Posted on 06/30/2025 5:29:54 AM PDT by Red Badger
ROCHESTER, Minn. — Mayo Clinic researchers have developed a new artificial intelligence (AI) tool that helps clinicians identify brain activity patterns linked to nine types of dementia, including Alzheimer's disease, using a single, widely available scan — a transformative advance in early, accurate diagnosis.
The tool, StateViewer, helped researchers identify the dementia type in 88% of cases, according to research published online on June 27, 2025, in Neurology, the medical journal of the American Academy of Neurology. It also enabled clinicians to interpret brain scans nearly twice as fast and with up to three times greater accuracy than standard workflows. Researchers trained and tested the AI on more than 3,600 scans, including images from patients with dementia and people without cognitive impairment.
This innovation addresses a core challenge in dementia care: identifying the disease early and precisely, even when multiple conditions are present. As new treatments emerge, timely diagnosis helps match patients with the most appropriate care when it can have the greatest impact. The tool could bring advanced diagnostic support to clinics that lack neurology expertise.
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.
For a complete list of authors, disclosures and funding, review the study.
###
About Mayo Clinic
Mayo Clinic is a nonprofit organization committed to innovation in clinical practice, education and research, and providing compassion, expertise and answers to everyone who needs healing. Visit the Mayo Clinic News Network for additional Mayo Clinic news.
Joey says, “three outa four ain’t bad, pal”
Time to test Joe-tato to see how many of the nine he has.
No joke, man!.....................
Still time to learn a new language.
The tool analyzes a fluorodeoxyglucose positron emission tomography
+++++++
Yeah, but what about methylfuckinbadstuff emissions?
Come on, AI, you got this..
I got a kick out of the study where they put dementia patients on a low carb died. The patients significantly improved due to the diet (certainly not cured, but far better than prior). Then the study ended and they were put back on the ‘proper’ (meaning high-carb diet) as prescribed by the ‘experts’. Of course they then reverted back to their original condition.
Maybe in 20 years, people will be allowed to draw the PROPER conclusions from work like this.
Only nine? I have been accused of at least 37 kinds.
forgetful
preoccupied
confused
absentminded
oblivious
bewildered
careless
dazed
senile
unmindful
amnesic
neglectful
absent
lost
negligent
abstracted
unfocused
bemused
thoughtless
muddled
scatterbrained
unaware
inattentive
amnesiac
inconsiderate
remiss
unconscious
heedless
unfocussed
befuddled
lax
unthinking
slack
unknowing
befogged
unperceptive
unheeding
insensible
The problem is that they won’t just do a Pet Scan on someone without a concern. And if there is enough evidence for “concern”, it’s already too late.
In the end, the scan will be used to provide the, “Yup, its dementia” diagnosis.
If I knew which way it was, I’d take you out back and punch you in your dog face.
Guilty as charged. :(
😎........................
Goin' in for a scan today?
A friend was told she’d had a minor heart attack, based on interpretation by AI. After a bevy of tests, the final result was ‘there was no heart attack.’ AI not quite ready for prime time.
I’d rather it be wrong on a positive than wrong on a negative...........
I’ve walked 5 relatives through the dementia exercise. I’ve gotten pretty good at spotting it. Now I see a hint of it and I run in the opposite direction.
But, as they say, you never hear the bullet with your name on it.
Brother ping.
wy69
While there are failures, there are successes identifying condi5ions/diseases using ai that were hard to diagnose- there is a medical a folks can type in symptoms- some people are finally getting diagnosed
It would be interesting if they ask about political affiliations and correlate the results.
If you can remember, let us know the results (your).
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.