Foundation AI model uses MRI data to predict multiple brain disorders

[erronis]

https://medicalxpress.com/news/2026-02-foundation-ai-mri-multiple-brain.html

Artificial intelligence (AI) systems are computational models that can learn to identify patterns in data, make accurate predictions or generate content (e.g., texts, images, videos or sound recordings). These models can reliably complete various tasks and are now also used to carry out research rooted in different fields.

Over the past few decades, some AI models have proved promising for the early diagnosis and study of specific diseases or neuropsychiatric conditions. For instance, by analyzing large amounts of brain scans collected using a noninvasive technique known as magnetic resonance imaging (MRI), AI could uncover patterns associated with tumors, strokes and neurodegenerative diseases, which could help to diagnose these conditions.

Researchers at Mass General Brigham, Harvard Medical School and other institutes recently developed Brain Imaging Adaptive Core (BrainIAC), a large AI system pre-trained on a vast pool of MRI data that could be adapted to tackle different tasks. This foundation model, presented in a paper published in Nature Neuroscience, was found to outperform many models that were trained to complete specific medical or neuroscience-related tasks.

"There is a vast trove of data within the millions of brain MRIs performed each year in the United States," Benjamin H. Kann, senior author of the paper, told Medical Xpress. "Typically, these scans are analyzed by humans for a particular reason, but this only scratches the surface of the story that these scans might tell us about our patients. With AI and advanced computational imaging techniques, we can unlock much more information from these scans than ever before--which may lead to potent, clinically useful ways to track a variety of acute and chronic conditions, from stroke, to cancer, to dementia, as well as predict future risks for patients."

. . .

[jmbar2]

1. Interesting article - K&R

[hunter]

2. How will this technology benifit patients?

That's the only question worth asking and we won't know without double-blind studies.

False positives and assembly line medicine can be hazardous to one's health and financial well being.

Interesting research, however.

BrainIAC is not the sort of acronym I'd want to be associated with. If this ever becomes a commercial product they'll have to come up with a serious sounding name.

Okay, close your eyes and relax now while we stick your head in the BrainIAC

[erronis]

3. Good points. Obviously we want simple tests that can properly diagnose many issues.

We get some of these with our normal blood draws that measure 20-40 and more components and flag those that are out of normal range.

Theranos is an example of a company that over-promised on this model and engaged in fraud to get investments.

Most MRIs now are done based on suspicions of something going wrong. This would be more of a screening MRI which would be similar to yearly mammograms. But with the risks of false positives (identifying a potential problem when there is not one) and the immense costs of these scans.

I think I was trying to point out that this "AI" thing has some useful applications.