New AI-Driven Dementia Test Detects Disease 9 Years Before Symptoms

The new fMRI-based test developed at QMUL detects alterations in the brain's default mode network with over 80% accuracy, up to nine years before diagnosis.

Highlights:

The new method predicts dementia with over 80% accuracy, up to nine years before clinical diagnosis
It uses fMRI scans to analyze changes in the brain's default mode network, the first area affected by Alzheimer's disease
The test's accuracy is significantly better than current methods, such as memory tests and brain shrinkage measurements

Researchers at Queen Mary University of London have created a new method for detecting dementia with more than 80% accuracy and up to nine years before a diagnosis (). The new method predicts dementia more accurately than memory tests or brain shrinkage measurements, which are two of the most regularly used procedures for diagnosis of dementia.

Dementia
Dementia has become a very big concern as we have an aging population across the world. Dementia is also terrifying to us because of its disturbing symptoms and limited treatment options.

‘Did You Know?
The default mode network (DMN), the first brain area affected by Alzheimer's, is also the region that lights up when you're daydreaming or thinking about yourself! #dementiaresearch #alzheimers #brainhealth #medindia’

First Brain Region That Gets Affected by Dementia

The researchers, led by Professor Charles Marshall, created the predictive test by analyzing functional MRI (fMRI) scans to detect alterations in the brain's 'default mode network' (DMN). The DMN, which connects brain regions to accomplish specialized cognitive activities, was the first neural network impacted by Alzheimers disease.

The researchers used fMRI scans from over 1,100 volunteers from 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 make up the default mode network.

The researchers gave a probability of dementia value to each patient depending on how much of their effective connectivity pattern resembled a dementia or control-like pattern.

They matched these predictions to each patient's medical data stored at the UK Biobank. The findings revealed that the model correctly predicted the development of dementia up to nine years before an official diagnosis was made, with an accuracy of more than 80%. In cases where the volunteers went on to develop dementia, it was discovered that the model could accurately estimate how long it would take to make that diagnosis with a two-year margin of error.

Vascular Dementia
Vascular dementia is the second most common form of dementia. Though it has no cure, you can still learn to manage its symptoms and lead a joyful life.

What Increases the Risk of Alzheimer's Disease?

The researchers also investigated whether DMN changes might be attributed to established dementia risk factors. Their findings indicated that hereditary risk for Alzheimer's disease was highly related with connectivity abnormalities in the DMN, confirming the notion that these changes are unique to Alzheimer's disease. They also discovered that social isolation increased the risk of dementia via reducing connection in the DMN.

Alzheimers Disease
Alzheimer''s disease is a progressive neurodegenerative disease affecting memory and thinking and making the person increasingly dependent on others.

Is it Possible to Predict the Risk of Dementia?

The research team was led by Charles Marshall, Professor and Honorary Consultant Neurologist at Queen Mary's Wolfson Institute of Population Health. He stated: "Predicting who will develop dementia in the future will be critical for developing treatments that can prevent the irreversible loss of brain cells that causes dementia symptoms." Although we are improving our ability to detect the proteins in the brain that can cause Alzheimer's disease, many people can have these proteins in their brains for decades without experiencing dementia symptoms. We think that the measure of brain function that we have developed will allow us to be considerably more accurate about whether or not someone is likely to acquire dementia, and how soon.

Samuel Ereira, lead author and Academic Foundation Programme Doctor at the Centre for Preventive Neurology, Wolfson Institute of Population Health, stated, "Using these analysis techniques with large datasets, we can identify those at high dementia risk, as well as learn which environmental risk factors pushed these people into a high-risk zone." These tools have enormous potential for application to many brain networks and populations, allowing us to better understand the interactions between environment, neurobiology, and sickness, both in dementia and possibly other neurodegenerative diseases. fMRI is a non-invasive medical imaging method that takes around 6 minutes to collect data on an MRI scanner, allowing it to be integrated into established diagnostic pathways, particularly where MRI is already utilized."

Hojjat Azadbakht, CEO of AINOSTICS (an AI company that collaborates with world-class research teams to develop brain imaging approaches for the early diagnosis of neurological disorders), stated, "The approach developed has the potential to fill an enormous clinical gap by providing a non-invasive biomarker for dementia. In a study published by the QMUL team, they were able to identify people who would later develop Alzheimer's disease up to 9 years before receiving a clinical diagnosis. Emerging disease-modifying medicines are most likely to benefit patients at the pre-symptomatic period."

Reference:

Early detection of dementia with default-mode network effective connectivity - (https://www.nature.com/articles/s44220-024-00259-5)

Source-Medindia

Diseases Related to Old Age
Ageing is referred to the accumulation of changes that brings a person closer to death.