Early dementia signs and symptoms that can be spotted in daydreams by breakthrough test

The field of dementia diagnosis has gone through a revolution in the past few years, as breakthroughs in medical science and emerging technologies like machine learning and artificial intelligence promise huge leaps forward in some of our most crippling and debilitating diseases.

This week, a combination of machine learning and the decade-long Biobank project examining the health of thousands of Brits made a fresh breakthrough in dementia diagnosis, that promises to be able to spot common dementia signs up to nine years before people are typically diagnosed. After reviewing over 1000 MRI scans, researchers say their test is more than 80 per cent accurate, in preliminary testing.




What is entirely new about this test is that it measures signs in your brain while it is daydreaming. But, in a world with regular breakthroughs in medical technology and an ever-higher prevalence of neurodegenerative disorders like dementia, experts at Medical News Today spoke to expert neurologists and researchers to find out just how useful this new test could be, and found one major problem.

READ MORE: ‘Disaster’ as £102k stained glass window at Gloucester bus station ‘welcomes’ visitors as they depart

Researchers at Queen Mary University of London analysed 1,111 functional MRIs (fMRIs) of people without dementia and ran it through a machine learning algorithm, before cross-referencing this model with those who went on to later develop a neurodegenerative disease. What is new about this analysis is that it focuses on when your brain is in “default mode.”

The new tool could spot dementia with a scan of your brain(Image: Getty)

This is the abstract mode of free-thinking often present in daydreaming and relaxed mental states, which the scientists say can present “early signs” that you will develop dementia. While in “default mode”, those in the study that went on to develop dementia had “disconnects” between 10 key regions in their brain while in this relaxed state.

This data model is how the researchers develop an AI tool that can analyse fMRI scans and spot, with an 80 per cent certainty, if someone is likely to develop dementia. However, it also worked as a short-term diagnostic tool, predicting with accuracy those who would develop dementia within a two-year window.

Professor Charles Marshall, clinical senior lecturer in dementia in the Preventive Neurology Unit at Queen Mary, described his study: “Some brain areas show reduced activity, but others show increased activity, probably as a compensatory response. We trained a machine learning tool to recognize patterns that were ‘dementia-like.’”

Reference

Denial of responsibility! Elite News is an automatic aggregator of Global media. In each content, the hyperlink to the primary source is specified. All trademarks belong to their rightful owners, and all materials to their authors. For any complaint, please reach us at – [email protected]. We will take necessary action within 24 hours.
DMCA compliant image

Leave a comment