Mayo Clinic researchers have developed a new artificial intelligence tool (AI) that helps clinicians to identify the standards of brain activity associated with nine types of dementia, including Alzheimer’s disease, using a single, widely available scanning – a transformative progress.
The tool, StateViewer, helped researchers to identify the type of dementia in 88% of cases, according to a study published online on June 27, 2025, in the NeurologyThe medical journal of the American Academy of Neurology. It also allowed clinicians to interpret brain scanning almost twice as fast and up to three times more accuracy than standard work flows. The researchers were trained and examined the AI in more than 3,600 scans, including images of patients with dementia and people without cognitive dysfunction.
This innovation faces a basic challenge in the care of dementia: Determination of the disease early and precisely, even when there are multiple conditions. As new treatments occur, early diagnosis helps to match patients with the most appropriate care when it may have the greatest impact. The tool could bring advanced diagnostic support to clinics that do not have neurology expertise.
The rising number 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 cause of death worldwide. Diagnosis of dementia usually requires cognitive tests, blood pulling, imaging, clinical interviews and special references. Even with extensive tests, distinctive conditions such as Alzheimer’s dementia, Lewy Body Dementia and Frontotemporal Dementia remain difficult, including high -level experts.
The Stateviewer was under the guidance of David Jones, MD, a Mayo Neurologist and director of the Artificial Intelligence Program Mayo Clinic Neurology.
Every patient entering the clinic has a unique story shaped by the complexity of the brain. This complexity has drew me to neurology and continues to lead my commitment to clearer answers. Stateviewer reflects this commitment – a step towards previous understanding, more accurate treatment and, one day, changing the course of these diseases. “
David Jones, MD, Mayo Clinic Neurology
To bring this vision to life, Dr. Jones worked with Leland Barnard, Ph.D., a data scientist leading Ai Engineering behind the Stateviewer.
“As we designed the Stateviewer, we never lost the fact that behind every point of data and brain scanning was a person who was facing a difficult diagnosis and urgent questions,” says Dr. Barnard. “Seeing how this tool could help doctors with real -time, accurate ideas and guidance highlights the potential of mechanical learning for clinical medicine.”
Turning brain standards into clinical insight
The tool analyzes a FDG-PET emission tomography, which shows how the brain uses glucose for energy. It then compares the scan with a large database of scanning from people with confirmed dementia diagnoses and identifies patterns that match specific types or combinations of dementia.
Alzheimer’s typically affects memory and processing areas, Lewy’s body dementia includes areas associated with attention and movement and frontal dementia alter the areas responsible for language and behavior. The Stateviewer displays these patterns through color -coded brain maps that emphasize basic areas of brain activity, giving all clinicians, even those who do not have neurology training, a visual explanation of what AI sees and how it supports diagnosis.
Mayo Clinic researchers plan to expand the use of the tool and will continue to evaluate its performance in a variety of clinical arrangements.
Source:
Magazine report:
Barnard, L., et al. (2025). A FDG-PET-based mechanical learning framework to support neurological decision-making in Alzheimer’s disease and related disorders. Neurology. Doi.org/10.1212/wnl.0000000000213831.
