June 22, 2022 – A single brain scan may someday offer an early diagnosis of Alzheimer’s disease.

Using artificial intelligence to look at structures in the brain, researchers in the United Kingdom developed an algorithm that can determine – with 98% accuracy – whether someone has the disease from a single MRI scan.

The tool could also tell the difference between early and late-stage dementia in 79% of cases.

“Currently, no other simple and widely available methods can predict Alzheimer’s disease with this level of accuracy, so our research is an important step forward,” Eric Aboagye, PhD, a professor with Imperial College London, who led the research, said in a news release.

“Most people will go through quite a raft of tests to get to a diagnosis of Alzheimer’s, and this tool may lead to a quicker diagnosis and reduce anxiety for patients,” he said.

Doctors may be able to use this information to refine and modify the diagnosis, he said.

To develop their method, researchers divided the brain into 115 regions and assessed each region for key features such as size, shape, and texture. Using machine learning, they trained an algorithm to identify where changes to these features could accurately predict the presence of Alzheimer’s disease.

This research addresses the “important” issue of early detection of Alzheimer’s disease, says Rebecca Edelmayer, PhD, senior director of scientific engagement for the Alzheimer’s Association.

“It is vital that individuals with Alzheimer’s be diagnosed early in the disease process when treatment may be most beneficial,” she says.

Early detection also allows people and their families more time to plan for the future, take part in clinical trials, and seek community resources, Edelmayer says.

But she cautions that this research is in its early days, and this tool is not ready to be used as a “standalone” test for Alzheimer’s but will need more testing in a more diverse group of people.

According to the Alzheimer’s Association, more than 6 million Americans have the disease. By 2050, this number is projected to rise to nearly 13 million.