AI News Monitor

The new tool can analyze brain wave patterns to discover early signs of cognitive illnesses like dementia.

Researchers at Mass General Bingham have developed an AI tool that can predict cognitive decline. The tool works by measuring brain wave patterns during sleep and predicting the likelihood of impairment within five years.

A study conducted by the researchers showed that among older people who develop cognitive impairments, there are usually subtle early changes in brain wave features. These changes are evident up to five years before symptoms are displayed. In a test, the AI tool they developed successfully predicted dementia using data collected from adults aged 65 and older. It had an accuracy of 77 percent.

The individual being examined has sensors placed on their scalp to record brain waves during sleep, a method known as electroencephalography (EEG). The AI tool then uses the data to analyze electrical activity in the brain.

Shahab Haghayegh, PhD, lead researcher of the team, believes that the tool can make a significant impact as medical professionals seek to address cognitive impairment in seniors. Using the tool, medical professionals can “detect subtle changes in brain wave patterns during sleep that signal future cognitive impairment, offering a window of opportunity for intervention years before symptoms appear,” says Haghayegh.

If cognitive decline can be predicted years before its onset, individuals could have ample time to plan for treatment and make necessary adjustments to their lifestyle. This could help them maintain much better cognitive health.

According to Kung Hu, physiologist at Brigham and Women’s Hospital and Harvard Medical School, the AI tool can also help get the best out of already existing treatments for cognitive illnesses.

“The new, FDA-approved treatments for Alzheimer’s disease are effective at the earlier stages of dementia, but not the more advanced stages,” said Hu. Therefore, she believes that if cognitive decline can be spotted much earlier, before the individual begins to show symptoms, then interventions can be applied sooner. Interventions performed at this early stage are likely to be “even more effective.”

As of 2022, up to four percent of adults in the US aged 65 and older had been diagnosed with dementia. The most common and recognized type of dementia is Alzheimer’s disease, which accounts for 60 to 80 percent of all dementia cases. It is also the sixth leading cause of death for US adults aged 60 and older. The new AI tool can help improve outcomes for individuals who develop cognitive decline. However, more research involving large populations is still needed before the tool can be rolled out.