As the demand for emergency care increases, overcrowding becomes a growing issue in ERs across the country. New research from New York City-based Columbia Business School reveals how predictive analytics can help hospitals reduce ER wait times by up to 15 percent.
The study, called "Using Future Information to Reduce Waiting Times in the Emergency Department via Diversion," unveils how hospitals can use predictive analytics to divert patients and refrain from overcrowding.
Most hospitals divert incoming ER patients only after the maximum threshold is reached. But, as the study outlines, hospitals should predict when patient congestion will build and begin the process of diverting patients before congestion occurs. Study coauthors Carri Chan, PhD, and Kuang Xu, PhD, propose an algorithm that hospitals can use to predict when the highest number of patients will arrive at the ER.
"Patients on their way to the emergency room want to know that their emergency is going to be handled as expeditiously as possible," said Dr. Chan. "By using predictive modeling to develop more effective diversion policies, hospitals can reduce wait times for patients by up to 15 percent, improving care and customer satisfaction while at the same time saving time and money."