• Posted July 31, 2024

AI Is Helping Doctors Interpret a Crucial Brain Test

Artificial intelligence is adding new luster to the old-fashioned EEG brain scan, increasing the potential usefulness of the century-old medical test, a new report says.

The EEG, or electroencephalogram, tracks brain activity through a dozen or more electrodes stuck to the scalp. It is often used to detect epilepsy.

But the test’s squiggly waves are difficult to interpret, so doctors have leaned on other, more expensive options like MRI or CT scans to spot early signs of dementia and Alzheimer’s disease, researchers said.

However, AI can be taught to look for abnormal brain patterns in EEGs that are too subtle for humans to detect, a new study says.

AI-guided EEGs could one day help doctors distinguish between different cognitive diseases like Alzheimer’s or Lewy body dementia, researchers write in the journal Brain Communications.

"There's a lot of medical information in these brain waves about the health of the brain in the EEG," senior researcher Dr. David Jones, director of the Mayo Clinic Neurology AI Program, said in a news release. "It's well-known that you can see these waves slow down and look a bit different in people who have cognitive problems.”

For the study, researchers had AI analyze EEG data from more than 11,000 patients who received the scan at the Mayo Clinic over the course of a decade.

The AI was taught to simplify complex brain wave patterns and look for specific patterns characteristic of cognitive problems.

"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," lead researcher Dr. Wentao Li, a Mayo Clinic clinical behavioral neurology fellow, said in a news release.

This sort of computer-aided analysis could boost the efforts of doctors to interpret EEG readings, Jones said.

"Right now, one common way that we quantify patterns in medical data is by expert opinion. And how do we know that the patterns are present? Because that expert tells you they're present," Jones said. "But now with AI and machine learning, not only do we see things that the expert can't see, but the things they can see, we can put a precise number on."

EEGs wouldn’t necessarily replace other types of exams like MRIs, PET or CT scans, researchers said.

But EEGs are more widely available, less expensive and less invasive than the other tests. For example, they don’t require X-rays or magnetic fields to scan brain activity.

An EEG powered by AI could offer a more economical and accessible tool for early detection of brain problems in communities without easy access to specialty clinics and high-tech equipment, Jones said.

"It's really important to catch memory problems early, even before they're obvious," he said. "Having the right diagnosis early helps us give patients the right outlook and best treatment. The methods we're looking at could be a cheaper way to identify people with early memory loss or dementia compared to the current tests we have, like spinal fluid tests, brain glucose scans or memory tests."

It will take several years of additional research to fine-tune the AI and improve EEG analysis, Jones said.

More information

The Cleveland Clinic has more on EEG.

SOURCE: Mayo Clinic, news release, July 29, 2024