Getty Images

Showing Predicted Patient Wait Time Estimates Can Trim ED Delays

By leveraging patient intake data, researchers were able to generate probabilistic wait-time predictions, aiding patients and paramedics in making informed choices to reduce emergency department delays.

Nationwide, emergency departments (EDs) are grappling with extensive patient wait times, soaring patient visits, and significant overcrowding. However, new research reveals that predictive estimates of ED wait times can effectively tackle these challenges and minimize care delays.

ED overcrowding has been a national concern since the 1980s. However, the problem has only worsened with insufficient beds available and pronounced staffing shortages.

Consequently, patients are often left to wait, sometimes in ED hallways for up to nine hours at a time. This may leave some patients without receiving any care.

These circumstances not only suggest overwhelmed resources but also indicate underlying systemic issues in healthcare. The rise in overcrowding has coincided with an increase in patient mortality rates. Specifically, when ED occupancy exceeded the average, the likelihood of patient death rose by 3.1 percent compared to conditions in less crowded facilities, a separate study indicated.

In this latest study, researchers analyzed factors such as calendar effects, patient demographics, staff count, ED workload due to patient volumes, and patient condition severity using a vast patient-level dataset. 

“By showcasing anticipated waiting-time estimates, patients and ambulance staff can be better informed in selecting an ED from a group of EDs, which can lead to a more uniform spread of patients across the system,” Ho-Yin Mak of Georgetown University and one of the study’s authors, said in a press release.

Although wait-time estimates can boost patient satisfaction, current methods often overlook key underlying factors by relying solely on point forecasts, researchers stated.

“Communicating only a point forecast to patients can be uninformative and potentially misleading,” Mak continued.

To address this, the researchers developed a new way to estimate wait times, incorporating both patient-specific and ED-specific information, such as the patient's condition and ED congestion levels. This method offers real-time wait times, enabling patients and paramedics to make informed decisions about which emergency department to visit.

It also helps manage patient flow, evenly distributes patients across different emergency departments, and reduces congestion.

“Our model allows for dynamic updating and refinement of waiting-time estimates as a patient- and ED-specific information (eg, patient condition, ED congestion levels) is revealed during the waiting process,” said study co-author Siddharth Arora of the University of Oxford.

The findings also showed that the approach can enhance patient outcomes and satisfaction, particularly for less urgent cases. First responders, who now have a more comprehensive understanding of potential wait times, may also report more job satisfaction.

“For emergency healthcare service providers, probabilistic waiting-time estimates could assist in ambulance routing, staff allocation and managing patient flow, which could facilitate efficient operations and cost savings, and aid in better patient care and outcomes,” said co-author James Taylor, also of the University of Oxford.

Along with this method, there have been numerous efforts to improve ED wait times. Researchers have explored ways to reduce overall ED utilization, which can expedite care for patients with life-threatening conditions. These efforts come alongside data from United Healthcare suggesting that two-thirds of ED visits could be avoided. Thus, with decreasing avoidable ED utilization, patient wait times can potentially improve.

A 2019 Mount Sinai Brooklyn program reduced ED wait times by connecting low-acuity patients with care access. Usually, an emergency department segments all of its patients into a single pool to be triaged and treated by ED providers. However, the FastER Track program created a separate triage pool for low-acuity, non-urgent cases and treated them rapidly.

Next Steps

Dig Deeper on Patient data access

xtelligent Virtual Healthcare
xtelligent Rev Cycle Management
xtelligent Healthtech Analytics
Close