Mayo Clinic researchers believe artificial intelligence can enable earlier and faster dementia diagnoses as dementia spreads.
The Mayo Clinic Neurology AI Program (NAIP) in Rochester, Minnesota, used AI and EEG tests to detect particular dementia types faster than humans.
These findings suggest that EEGs could be more accessible, cheaper, and less intrusive for early brain health assessment, according to a hospital press release.
The study was published in Brain Communications last week.
What’s an EEG?
A technician places small metal electrodes on the patient’s scalp to measure brain activity with an EEG.
READ MORE: Wendy Williams’ Guardian Sells NYC Penthouse At A Loss As Dementia Has Reportedly Incapacitated Her
The test records brain electrical impulses as wavy lines.
Dr. David Jones, a behavioral neurology doctor who oversees the artificial intelligence program at Mayo Clinic in Minnesota, says it is mostly used to diagnose epilepsy but can also detect other brain diseases.
The clinic evaluates hundreds of neurological patients with EEGs annually.
Jones told Fox News Digital that brain wave patterns vary in dementia or cognitive impairments caused by Alzheimer’s or Lewy body disease for some time.
READ MORE: Wendy Williams Was Diagnosed With Frontotemporal Dementia And Aphasia
“However, it takes a lot of specialized analysis, expertise and manual labor to extract that information, so Alzheimer’s and dementia are not routinely assessed on EEG.”
Accessing ‘hidden information’
Jones said this study used computer algorithms to identify “hidden information” in patients’ brain waves without physical work.
The Mayo Clinic-built AI technology was trained on data from over 11,000 EEG patients over a decade.
The model detected six patterns in complex brain waves from Alzheimer’s or Lewy body dementia patients that were not present in healthy participants, according to Jones.
Other measurements like cognitive testing, blood biomarkers, and brain PET scans supported the association.
Overall, the AI technology cut EEG reading time by 50% and improved accuracy “pretty significantly,” Jones said.
“This tells us that there is a lot of unused information in clinically acquired EEGs that we can extract automatically — and now we can begin to build better tools, algorithms and methods,” he said.
The neurologist says this type of study at scale would be “very difficult” without AI or machine learning.
‘Significant leap forward’
Harvey Castro, a Dallas-based board-certified emergency medicine physician and national speaker on AI in health care, called Mayo Clinic’s research “a significant leap forward.”
READ MORE: Elon Musk Provides An Update As The Second Person Receives Neuralink Brain Implants
“This technology can rapidly and precisely analyze brain wave patterns, identifying early signs of dementia often invisible to the human eye,” he said on Fox News.
“There is a lot of unused information in clinically acquired EEGs that we can extract automatically.”
Castro said he rarely uses EEGs as an ER doctor because they take time to interpret.
“However, AI technology allows for fast processing of large amounts of data, facilitating quicker, more informed decisions about a patient’s cognitive health,” added he.
“As a result, I can see this becoming a new tool for me to use in the ER.”
Castro calls AI-driven EEG analysis a “game-changer” in rural and neglected communities.
“It provides a cost-effective, non-invasive method to screen for cognitive issues early, where advanced diagnostic tools like MRIs or PET scans are limited.”
Next steps
Jones wants to integrate AI-driven EEG analysis into a “multimodal” dementia test.
“That means being able to model brain scans, blood work, cognitive tests and brain waves into one complete model of brain health,” he said on Fox News.
The AI tool must be integrated into clinical practice next.
“So if you’re coming in and having an EEG for epilepsy or a sleep study, we’ll also simultaneously be able to tell you something about your cognitive health, and whether we see something that means you might need to see a behavioral neurologist,” he added.
Brain scan of man
To make this technology broadly available, the researcher said it will need years of development. (iStock)
The doctor envisions EEGs becoming “highly scalable and portable” so people may undertake cognitive exams remotely “in the same way that you measure blood pressure or heart rate in your own home.”
Jones said several years of research are needed before this technology is generally available.
Risks and constraints
Castro warned that integrating AI into clinical practice is difficult despite its benefits.
“While AI can provide valuable insights, the clinician’s expertise and empathy remain irreplaceable.”
“These include the need for substantial training for health care professionals to use these tools effectively and the potential for over-reliance on AI at the expense of clinical judgment,” he said on Fox News.
AI must be balanced with a “human touch,” Castro added.
“While AI can provide valuable insights, the clinician’s expertise and empathy remain irreplaceable in delivering holistic patient care.”
The doctor also stressed data protection, informed consent, and AI algorithm bias prevention.
AI dementia model
The model discovered six unique patterns in complex brain waves from Alzheimer’s or Lewy body dementia patients that were not detected in healthy individuals. (iStock)
The Mayo Clinic neurologist Jones admitted that overusing algorithms is risky, but said the system is created using “real-world data for real-world use.”
“Its value is gauged by whether it’s helping us take care of our patients — that’s our focus.”
Jones told Fox News Digital the staff is “well aware” of potential issues and mitigates them.
“We follow good AI and machine learning practices as part of the ethos of our software design and the values of Mayo Clinic.”
Radiant TV, offering to elevate your entertainment game! Movies, TV series, exclusive interviews, music, and more—download now on various devices, including iPhones, Androids, smart TVs, Apple TV, Fire Stick, and more.
