Mayo Clinic Unveils AI Tool for Dementia Diagnosis

The AI tool could be especially beneficial in clinics that lack neurology specialists, offering advanced diagnostic support in real time.
Researchers at Mayo Clinic have developed a new artificial intelligence (AI) tool that can identify brain activity patterns associated with nine types of dementia, including Alzheimer’s disease, using a single, widely available scan.
The innovation, known as StateViewer, represents a major advancement in the early and accurate diagnosis of dementia.
According to a study published on June 27, 2025, in Neurology, the official journal of the American Academy of Neurology, StateViewer identified the correct dementia type in 88% of cases.
It also enabled clinicians to interpret brain scans nearly twice as fast and with up to three times the accuracy of standard diagnostic workflows. Researchers trained and tested the tool using more than 3,600 brain scans from both patients with dementia and individuals without cognitive impairment.
StateViewer addresses a central challenge in dementia care: pinpointing the specific type of dementia early, especially when multiple conditions are present. This is increasingly critical as new treatment options emerge, and early diagnosis can help connect patients with interventions at the most effective stage.
The AI tool could be especially beneficial in clinics that lack neurology specialists, offering advanced diagnostic support in real time.
The Rising Global Burden of Dementia
Currently, dementia impacts more than 55 million people globally, with an estimated 10 million new cases every year. Alzheimer's disease remains the most common form and is now the fifth-leading cause of death worldwide.
Diagnosis typically involves a complex process of cognitive assessments, blood tests, imaging, clinical interviews, and specialist referrals. Even with such a thorough approach, distinguishing between conditions such as Alzheimer’s, Lewy body dementia, and frontotemporal dementia remains difficult, even for expert neurologists.
The development of StateViewer was led by Dr David Jones, neurologist and director of the Mayo Clinic Neurology Artificial Intelligence Program.
“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,” he said.
Dr Jones collaborated with Leland Barnard, Ph D, a data scientist at Mayo Clinic and the AI engineer behind the new system.
“Seeing how this tool could assist physicians with real-time, precise insights and guidance highlights the potential of machine learning for clinical medicine,” Dr Barnard added.
How It Works
StateViewer analyzes fluorodeoxyglucose positron emission tomography (FDG-PET) scans, which measure how the brain consumes glucose. The AI then compares these scans with a large database of brain images from patients with confirmed dementia diagnoses to detect matching patterns.
Each type of dementia affects different brain regions. Alzheimer’s impacts memory and cognitive areas, Lewy body dementia affects movement and attention zones, while frontotemporal dementia influences language and behavioral functions.
The tool generates color-coded brain maps highlighting these activity patterns, enabling clinicians, even those without specialized neurology training, to understand and communicate diagnostic findings more effectively.
Mayo Clinic researchers plan to expand the clinical deployment of StateViewer and continue evaluating its performance in diverse healthcare settings.
Stay tuned for more such updates on Digital Health News