New test likely to predict dementia with 82% accuracy

Dementia is impaired ability to remember, think, make decisions affecting many people across globe

By  Web Desk   |  
June 11, 2024
A representational image for dementia. — Unsplash/File

Dementia can be predicted with 82% accuracy with the help of a new test, as per the researchers at Queen Mary University of London in the United Kingdom.

The researchers produced a model using machine learning after analysing 1,111 functional magnetic resonance imaging (fMRI) scans of people with and without dementia. They say it spots the telltale signs of dementia up to nine years before diagnosis, according to Medical News Today.


Changes in the brain’s default mode network (DMN) can be identified by the model. When a person is lying in an fMRI scanner, not doing anything, the DMN is active.

Among other activities, the DMN state is believed to play a role in daydreaming and introspection. When a person is at rest or engaged in self-referential thought, it is found to be more active.

From the UK Biobank, the researchers collected the fMRI scans used in the study. The participants consisted of 81 people who had not been diagnosed with dementia at the time their scans were taken, however, who developed the condition up to nine years afterward. For juxtaposition, 1,030 people served as matched controls for the study.

Dr Claire Sexton, DPhil, the Alzheimer’s Association’s US senior director of scientific programs and outreach, who was not involved in the study, said the DMN seems to be implicated in Alzheimer’s.

“A number of studies,” she said, “have found that Alzheimer’s is associated with decreased functional connectivity within the DMN.”