures effective patient care throughout the hospital or health system.


1 Aiken, L. H., Clarke, S. P., Sloane, D. M., Sochalski, J., & Silber, J. H. (2002). Hospital nurse staffing and patient mortality, nurse burnout, and job dissatisfaction. Jama, 288(16), 1987-1993; Needleman, J., Buerhaus, P., Mattke, S., Stewart, M., & Zelevinsky, K. (2002). Nurse-staffing levels and the quality of care in hospitals. New England Journal of Medicine, 346(22), 1715-1722.

2  For several examples see: Brennan, C. W., Daly, B. J., & Jones, K. R. (2013). State of the science: the relationship between nurse staffing and patient outcomes. Western Journal of Nursing Research, 35(6), 760-794; Cho, E., Chin, D. L., Kim, S., & Hong, O. (2016). The relationships of nurse staffing level and work environment with patient adverse events. Journal of Nursing Scholarship, 48(1), 74-82; Duffield, C., Diers, D., O'Brien-Pallas, L., Aisbett, C., Roche, M., King, M., & Aisbett, K. (2011). Nursing staffing, nursing workload, the work environment and patient outcomes. Applied nursing research, 24(4), 244-255; Glette, M. K., Aase, K., & Wiig, S. (2017). The relationship between understaffing of nurses and patient safety in hospitals - A literature review with thematic analysis. Open journal of nursing, 7, 1387-1429; Needleman, J., Buerhaus, P., Pankratz, V. S., Leibson, C. L., Stevens, S. R., & Harris, M. (2011). Nurse staffing and inpatient hospital mortality. New England Journal of Medicine, 364(11), 1037-1045.

3 Oh, D., & Lee, K. H. (2022). Why Nurses Are Leaving Veterans Affairs Hospitals?. Armed Forces & Society, 48(4), 760-779.

4 Halpern, N. A., Goldman, D. A., Tan, K. S., & Pastores, S. M. (2016). Trends in critical care beds and use among population groups and Medicare and Medicaid beneficiaries in the United States: 2000–2010. Critical care medicine, 44(8), 1490.

5 https://www.aha.org/costsofcaring

6 Griffiths, P., Saville, C., Ball, J., Jones, J., Pattison, N., Monks, T., & Safer Nursing Care Study Group. (2020). Nursing workload, nurse staffing methodologies and tools: A systematic scoping review and discussion. International Journal of Nursing Studies, 103, 103487.

7 Kortbeek, N., Braaksma, A., Burger, C. A., Bakker, P. J., & Boucherie, R. J. (2015). Flexible nurse staffing based on hourly bed census predictions. International journal of production economics, 161, 167-180.

Copyright © 2024 Becker's Healthcare. All Rights Reserved. Privacy Policy. Cookie Policy. Linking and Reprinting Policy.

 

Featured Whitepapers

Featured Webinars