The many ways that AI enters rheumatology

Artificial intelligence (AI) is entering the mainstream. The term encompasses a wide variety of machines that can learn from data, identify patterns, and make decisions. But how can it be used to support health care? EULAR—The European Alliance of Associations for Rheumatology—has picked a number of abstracts for its 2025 congress in Barcelona that showcase how AI is influencing different areas in rheumatology—from diagnosis through to monitoring, risk prediction, and patient communication.

Pregnancy outcomes in autoinflammatory disease

Autoinflammatory diseases predominantly affect young patients, many of whom may go on to become pregnant. For many inflammatory diseases, pregnancy can be a period of destabilization of inflammatory activity, and may lead to complications for the mother or fetus. But there is a lack of prospective large cohort data on pregnancy outcomes in these patients—particularly in familial Mediterranean fever (FMF).

Machine-learning model can reliably predict cognitive performance based on lifestyle indicators

A new study offers insight into the health and lifestyle indicators—including diet, physical activity and weight—that align most closely with healthy brain function across the lifespan. The study used machine learning to determine which variables best predicted a person’s ability to quickly complete a task without becoming distracted.

When it comes to our working memory, it’s more complicated than we thought

It’s been long established that our working memory, which allows us to temporarily hold and use information, such as remembering a phone number or a shopping list, is largely driven by the brain’s prefrontal cortex. However, new research finds that the part of the brain used in visual processing plays a much more critical role in working memory than previously thought.