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.
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.”
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, reports GloucestershireLive.
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.'”
While the study focused on the most common forms of dementia, others in the field have reacted with interest to how it could apply to other similar diseases. Dr Claire Sexton told Medical News Today that: “A number of studies have found that Alzheimer’s is associated with decreased functional connectivity within the DMN.”
However, there is one major issue with the new tool. While the test is a good sign for the future of medical diagnosis, if someone was diagnosed with a common form of dementia nine years before they would typically be diagnosed, there would be very little a doctor could do to prevent that dementia from occurring.
Neurologist Clifford Segil said: “If these tests pan out to have some clinical utility in the future, these patients would be followed by more frequent 3T structural MRI scans to determine if there were anatomical changes that would correlate with their memory loss.”
“Unfortunately, in the year 2024, even if we could target patients with early onset dementia, we do not have any neuroprotective medications to be used at this time.”
However, in a hopeful note, he added that this diagnostic test could help researchers identify people that could assist in preventative medical trials for future dementia medications.
Early symptoms of dementia
The study also found that social isolation, as well as these patterns that could be spotted in people while they were daydreaming, had a strong correlation with the onset of dementia-related illnesses, reinforcing a growing body of evidence. Other signs that can indicate dementia include:
- Depression
- Memory loss that affects day-to-day abilities
- Difficulty performing familiar tasks
- Problems with language
- Disorientation to time and place
- Impaired judgement
- Problems with abstract thinking
- Misplacing things
- Changes in mood and behaviour
- Changes of personality
- Loss of initiative