New AI Tool Accurately Detects Nine Types of Dementia Using Single Brain Scan: Study Shows

Published in the journal Neurology, Mayo Clinic researchers have introduced an artificial intelligence (AI) tool that can identify brain activity patterns linked to nine types of dementia including Alzheimer’s disease from a single, commonly used scan. The tool, called StateViewer, marks a major step forward in early, accurate diagnosis and faster clinical decision-making.

Diagnosing dementia has long been a complex and time-consuming process, often involving a mix of cognitive assessments, imaging, clinical interviews, and referrals to specialists. Even with these, distinguishing dementia remains difficult.

To tackle this challenge, Mayo Clinic researchers trained StateViewer on more than 3,600 brain scans from both dementia patients and cognitively healthy individuals. The tool analyzes FDG-PET scans used to observe glucose metabolism in the brain and compares them to a vast database of confirmed dementia cases. By identifying specific brain activity patterns, the tool matches scans with distinct dementia types.

StateViewer achieved an 88% accuracy rate in identifying dementia types and helped clinicians interpret scans nearly twice as fast and with up to three times the accuracy of standard workflows.

“Every patient who walks into my clinic carries a unique story shaped by the brain’s complexity. That complexity drew me to neurology and continues to drive my commitment to clearer answers.” said Dr. David Jones, Mayo Clinic neurologist and director of the Neurology Artificial Intelligence Program. “StateViewer reflects that commitment a step toward earlier understanding, more precise treatment and, one day, changing the course of these diseases.”

Dr. Jones collaborated with data scientist Dr. Leland Barnard, who led the engineering behind StateViewer. “Seeing how this tool could assist physicians with real-time, precise insights and guidance highlights the potential of machine learning for clinical medicine."

By turning complex brain data into clear visual maps, StateViewer offers clinicians regardless of specialty real-time, interpretable insights. This advancement could help bring expert-level diagnostic support to clinics with limited access to neurology services.

Reference: Barnard, L., Botha, H., Corriveau-Lecavalier, N., Graff-Radford, J., Dicks, E., Gogineni, V., ... & Alzheimer's Disease Neuroimaging Initiative. (2025). An FDG-PET–Based Machine Learning Framework to Support Neurologic Decision-Making in Alzheimer Disease and Related Disorders. Neurology, 105(2), e213831.