By giving clinicians advance notice, this approach may enhance patient care and the patient experience, reduce overcrowding and "boarding" (when a patient is admitted but remains in the ED because no bed is available), and enable hospitals to direct resources where they’re needed most. Among the largest prospective evaluations of AI in the emergency setting to date, the study published in the July 9 online issue of the journal Mayo Clinic Proceedings: Digital Health.
In the study, researchers collaborated with more than 500 ED nurses across the seven-hospital Health System. Together, they evaluated a machine learning model trained on data from more than 1 million past patient visits. Over two months, they compared AI-generated predictions with nurses’ triage assessments to see whether AI could help identify likely hospital admissions sooner after the patient arrives.
"Emergency department overcrowding and boarding have become a national crisis, affecting everything from patient outcomes to financial performance. Industries like airlines and hotels use bookings to forecast demand and plan. In the ED, we don’t have reservations. Could you imagine airlines and hotels without reservations, solely forecasting and planning from historical trends? Welcome to health care," says lead author Jonathan Nover, MBA, RN, Vice President of Nursing and Emergency Services, Mount Sinai Health System. "Our goal was to see if AI combined with input from our nurses, could help hasten admission planning, a reservation of sorts. 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."
The study, involving nearly 50,000 patient visits across Mount Sinai’s urban and suburban hospitals, showed that the AI model performed reliably across these diverse hospital settings. Surprisingly, the researchers found that combining human and machine predictions did not significantly boost accuracy, indicating that the AI system alone was a strong predictor.
"We wanted to design a model that doesn’t just perform well in theory but can actually support decision-making on the front lines of care," says co-corresponding senior author Eyal Klang, MD, Chief of Generative AI in the Windreich Department of Artificial Intelligence and Human Health at the Icahn School of Medicine at Mount Sinai. "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. The strength of this approach is its ability to turn complex data into timely, actionable insights for clinical teams - freeing them up to focus less on logistics and more on delivering the personal, compassionate care that only humans can provide."
While the study was limited to one health system over a two-month period, the team hopes the findings will serve as a springboard for future live clinical testing. The next phase involves implementing the AI model into real-time workflows and measuring outcomes such as reduced boarding times, improved patient flow, and operational efficiency.
"We were encouraged to see that AI could stand on its own in making complex predictions. 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," says co-corresponding senior author Robbie Freeman, DNP, RN, NE-BC3, Chief Digital Transformation Officer at Mount Sinai Health System. "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. 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."
Nover J, Bai M, Tismina P, Raut G, Patel D, Nadkarni GN, Abella BS, Klang E, Freeman R.
Comparing Machine Learning and Nurse Predictions for Hospital Admissions in a Multisite Emergency Care System.
Mayo Clin Proc Digit Health. 2025 Jul 9;3(3):100249. doi: 10.1016/j.mcpdig.2025.100249