AI detects Alzheimer’s with 93% accuracy, researchers say

Do you know if you have Alzheimer's disease? According to researchers at Worcester Polytechnic Institute in Massachusetts, this may now be possible thanks to artificial intelligence, writes il messaggero.it.

Scientists claim they are able to predict the disease with nearly 93% accuracy, CE Report quotes ATA.

According to a report published in early March, more than 800 brain scans helped artificial intelligence identify anatomical changes in the brain that signal the onset of the most common form of dementia.

The goal is to detect changes that are still subtle but already clinically significant.

“Early diagnosis of Alzheimer’s disease can be challenging because symptoms may be confused with the normal aging process,” explained Benjamin Nephew, associate research professor at the institute.

“We have found that machine learning technologies can analyze large amounts of scan data to identify subtle changes and accurately predict Alzheimer’s disease and related cognitive conditions,” he emphasized.

The analyzed MRI scans belonged to 344 individuals aged between 69 and 84: 281 with normal cognitive function, 332 with mild cognitive impairment, and 202 with existing Alzheimer’s disease.

Researchers examined 95 out of nearly 200 distinct brain regions, then tasked the algorithm with assessing patients’ health conditions.

Among the most important indicators was a reduction in brain volume, a phenomenon that particularly affects the hippocampus, which is linked to memory; the amygdala, involved in processing fear; and the entorhinal cortex, important for time perception.

This finding emerged regardless of age and gender: men and women between 69 and 76 showed volume loss in the right hippocampus, a discovery that could be crucial for earlier diagnosis.

The study also highlighted gender differences.

In women, brain volume reduction was more pronounced in the left middle temporal cortex, an area associated with language and visual perception.

In men, however, the decline was mainly observed in the right entorhinal cortex. According to researchers, this discrepancy may be linked to differences in sex hormones, such as the decline of estrogen in women and testosterone in men.