AI Might Be Able To Ease ER Overcrowding And Boarding

Artificial intelligence (AI) programs can help doctors and nurses predict hours earlier which ER patients will likely require hospital admission, a new study says.

An AI program trained on nearly 2 million patient visits became slightly more accurate than ER nurses in predicting which patients would need to be admitted, according to findings published Aug. 11 in the journal Mayo Clinic Proceedings: Digital Health.

If this approach proves successful, it could help reduce overcrowding in hospital emergency departments, researchers say.

“Emergency department overcrowding and boarding have become a national crisis, affecting everything from patient outcomes to financial performance,” said lead researcher Jonathan Nover, vice president of nursing and emergency services at Mount Sinai Health System in New York City.

“Industries like airlines and hotels use bookings to forecast demand and plan. In the ED, we don’t have reservations,” he continued in a news release. “Could you imagine airlines and hotels without reservations, solely forecasting and planning from historical trends? Welcome to health care.”

Up to 35% of ER patients who require admission wind up spending four or more hours biding their time in spare rooms or busy hallways awaiting a bed, a practice known as “boarding,” according to a recent study in the journal Health Affairs.

Worse, nearly 5% of patients wait a full day for a bed during the busy winter months, the earlier study found.

“Our goal was to see if AI combined with input from our nurses could help hasten admission planning, a reservation of sorts,” Nover said. “We developed a tool to forecast admissions needs before an order is placed, offering insights that could fundamentally improve how hospitals manage patient flow, leading to better outcomes.”

For the project, researchers trained the AI on more than 1.8 million ER visits that had occurred between 2019 and 2023.

“By training the algorithm on more than a million patient visits, we aimed to capture meaningful patterns that could help anticipate admissions earlier than traditional methods,” co-senior researcher Dr. Eyal Klang, chief of generative AI at the Icahn School of Medicine at Mount Sinai, said in a news release.

The team then put the AI up against a cadre of more than 500 ER nurses in evaluating nearly 47,000 patient visits that occurred in September and October 2024 at six emergency departments in the Mount Sinai Health System.

The nurses were asked to judge whether a patient would need hospital admission, after performing a quick triage. Researchers also fed the triage results to the AI, to see what it would predict.

The nurses proved about 81% accurate in predicting which patients would need hospital admission, compared to 85% accuracy from the AI.

“We were encouraged to see that AI could stand on its own in making complex predictions,” co-senior researcher Robert Freeman, chief digital transformation officer at Mount Sinai Health System, said in a news release. “But just as important, this study highlights the vital role of our nurses — more than 500 participated directly — demonstrating how human expertise and machine learning can work hand in hand to reimagine care delivery.”

Researchers next plan to implement their AI into real-time workflows and monitor how the program affects boarding times and patient flow through the ER.

“This tool isn’t about replacing clinicians; it’s about supporting them. By predicting admissions earlier, we can give care teams the time they need to plan, coordinate, and ultimately provide better, more compassionate care,” Freeman said. “It’s inspiring to see AI emerge not as a futuristic idea, but as a practical, real-world solution shaped by the people delivering care every day.”

More information

The American College of Emergency Physicians has more on ER boarding and crowding.

SOURCE: Mount Sinai Health System, news release, Aug. 11, 2025

Source: HealthDay