June 22, 2022 – A single brain scan may provide an early diagnosis of Alzheimer’s disease.
Using artificial intelligence to look at structures in the brain, researchers in the UK have 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.
“At present, no other simple and widely available method can predict Alzheimer’s disease with this level of accuracy, so our research is an important step forward,” said Eric Aboagye, PhD, a professor at Imperial College London, who lead the investigation, in a news report.
“Most people will go through a lot of tests to get a diagnosis of Alzheimer’s, and this tool can lead to a faster diagnosis and reduce fear for patients,” he said.
Doctors may be able to use this information to refine and change the diagnosis, he said.
To develop their method, researchers divided the brain into 115 regions and assessed each region for important 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 involvement for the Alzheimer’s Association.
“It is essential that individuals with Alzheimer’s be diagnosed early in the disease process as treatment may be most beneficial,” she says.
Early detection also gives people and their families more time to plan for the future, participate in clinical trials, and seek community resources, Edelmayer says.
But she warns 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 require 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 expected to increase to nearly 13 million.