As artificial intelligence (AI) becomes more common in health care, from managing records to assisting with medication decisions, researchers at the Icahn School of Medicine at Mount Sinai are asking an important question: How well does AI hold up when the workload gets intense at health system scale? 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.

A study from community researchers partnering with Rutgers Health faculty and staff offers an in-depth look at the pregnancy, childbirth and postpartum experiences of women of color in New Jersey – finding both meaningful progress and continued inequities persist in the state’s maternal care.

The gut microbiome—the trillions of bacteria and other microbes that inhabit the gastrointestinal tract—drives a process vital for protecting the colon against tissue injury, according to the findings of a study co-led by Cedars-Sinai Health Sciences University investigators.

In a large study, younger stroke survivors reported more difficult concentrating and more poor mental health days

According to a new study from the University of Missouri School of Medicine, holding blood thinners for too long both before and after free flap reconstruction surgery could jeopardize the patient's outcome.