Mayo Clinic scientists are leveraging artificial intelligence (AI) and machine learning to enhance the analysis of electroencephalogram (EEG) tests, enabling neurologists to identify early signs of dementia more quickly and accurately. Traditionally used to detect epilepsy, EEGs involve attaching electrodes to the scalp to monitor brain activity, with results interpreted by trained experts.
New research published in Brain Communications by the Mayo Clinic Neurology AI Program (NAIP) demonstrates that AI can expedite analysis and alert experts to subtle abnormal patterns that might go unnoticed. This technology could eventually help distinguish between different causes of cognitive problems, such as Alzheimer's disease and Lewy body dementia. The study suggests that EEGs, which are more accessible and less invasive than other brain health tests, could become a valuable tool for early detection of cognitive issues.
"There's a lot of medical information in these brain waves about the health of the brain in the EEG," said David T. Jones, M.D., a neurologist and director of NAIP. "It's well known that you can see these waves slow down and look a bit different in people who have cognitive problems. In our study, we wanted to know if we could accurately measure and quantify that type of slowing with the aid of AI."
To develop this tool, researchers analyzed data from over 11,000 patients who underwent EEGs at Mayo Clinic over ten years. They utilized machine learning and AI to distill complex brain wave patterns into six specific features, teaching the model to ignore irrelevant data while focusing on patterns indicative of cognitive problems like Alzheimer's disease.
"It was remarkable the way the technology helped quickly extract EEG patterns compared to traditional measures of dementia like bedside cognitive testing, fluid biomarkers and brain imaging," said Wentao Li, M.D., co-first author of the paper.
Dr. Jones emphasized that while AI-enhanced EEGs would not replace other exams such as MRIs or PET scans, they could provide a more economical and accessible diagnostic tool for early detection in communities lacking access to specialized clinics or equipment.
"It's really important to catch memory problems early, even before they're obvious," Dr. Jones stated. "Having the right diagnosis early helps us give patients the right outlook and best treatment."
Further testing and validation will require several additional years of research. However, Dr. Jones noted that this work illustrates how clinical data can be used to integrate new tools into clinical practice, enhancing existing assessments' capabilities.
"This work exemplifies multidisciplinary teamwork to advance translational technology-based healthcare research," said Yoga Varatharajah, Ph.D., co-first author of the paper.
The research received funding from various sources including the Edson Family Fund, Epilepsy Foundation of America, Benjamin A. Miller Family Fellowship in Aging and Related Diseases, Mayo Clinic Neurology Artificial Intelligence Program, National Science Foundation (Award No. IIS-2105233), and National Institutes of Health (grant UG3 NS123066).
A complete list of co-authors and financial disclosures is available in the manuscript.
###
Mayo Clinic is a nonprofit organization committed to innovation in clinical practice, education and research.
