Real-Time Location Systems (RTLS) solve commonplace challenges by tracking valuable assets, staff, and patients on virtual maps, helping hospital employees and administrators save time. Without RTLS technology, administrators do not know how many IV pumps are available in the ED or how often caregivers wash their hands, for example. Beyond these conventional use cases however, RTLS is quickly evolving into the missing piece of a hospital’s Big Data puzzle. By revealing new workflow data to team leaders, location-based intelligence is transforming healthcare.
RTLS technologies collect vast amounts of location data by following objects and people while recording their locations in ‘real-time’. The more impactful RTLS solutions now offer rules-based software which categorize location data into ‘events’ or discernible patterns for use by other hospital applications. The business intelligence (BI) use case for RTLS is not just about deriving savings from locating objects quickly, it is about understanding real-world hospital workflows in order to predict what happens next and, ultimately, making more informed decisions. By knowing where someone is located in relation to a patient, caregiver, piece of equipment or a combination of these factors, decision-makers can truly know if a process or procedure occurred, how often it occurred and more. For example, a nurse entering a patient room and staying for longer than a few minutes is transformed into a location event that indicates patient interaction time.
Because software-based rules lend meaning to location coordinates, rules-based RTLS solutions are on the verge of revolutionizing patient care. Most people know that even with an appointment, they must wait to be treated by a physician. Long wait times impact revenues resulting from high patient throughput and bed availability and they take an equal toll on patient satisfaction. Now, clinics can classify patients by appointment type and RTLS tags will follow them as they move throughout designated zones such as ‘ED waiting room’ and ‘Radiology’, for example. RTLS software time-stamps a patient’s waiting time in each zone and if a patient’s waiting time exceeds prescribed benchmarks, the patient can be instructed to move to the next location (procedure) or a nearby caregiver can be alerted. Staff scheduling can be optimized based on average wait time benchmarks and the patient load in order to increase revenues and improve patient experience.
Hospital leaders will soon take location intelligence provided by RTLS software rules and merge that data into Big Data platforms to perform predictive analytics. For example, if a leader’s objective is to prevent patients from leaving through a particular exit which faces a busy street, RTLS can monitor the frequency of patient exits over time and analyze when it most likely occurs. Perhaps the manager will decide that hiring a guard for that exit on Saturdays, is worth the investment. With integration to Big Data platforms, leaders may even be able to associate a 10% higher patient load resulting from faster processing in the ED to 20% more revenues and a 30% jump in patient satisfaction, as an example. The possibilities of marrying location intelligence with other data sets are endless.
In order to build a long-term RTLS strategy, CIOs, CNOs, CFOs and COOs should ask themselves two questions:
What is the most compelling use case for RTLS?
- Define what a ‘win’ with RTLS looks like for multiple departments and work backwards. While improving asset utilization by 10% today through asset tracking and reducing rental equipment budgets next year is important, consider how RTLS could impact patient flow, caregiver workflows, patient safety and patient satisfaction while offering new business intelligence as a part of your Big Data strategy.
How much RTLS accuracy do I really need to effectively implement my use case long-term?
- RTLS accuracy requirements drive costs and vary by use case. Most RTLS applications offer room-level location visibility. On the other hand, achieving sub-1 meter location accuracy may not be affordable for hospital-wide RTLS adoption unless you are tracking small objects such as medication bottles on shelves. Some RTLS infrastructure options re-use existing network infrastructure (i.e. Wi-Fi) and thus better lend themselves to whole-hospital RTLS adoption, which is critical for revealing business intelligence as a part of a Big Data strategy.
While traditionally RTLS has been a means of locating objects and people on virtual maps, a new breed of RTLS offers rule-based software that derives meaning from location events, indicating the who and the where but also the when, of a particular workflow. By completing a hospital’s Big Data approach to patient safety, cost of care, patient satisfaction and caregiver productivity issues, RTLS is becoming an essential tool for improved decision-making in the hospital of the future.