A new study, published in the March 9 online issue of npj Health Systems [https://doi.org/10.1038/s44401-026-00077-0], suggests that the answer depends less on the AI itself and more on how it’s designed.

The investigators found that health care AI systems work far better when tasks are distributed among multiple specialized AI “agents”—software systems that can perform complex tasks, learn, and adapt—rather than relying on a single, all-purpose agent. This multi-agent approach kept performance steady even as demands increased, while dramatically reducing computing costs and delays, say the investigators.

“For health care organizations, our findings point to a smarter way to use AI,” says senior study author Girish N. Nadkarni, MD, MPH, Barbara T. Murphy Chair of the Windreich Department of Artificial Intelligence and Human Health, Director of the Hasso Plattner Institute for Digital Health, Irene and Dr. Arthur M. Fishberg Professor of Medicine at the Icahn School of Medicine, and Chief AI Officer of the Mount Sinai Health System. “By assigning different tasks, such as finding patient information, extracting data, or checking medication doses, to specialized AI agents, systems can run faster and more reliably while keeping costs under control. Ultimately, this kind of design could help health care teams spend less time on administrative work and more time focusing on patients.”

As part of the study, the researchers compared two approaches to clinical AI: a single system responsible for handling many different clinical tasks, and a coordinated network of specialized AI agents overseen by a central “orchestrator.” Using state-of-the-art language models, the team evaluated performance across common clinical functions, including information retrieval, data extraction, and medication dosing calculations—under simulated real-world conditions involving up to 80 simultaneous tasks.

“What we found is that AI systems behave a lot like people,” says study lead author Eyal Klang, MD, formerly with the Icahn School of Medicine. “When you ask one system to do too many different things at once, performance suffers. But when one orchestrator agent divides the work among specialized agents, the system stays accurate, responsive, and far more efficient, even under heavy demand.”

The coordinated multi-agent system maintained superior accuracy levels while using far fewer computing resources, up to 65 times fewer, than a single-agent design. The study simulated real clinical “traffic,” where many types of tasks arrive at once and compete for attention, the investigators say.

“Our findings show that smart coordination is not just a technical preference,” Dr. Klang says. “It can make the difference between an AI system that continues to function smoothly and one that begins to break down when it is exposed to the pressures of real clinical workloads.”

Next, the research team plans to test these coordinated AI systems directly in clinical settings, using real-time patient data. If successful, this approach could help shape how hospitals and health systems scale AI in the future, helping them handle peak workloads without sacrificing quality or safety.

The researchers emphasize that the gains are not automatic: even sophisticated AI can fall short when systems are poorly designed or implemented. “Health care does not operate one task at a time,” Dr. Nadkarni says. “Hospitals face constant, overlapping demands, especially during busy periods. Our findings show that the future of health care AI is not a single super-intelligent system, but a coordinated team of focused agents that work together to scale safely, control costs, and support real clinical operations.”

“When a single agent handles everything, you can’t trace where it went wrong. With the orchestrator, every step is logged, which tool was called, what it returned, and how the answer was assembled. At 80 simultaneous tasks, the single agent dropped to 16 percent accuracy while burning 65 times more compute—and you’d have no way to figure out why. That kind of transparency isn’t optional in medicine,” says second author Mahmud Omar, MD, a visiting researcher in the Windreich Department. “This matters more now than ever—agentic AI is no longer a research concept. Tools like OpenAI’s operator mode, Claude’s Cowork, and similar platforms are putting autonomous agents directly in the hands of clinicians and patients. As that adoption accelerates, the architecture behind these systems has to be auditable from the start.”

The paper is titled “Orchestrated multi agents sustain accuracy under clinical‑scale workloads compared to a single agent.”

The study’s authors, as listed in the journal, are Eyal Klang, Mahmud Omar, Ganesh Raut, Reem Agbareia, Prem Timsina, Robert Freeman, Lisa Stump, Alexander Charney, Benjamin S. Glicksberg, Girish N. Nadkarni.

This work was supported  in part by the Clinical and Translational Science Awards (CTSA) grant UL1TR004419 from the National Center for Advancing Translational Sciences. Research reported in this publication was also supported by the Office of Research Infrastructure of the National Institutes of Health under award number S10OD026880 and S10OD030463.

For more Mount Sinai artificial intelligence news, visit: https://icahn.mssm.edu/about/artificial-intelligence.

Lifestyle interventions targeting physical activity, nutrition, sleep and smoking are key to mental health care, not optional extras, according to the report by a team of 30 authors from 19 countries.

“Our lifestyles can change the trajectory of our mental and physical health,” said lead author Dr Scott Teasdale, a dietitian and Senior Research Fellow with UNSW Sydney’s Discipline of Psychiatry and Mental Health and Mindgardens Neuroscience Network.

“Many people living with mental health challenges face barriers to being physically active, eating a balanced and nutrient-rich diet, getting quality sleep, and quitting smoking. These, in turn, impact their mental health further and contribute to physical health disparities,” Dr Teasdale said.

Making changes to lifestyle risk factors eases symptoms and improves overall health, making it an important addition to psychological therapy and medication, he said. But people with mental illness need support to make such changes.

“This is not just about individual behaviour change, it’s about transforming systems to support health and wellbeing,” Dr Teasdale said.

A roadmap for reform  

The Commission report, Implementing lifestyle interventions in mental health care, outlines a roadmap to improve care worldwide – from bringing in exercise and nutrition specialists to shifting workforce attitudes to prioritise a holistic approach.

It builds on a 2019 Commission report on protecting physical health in people with mental illness – who die 13 to 15 years earlier than the general population, largely due to preventable conditions like cardiovascular disease and diabetes.

Researchers reviewed 89 recent lifestyle interventions, targeting physical activity, nutrition, smoking cessation and sleep, to determine the most effective approaches, resulting in eight recommendations and 19 priorities for action. These were reviewed by people with lived experience and a Global South Advisory Group of 14 experts from lower income and conflict-affected countries to ensure they could be adapted across diverse settings.

Increased funding, upskilling of mental health staff and enabling access to a broader range of allied health professionals will be key to better incorporating lifestyle interventions into care.

“Mental health services have traditionally focused on medications, crisis care and therapy, and lifestyle hadn’t been prioritised — in funding, training or service delivery,” Dr Teasdale said. “We previously didn’t have the evidence on the benefits of lifestyle changes, but that’s no longer the case.”

While delivery methods must be tailored to local contexts, many core principles are universal, said senior author UNSW Professor Simon Rosenbaum.

“We’ve identified common elements that should apply to care, whether you’re in a refugee camp in Bangladesh or a hospital in Sydney’s eastern suburbs,” he said.

This includes creating psychologically safe environments and ensuring support staff have the empathy and skills to provide trauma-informed, culturally sensitive care.

“Embedding these interventions must be done in partnership with people who live with mental illness, and with attention to the social and economic realities they face,” Prof. Rosenbaum said.

Global South Advisory Group co-Chair Professor Pillaveetil Sathyadas Indu, from Kerala University of Health Sciences, said the recommendations were adaptable across diverse settings, including her home country of India.

“In countries with limited resources, the focus may be on upskilling existing staff and non-specialist workers, and engaging family members, to help deliver lifestyle interventions,” Prof. Indu said.

Embedding exercise and nutrition specialists into mental health services at top training and research institutions would also help drive systemic change, she said.

 Shifting clinical practice in Australia    

The shift to lifestyle-focused care is underway in Australia, with lifestyle changes included in clinical practice guidelines for mood disorders since 2020.

“An ideal treatment plan no longer starts and ends with medication and psychology support. It now begins with lifestyle changes and psychological support as the foundation, with medication added where needed,” Dr Teasdale said.

But change has been slow, amid budget constraints and a stretched workforce, and more needs to be done by government, health services and education providers to better embed lifestyle interventions into care.

While this requires greater upfront investment, it would reduce more substantial health care and societal costs long term, Dr Teasdale said.

“Improving these lifestyle factors is crucial for the mental wellbeing of every person, and in the prevention and management of mental illness.”

The report is one of two published by The Lancet Psychiatry Physical Health Commission on Wednesday, with the other, led by University of Queensland, focused on the physical health side effects of medication.

What Covid “long haulers” found was that their new illness was not so new. In fact, it resembled other post-viral syndromes: difficult to treat and neglected by science. In riveting and accessible prose, Prior follows an innovative band of patients who took matters into their own hands and researched the disease themselves, thereby flipping the script and illustrating a new paradigm for research. In these unprecedented times, the CDC and the WHO came to them. As Covid continues to circulate, its long-term effects could grow as well, weighing on the healthcare system for decades to come. But, as Prior shows, getting Long Covid treatments right could help revolutionize care for all complex and chronic illnesses.

Ryan Prior is a journalist and former Journalist-in-Residence at the Century Foundation. He covered the COVID-19 pandemic as a features writer for CNN and writes the Patient Revolution column for Psychology Today. He has also written for USA Today, STAT, the Guardian, and the Nation. He directed the documentary Forgotten Plague, is a board member at the ME Action Network, and was a Stanford Medicine ePatient Scholar.