A recent study conducted by the Mount Sinai Health System has found that artificial intelligence (AI) can help emergency department teams predict which patients will need hospital admission, providing this information hours earlier than current methods. The research involved more than 500 emergency department nurses across seven hospitals and evaluated a machine learning model trained on data from over one million past patient visits.
The study, published in the July 9 online issue of Mayo Clinic Proceedings: Digital Health (https://doi.org/10.1016/j.mcpdig.2025.100249), compared AI-generated predictions with nurses’ triage assessments during nearly 50,000 patient visits over two months at both urban and suburban hospitals within the health system.
“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,” said lead author Jonathan Nover, MBA, RN, Vice President of Nursing and Emergency Services at 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.”
Researchers found that the AI model performed reliably across different hospital settings and that combining human judgment with machine predictions did not significantly increase accuracy—suggesting that the AI system alone was effective at predicting admissions.
“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,” said 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.”
Although limited to one health system over two months, researchers hope these findings will guide future live clinical testing by integrating the AI model into real-time workflows in order to measure effects such as reduced boarding times and improved 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,” said 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.”
The paper is titled “Comparing Machine Learning and Nurse Predictions for Hospital Admissions in a Multisite Emergency Care System.” Authors include Jonathan Nover; Matthew Bai; Prem Tismina; Ganesh Raut; Dhavalkumar Patel; Girish N Nadkarni; Benjamin S Abella; Eyal Klang; and Robert Freeman.
Funding for this research came from resources provided by Scientific Computing and Data at Icahn School of Medicine at Mount Sinai as well as grants from Clinical and Translational Science Awards (CTSA) through UL1TR004419 from National Center for Advancing Translational Sciences and awards S10OD026880/S10OD030463 from Office of Research Infrastructure at National Institutes of Health.
