Study: AI programs might help ER overcrowding in hospitals
Artificial intelligence 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.
Copyright © 2025 HealthDay. All rights reserved.
Hashtags
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
UPI
6 hours ago
- UPI
Alcohol use by U.S. adults at all-time low, Gallup says
1 of 2 | The results of Washington, D.C.-based Gallup's new survey released Wednesday suggest the self-reported drinking habits of many Americans is down to a new record low of 54%. File Photo (2021) by Bill Greenblatt/UPI | License Photo Aug. 13 (UPI) -- A new Gallup Poll shows the use of alcohol among American adults is at its lowest point in a nearly 90-year downward trend. The results of Washington, D.C.-based Gallup's new survey released Wednesday suggest the self-reported drinking habits of many Americans is down to a new record low of 54% after "consecutive declines" since 1939 when the firm began tracking such behavior. The results of Gallup's annual Consumption Habits survey from July 7-21 supported data indicating that drinkers reported drinking less, and 53% of respondents say they believe that even a few drinks is bad for a person. Gallup experts are suggesting that, for the first time, it's now the majority view of the population that even moderate alcohol drinking is bad for one's health. Even John Gramlich, an associate research director at the nonpartisan Washington think tank Pew Research Center, called it "fascinating new data" in a social media post early Wednesday morning. The downward trend of drinking among young American adults has only accelerated from 59% in 2023 to 50% in the latest Gallup surveys. Previous Gallup results from 1997 to 2023 revealed at least 60% of Americans reported being casual alcohol drinkers. That number fluctuated for a few years before landing at its current 54% in the latest survey results. Gallup's historic data highlighted a 58% use of alcohol among Americans in its initial 1939 poll only 10 years after the economically devastating October 1929 stock market crash, but a one-time low in 1958 of 55%. Gallup said the belief that drinking is detrimental is now gaining traction with older adults, too. From 2023-2025, there was a 5% drop to 56% among people age 55 and older. The World Health Organization noted earlier last month that a separate 2022 Gallup Poll found strong public support among respondents for higher taxes on alcohol, tobacco and "sugary drinks." "Why? Because these products can harm your health & smart taxes help reduce consumption & fund better healthcare," the WHO said on social media.
UPI
9 hours ago
- UPI
Researchers say changes in stride can ease arthritis pain
A new study published in The Lancet Rheumatology suggests foot positioning while walking can reduce stress on a person's knee joint. Photo by Samuel Corum/UPI | License Photo Slightly altering your stride while walking could considerably ease pain caused by wear-and-tear knee arthritis, a new study says. Foot positioning while walking can reduce stress on a person's knee joint, researchers reported Tuesday in The Lancet Rheumatology. People trained to angle their feet slightly inward or outward from their natural alignment experienced slower degeneration of the cartilage cushion inside their aching knees, results show. They also reported greater reductions in knee pain and better knee function after a year, researchers said. "Altogether, our findings suggest that helping patients find their best foot angle to reduce stress on their knees may offer an easy and fairly inexpensive way to address early-stage osteoarthritis," said co-lead researcher Valentina Mazzoli, an assistant professor of radiology at NYU Grossman School of Medicine in New York City. This strategy could lower patients' reliance on painkillers and delay the need for knee replacement surgery, Mazzoli added in a news release. For the study, researchers recruited 68 people with knee osteoarthritis and recorded their gait while walking on a treadmill. A computer program simulated their walking patterns and calculated the maximum stress they were placing on their knees. The research team also generated computer models of four new foot positions angled inward or outward by 5 or 10 degrees and estimated which would best reduce stress on each person's knees. Participants then were randomly divided into two groups. Half were trained in six sessions to walk with the foot angle ideal to them, and the other half were told to continue walking normally. Overall, those who adjusted their gait reduced maximum loading in their knees by 4%, while those who kept their normal stride increased loading by more than 3%. Further, those taught the new foot position experienced a 2.5-point reduction on a 10-point pain scale, equivalent to the effect of over-the-counter painkillers like NSAIDs and acetaminophen, researchers said. "These results highlight the importance of personalizing treatment instead of taking a one-size-fits-all approach to osteoarthritis," Mazzoli said. "While this strategy may sound challenging, recent advances in detecting the motion of different body parts using artificial intelligence may make it easier and faster than ever before." AI software that estimates joint loading using smartphone videos is now available, allowing doctors to perform a gait analysis without specialized lab equipment, researchers noted. The team next plans to test whether those AI tools can indeed help identify the best walking method for knee arthritis patients, Mazzoli said. They also plan to expand their study to include people with obesity. More information The American Academy of Orthopedic Surgeons has more about knee arthritis. Copyright © 2025 HealthDay. All rights reserved.
UPI
9 hours ago
- UPI
NIH study links cigarette cessation with drug, alcohol addiction recovery
On Wednesday, scientists at the National Institutes of Health in Bethesda, Md. (pictured in March), said fresh data in its nearly 15-year-old ongoing PATH study with the FDA is suggesting longer-term remission from drug or alcohol addiction is more likely if a person also quits cigarettes at the same time. File Photo by Annabelle Gordon/UPI | License Photo Aug. 13 (UPI) -- A new federal study is linking the ability to quit smoking with longer-term success from the grip of drug or alcohol addiction, as well. Scientists at the National Institutes of Health on Wednesday said that fresh data in its nearly 15-year-old ongoing PATH study with the U.S. Food and Drug Administration is suggesting that sustained remission from drug or alcohol addiction is more likely to be achieved if a person also quits cigarettes at the same time versus separately. The PATH study, or Population Assessment of Tobacco and Health Study, has been ongoing for more than a decade in an attempt to better understand the health effects of smoking. "It underscores the importance of addressing different addictions together, rather than in isolation," Dr. Nora Volkow director of NIH's National Institute on Drug Abuse, said in a statement. Health officials pointed out that people in addiction also have a higher likelihood of being addicted to nicotine. The longitudinal NIH analysis showed a 42% greater odd of going from a "current" to "former" smoker if a person is already working in a recovery stage from a non-tobacco vice. Volkow added that NIH national sampling is "strong evidence" that quitting cigarette smoking "predicts improved recovery from other substance use disorders." The federally funded PATH study analyzed more than 2,650 participants age 18 or older with a history of substance abuse but with a change in recovery over a four-year period. As part of the study, NIH researchers asked annual questions of participants concerning smoking habits and use of other items. "Although the health benefits of quitting smoking are well-known, smoking cessation has not been seen as a high priority in drug addiction treatment programs," stated Dr. Wilson Compton, deputy director of NIDA and the study's senior author. The study's authors highlighted it's uniqueness but noted it was only suggestive in nature, that prior studies had utilized addiction-specific data out of U.S. drug and alcohol treatment centers that "could not adequately test for an association" with cigarette smoking. Compton said the findings "bolster support for including smoking cessation as part of addiction treatment." Officials at NIH said its researchers have an "increasing confidence" in the belief the new finding are "generalizable to the millions of adults" in the throes of alcohol or drug addiction in the United States. However, they added that further research is needed to "definitively establish" a causal connection.
