Researchers at Queen Mary University of London have developed a new method for predicting dementia with an accuracy of over 80% and up to nine years before diagnosis. The new method provides a more accurate prediction of dementia than memory tests or measures of brain shrinkage, two commonly used methods for diagnosing dementia. The team, led by Professor Charles Marshall, developed the predictive test by analyzing functional MRI (fMRI) scans to detect changes in the brain’s “default mode network” (DMN). The DMN connects regions of the brain to perform certain cognitive functions and is the first neural network to be affected by Alzheimer’s disease.
Model Can Predict the Onset of Dementia Up to Nine Years Before Official Diagnosis
The researchers used fMRI scans of over 1,100 volunteers from the UK Biobank, a large-scale biomedical database and research resource containing genetic and health information from half a million UK participants, to estimate the effective connectivity between ten brain regions that form the default mode network. The researchers assigned each patient a value for the likelihood of dementia according to the extent to which the pattern of effective connectivity matched a pattern indicative of dementia or a control-like pattern. They compared these predictions with the medical data of individual patients stored in the UK Biobank. The results showed that the model predicted the onset of dementia up to nine years before official diagnosis with an accuracy of over 80%. In cases where the subjects later developed dementia, the model was able to accurately predict within an error margin of two years how long it would take for the diagnosis to be made.
The researchers also investigated whether changes in the DMN could be caused by known risk factors for dementia. The analysis showed that genetic risk for Alzheimer’s disease was strongly associated with changes in connectivity in the DMN, supporting the idea that these changes are specific to Alzheimer’s disease.
The researchers also found that social isolation is likely to increase the risk of dementia through its effects on connectivity in the DMN.
Chales Marshall, professor and honorary doctor of neurology, led the research team within the Center for Preventive Neurology at Queen Mary’s Wolfson Institute of Population Identifying who will develop dementia in the future is crucial to developing treatments that can prevent the irreversible loss of brain cells that causes the symptoms of dementia, according to Marshall. Although scientists are getting better at detecting the proteins in the brain that can trigger Alzheimer’s disease, many people live with these proteins in their brains for decades without developing symptoms of dementia. The researchers hope that the measurement of brain function they have developed will allow them to determine much more accurately whether someone will actually develop dementia and how soon, so that it can be determined whether they might benefit from future treatments. With these analysis techniques and large data sets, they can identify those who are at high risk of dementia and also learn what environmental risk factors have put these people in a high-risk zone. There is huge potential to apply these methods to different brain networks and populations to better understand the interactions between environment, neurobiology and disease in both dementia and potentially other neurodegenerative diseases.
AI Tool for Diagnosing Different Forms of Dementia
10 million new cases of dementia are diagnosed each year, but the presence of different forms of dementia and overlapping symptoms can complicate diagnosis and the delivery of effective treatments. Researchers at Boston University have developed an AI tool that can diagnose ten different forms of dementia, such as vascular dementia, Lewy body dementia and frontotemporal dementia, even when they occur simultaneously. The researchers have developed a multimodal machine learning (ML) method that uses commonly collected clinical data such as demographic information, patient and family medical history, medication use, neurological and neuropsychological examination results and imaging techniques such as MRI scans to accurately identify specific dementias. The results were published in Nature Medicine. This generative AI tool enables a differentiated dementia diagnosis using routinely collected clinical data and shows its potential as a scalable diagnostic tool for Alzheimer’s disease and related dementias
There are not enough neurology experts in the world, and the number of patients who need their help is growing rapidly. This discrepancy places a huge burden on the healthcare system. Researchers believe that AI can help by detecting these disorders early and assisting doctors in treating their patients to prevent the diseases from worsening. With the number of dementia cases expected to double in the next 20 years, the researchers hope that this AI tool can provide accurate differential diagnosis and support the increasing demand for targeted therapeutic interventions for dementia.