The events of the past two years have irrevocably shifted hospital capacity management practices. From new COVID-19 variants and unpredictable surges to downstream impacts like delayed procedures and the great reshuffling and resignation of hospital staff, hospitals have never been more critical to adopt solutions that optimally manage their capacity.

Still, too often in the inpatient space, nursing managers and directors are forced to rely on manual data, intuition, and past experience to make capacity decisions for both patient flow and supply management. While the decisions inpatient staff make are often correct, the methods they rely on are not scalable and cause undue pressure on these personnel who are already at great risk of burnout.

One of the most significant shifts in hospital operations over the course of the COVID-19 pandemic has been increased reliance on AI-based technology for capacity management and general health care delivery. The following goals are focus areas where adoption of AI-based technology can continue to help inpatient staff address common issues that prevent efficient capacity management.

1. Achieve more effective discharge practices. The process of discharging a patient and freeing an inpatient bed inevitably takes time. However, inpatient managers and staff can control the amount of time it takes. Discharge times can be safely reduced through strategic planning and addressing discharge needs at admission time. If inpatient staff address these tasks earlier in the inpatient process than they do now, they will be free to focus on directing overall patient flow and provide more streamlined discharge processes overall. While it is not possible to accelerate a patient’s healing, inpatient leaders and staff can ensure that patients are safely and efficiently delivered to the next stage in their care journey.

Investing in a transparent, scalable software solution to coordinate the inpatient care management team helps them anticipate potential delays before they occur and better directs patient flow overall. Predictive modeling, which is already used in a variety of other industries and health care sectors, can also be implemented to improve discharge planning.

By optimizing discharge practices and planning methods, care providers will be able to better view, manage, and ultimately care for their entire patient pipeline, reducing burnout and improving care standards and idle wait times.

2. Open and close surge units at the right time. The ebbs and flows of the COVID-19 pandemic caused massive uncertainty in capacity predictions, overflow management, and overall inpatient surges. With the right technology, however, supply and demand-side models can be used to predict upcoming bed shortages. Factoring in trends of which beds are often occupied, where new demand is coming from, and which departments are likely to have higher utilization empowers staff to be agile and proactive in triaging patient flow and specialized care. This enables staff to match demand with supply correctly and open surge units only when needed. Neglecting to utilize technology to flag upcoming demand signals can lead to quicker burnout and disorganized case management.  Reactively opening an unneeded surge unit, rather than relying on technology and predictive analytics to support more appropriate action, can waste time, energy, and resources.

3. Promote system-wide visibility. A critical key to a successful health system is transparency. In the wake of the COVID-19 pandemic, achieving an acceptable level of visibility in distributing patients across a health system has become particularly crucial. Even in very specialized facilities, all providers need a system-wide approach to sufficiently support their patients’ care journeys.  Still, this is often a challenge in health systems, where individual facilities may feel siloed within the larger organization, struggling to collaborate and communicate to share information with others in the network.

This issue must be approached strategically and with the proper planning assessment. AI-based technology solutions can show an accurate overview of the entire system’s capacity, as well as up-to-date, network-wide information on which hospitals are best equipped to take which patients and which are struggling with capacity at a given time. This visibility, coupled with constant communication and transparency, allows much more feasible, manageable transfers between facilities – allowing health systems to direct patient flow and optimize their entire capacity of inpatient beds across the system.

The future of capacity management

Proper patient placement requires health care leaders to play a daily and constant game of chess. Providers need tools to help them make as many strategically planned moves as possible throughout the ED, PACU, ICU, and nursing units. This shuffle becomes infinitely easier to navigate with predictive models running each element of demand. This spans incoming volumes from the OR and ED, as well as external and inter-hospital transfers. Predictive models should be updated using real-time feeds that capture data, any delays, and unanticipated surges.

Health system leaders can master this “chess game” by anticipating the next several moves well in advance with the assistance of AI-based predictive analytic tools. This adoption will lead to dramatically better outcomes than a purely reactive response with no appreciation for how unit capacities are likely to unfold. In managing the next phase of the COVID-19 pandemic and beyond, it will become evermore critical for health systems to invest in transparent, data-driven solutions that will optimize capacity management issues.

Pallabi Sanyal-Dey is an internal medicine physician.

Image credit: Shutterstock.com