First-of-its-kind test can predict dementia nine years before diagnosis

Researchers at Queen Mary University of London have developed a new method for predicting dementia with over 80% accuracy and up to nine years before diagnosis. This new method provides a more accurate prediction of dementia than memory tests or brain shrinkage measurements, which are two commonly used methods for diagnosing dementia.

A team led by Professor Charles Marshall developed a predictive test by analysing 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.

The researchers used fMRI scans of more than 1,100 volunteers from the UK Biobank, a large biomedical database and research resource containing genetic and medical information from half a million participants in the UK, to assess the effective connectivity between the ten brain regions that make up the default mode network.

The researchers assigned each patient a dementia probability score based on the degree to which their effective connectivity pattern matched either the dementia-indicating pattern or the controlled pattern.

They compared these predictions with each patient’s medical data stored in the UK Biobank. The results showed that the model accurately predicted the onset of dementia up to nine years before official diagnosis with over 80% accuracy. In cases where the volunteers subsequently developed dementia, the model was also able to predict, to within two years, how long it would take to receive a diagnosis.

The researchers also examined whether changes in the DMN could be caused by known risk factors for dementia. Their 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. They also found that social isolation likely increases the risk of dementia through its effect on connectivity in the DMN.

Professor Charles Marshall, who led the research team at the Centre for Preventive Neuroscience, Wolfson Institute of Population Health, Queen Mary University, said: "Predicting who will suffer dementia in the future will be vital to developing treatments that can prevent the irreversible loss of brain cells that causes the symptoms of dementia. Although we are getting better at identifying proteins in the brain that can cause Alzheimer's, many people live for decades with these proteins in their brains without developing symptoms of dementia.

"We hope that the brain function measurement we have developed will allow us to be much more precise about whether and when someone will actually develop dementia, so we can determine whether they might benefit from future treatments."

Samuel Ereira, lead author and a postdoctoral fellow in the Wolfson Institute for Population Health's Center for Preventive Neuroscience, added: "By using these analysis methods with large data sets, we can identify those at high risk for dementia and also figure out what environmental factors pushed those people into high risk.

"There is huge potential to apply these methods to different neural networks and populations to better understand the relationship between environment, neurobiology and disease, both in dementia and potentially other neurodegenerative diseases. fMRI is a non-invasive medical imaging technique and takes about six minutes to collect the necessary data on an MRI scanner, so it can be integrated into existing diagnostic pathways, especially where MRI is already used."

Hojat Azadbakht, CEO of AINOSTICS (an AI company collaborating with leading research groups to develop brain imaging techniques for the early diagnosis of neurological disorders), commented: “The approach developed has the potential to fill a huge clinical gap by providing a non-invasive biomarker for dementia. In a study published by a team from Queen Mary University, they were able to identify people who later developed Alzheimer’s disease up to nine years before receiving a clinical diagnosis. It is at this pre-symptomatic stage that new disease-modifying techniques can bring the greatest benefit to patients.”