A new Mayo Clinic AI tool detects dementia patterns in brain scans with remarkable precision, potentially transforming early diagnosis.
A powerful new artificial intelligence tool developed by Mayo Clinic could transform how doctors detect dementia. The tool, called StateViewer, can spot brain activity patterns tied to nine different types of dementia, including Alzheimer’s disease, using just one widely available brain scan.
Published in the journal Neurology, the study shows that StateViewer correctly identified the type of dementia in 88% of cases. Additionally, it helped doctors analyze scans nearly twice as fast and with up to three times greater accuracy compared to traditional methods.
Researchers trained the AI using over 3,600 brain scans from both patients with dementia and individuals without cognitive issues. This large dataset allowed the tool to learn the subtle patterns that distinguish one type of dementia from another.
Early and accurate diagnosis is one of the biggest challenges in dementia care—especially when multiple brain conditions overlap. This tool could be a game-changer, helping match patients with treatments earlier, when interventions are likely to be most effective.
What’s more, because StateViewer uses common imaging techniques, it could bring advanced diagnostic support to hospitals and clinics that don’t have specialized neurology teams.
The rising toll of dementia
Dementia affects more than 55 million people worldwide, with nearly 10 million new cases each year. Alzheimer’s disease, the most common form, is now the fifth-leading cause of death globally. Diagnosing dementia typically requires cognitive tests, blood draws, imaging, clinical interviews, and specialist referrals. Even with extensive testing, distinguishing conditions such as Alzheimer’s, Lewy body dementia, and frontotemporal dementia remains challenging, including for highly experienced specialists.
StateViewer was developed under the direction of David Jones, M.D., a Mayo Clinic neurologist and director of the Mayo Clinic Neurology Artificial Intelligence Program.
“Every patient who walks into my clinic carries a unique story shaped by the brain’s complexity,” Dr. Jones says. “That complexity drew me to neurology and continues to drive my commitment to clearer answers. StateViewer reflects that commitment — a step toward earlier understanding, more precise treatment and, one day, changing the course of these diseases.”
To bring that vision to life, Dr. Jones worked alongside Leland Barnard, Ph.D., a data scientist who leads the AI engineering behind StateViewer.
“As we were designing StateViewer, we never lost sight of the fact that behind every data point and brain scan was a person facing a difficult diagnosis and urgent questions,” Dr. Barnard says. “Seeing how this tool could assist physicians with real-time, precise insights and guidance highlights the potential of machine learning for clinical medicine.”
Turning brain patterns into clinical insight
The tool analyzes a fluorodeoxyglucose positron emission tomography (FDG-PET) scan, which shows how the brain uses glucose for energy. It then compares the scan to a large database of scans from people with confirmed dementia diagnoses and identifies patterns that match specific types, or combinations, of dementia.
Alzheimer’s typically affects memory and processing regions, Lewy body dementia involves areas tied to attention and movement, and frontotemporal dementia alters regions responsible for language and behavior. StateViewer displays these patterns through color-coded brain maps that highlight key areas of brain activity, giving all clinicians, even those without neurology training, a visual explanation of what the AI sees and how it supports the diagnosis.
Mayo Clinic researchers plan to expand the tool’s use and will continue evaluating its performance in a variety of clinical settings.
Reference: “An FDG-PET–Based Machine Learning Framework to Support Neurologic Decision-Making in Alzheimer Disease and Related Disorders” by Leland Barnard, Hugo Botha, Nick Corriveau-Lecavalier, Jonathan Graff-Radford, Ellen Dicks, Venkatsampath Gogineni, Gemeng Zhang, Brian J. Burkett, Derek R. Johnson, Sean J. Huls, Aditya Khurana, John L. Stricker, Hoon-Ki Paul Min, Matthew L. Senjem, Winnie Z. Fan, Heather Wiste, Mary M. Machulda, Melissa E. Murray, Dennis W. Dickson, Aivi T. Nguyen, R. Ross Reichard, Jeffrey L. Gunter, Christopher G. Schwarz, Kejal Kantarci, Jennifer L. Whitwell, Keith Anthony Josephs, David S. Knopman, Bradley F. Boeve, Ronald C. Petersen, Clifford R. Jack, Val J. Lowe and David T. Jones, 27 June 2025, Neurology.
DOI: 10.1212/WNL.0000000000213831
Never miss a breakthrough: Join the SciTechDaily newsletter.
Follow us on Google and Google News.
2 Comments
A guy in my area hated his job at a major, major computer co. So, he got a PET scan in his early 50s, and told everyone he has Alzheimer’s. I said to him, “XXX, what do you mean, you have Alzheimer’s? You ride a motorcycle, drive a car and seem normal?” He said, “Well, you should have seen me before.” So he’s driving a 4,000 lb car, riding around, getting full pay from XXXXXsoft Corp and claiming to have dementia. These tests may have unintended consequences in that people who are fully productive, and may in fact never live to florid dementia will be declared redundant, or self declare.
I mean, if you show a positive on the scan but were going to die of sudden cardiac death first, is that right?
My father, who is in the beginning phases of dementia at the age of 70 literally had to stop working because he cant remember how to use the software. Its too much of a daily struggle. He sold his sail boat because he’s too forgetful and that could lead to an unsafe situation on a boat. The clinicians diagnosed him, through verbal tests, blood, brain scans, etc that yes, he has growing issues. When you speak with my dad and he forgets the word for “bread” and “spaghetti” you know you’re dealing with someone dealing with cognitive decline.
So, it seems to me, there are varying degrees and we are lacking some standards here. I agree that you could be diagnosed with a brain scan etc, but likely may not be impared as of yet.
Although, the humanity of it is that — if you are diagnosed with legitimate dementia, however early, you are staring at a bleak future. And you better start living your best life because the clock is definitely ticking!
As I consider my future, my dad and my grandmother’s diagnoses, I wonder if it is in the cards for me. I hope I can live a full life through the ripe old age of 90-100. But if my mind starts melting when I’m 70, thats 20 years lost. It is sad. Let people live their life. We’re only here so long, or rather, so short.
If I’m diagnosed early on, I’ll retire and start living a life of freedom and contribution to the greater good instead of feeding the corporate machine. Better that than slave away my better years and retire when I’m a vegetable.