First-of-its-kind test uses machine learning to predict dementia up to 9 years in advance

In a groundbreaking study published in Nature Mental Health, researchers from Queen Mary University of London have developed a new method for predicting dementia with over 80% accuracy up to nine years before a clinical diagnosis. This method, which outperforms traditional memory tests and measurements of brain shrinkage, relies on detecting changes in the brain’s default mode network (DMN) using functional magnetic resonance imaging (fMRI).

Dementia is a collective term used to describe a variety of conditions characterized by the gradual decline in cognitive function severe enough to interfere with daily life and independent functioning. It affects memory, thinking, orientation, comprehension, calculation, learning capacity, language, and judgment.

Alzheimer’s disease is the most common cause of dementia, accounting for 60-70% of cases. Other types include vascular dementia, dementia with Lewy bodies, and frontotemporal dementia.

Dementia is a progressive condition, meaning symptoms worsen over time, often leading to significant impairments in daily activities and quality of life. Currently, there is no cure for dementia, and treatments primarily focus on managing symptoms and supporting patients and their caregivers.

Early diagnosis is important because it opens the door to interventions that might slow the progression of the disease, improve quality of life, and provide individuals and their families more time to plan for the future. Traditional diagnostic methods, such as memory tests and brain scans to detect atrophy, often catch the disease only after significant neural damage has occurred. These methods are not sensitive enough to detect the very early changes in brain function that precede clinical symptoms.

“Predicting who is going to get dementia in the future will be vital for developing treatments that can prevent the irreversible loss of brain cells that causes the symptoms of dementia,” said Charles Marshall, who led the research team within the Centre for Preventive Neurology at Queen Mary’s Wolfson Institute of Population Health. “Although we are getting better at detecting the proteins in the brain that can cause Alzheimer’s disease, many people live for decades with these proteins in their brain without developing symptoms of dementia.”

“We hope that the measure of brain function that we have developed will allow us to be much more precise about whether someone is actually going to develop dementia, and how soon, so that we can identify whether they might benefit from future treatments.”

The study involved a nested case-control design using data from the UK Biobank, a large-scale biomedical database. The researchers focused on a subset of participants who had undergone functional magnetic resonance imaging (fMRI) scans and either had a diagnosis of dementia or developed it later. The sample consisted of 148 dementia cases and 1,030 matched controls, ensuring a robust comparison group by matching on age, sex, ethnicity, handedness, and the geographical location of the MRI scanning center.

Participants underwent resting-state fMRI (rs-fMRI) scans, which measure brain activity by detecting changes in blood flow. The researchers specifically targeted the default mode network (DMN), a network of brain regions active during rest and involved in high-level cognitive functions such as social cognition and self-referential thought.

Using a technique called dynamic causal modeling (DCM), they analyzed the rs-fMRI data to estimate the effective connectivity between different regions within the DMN. This method goes beyond simple correlations to model the causal influence one brain region has over another, providing a detailed picture of neural connectivity.

The researchers then used these connectivity estimates to train a machine learning model. This model aimed to distinguish between individuals who would go on to develop dementia and those who would not. The training process involved a rigorous cross-validation technique to ensure the model’s reliability and to prevent overfitting. Additionally, a prognostic model was developed to predict the time until dementia diagnosis, using similar data and validation techniques.

The predictive model achieved an area under the curve (AUC) of 0.824, indicating excellent performance in distinguishing between future dementia cases and controls. This level of accuracy is significantly higher than traditional diagnostic methods, which often struggle to detect early-stage dementia.

The model identified 15 key connectivity parameters within the DMN that differed significantly between future dementia cases and controls. Among these, the most notable changes included increased inhibition from the ventromedial prefrontal cortex (vmPFC) to the left parahippocampal formation (lPHF) and from the left intraparietal cortex (lIPC) to the lPHF, as well as attenuated inhibition from the right parahippocampal formation (rPHF) to the dorsomedial prefrontal cortex (dmPFC).

In addition to its diagnostic capabilities, the study also developed a prognostic model to predict the time until dementia diagnosis. This model showed a strong correlation (Spearman’s ρ = 0.53) between predicted and actual times until diagnosis, indicating its potential to provide valuable timelines for disease progression. The predictive power of these connectivity patterns suggests that changes in the DMN can serve as early biomarkers for dementia, offering a window into the disease process years before clinical symptoms appear.

Furthermore, the study explored the relationship between DMN connectivity changes and various risk factors for dementia. They found a significant association between social isolation and DMN dysconnectivity, suggesting that social isolation might exacerbate the neural changes associated with dementia. This finding highlights the importance of considering environmental and lifestyle factors in dementia risk and opens up potential avenues for intervention.

“Using these analysis techniques with large datasets we can identify those at high dementia risk, and also learn which environmental risk factors pushed these people into a high-risk zone,” said co-author Samuel Ereira. “Enormous potential exists to apply these methods to different brain networks and populations, to help us better understand the interplays between environment, neurobiology and illness, both in dementia and possibly other neurodegenerative diseases. fMRI is a non-invasive medical imaging tool, and it takes about 6 minutes to collect the necessary data on an MRI scanner, so it could be integrated into existing diagnostic pathways, particularly where MRI is already used.”

Despite the promising results, there are some caveats to consider. One limitation of the study is the use of data from the UK Biobank, which may not be fully representative of the general population. Participants in this cohort tend to be healthier and less socio-economically deprived. Future research should validate these findings in more diverse and representative samples.

“One in three people with dementia never receive a formal diagnosis, so there’s an urgent need to improve the way people with the condition are diagnosed. This will be even more important as dementia becomes a treatable condition,” Julia Dudley, the head of Strategic Research Programmes at Alzheimer’s Research UK, told the Science Media Centre.

“This study provides intriguing insights into early signs that someone might be at greater risk of developing dementia. While this technique will need to be validated in further studies, if it is, it could be a promising addition to the toolkit of methods to detect the diseases that cause dementia as early as possible. An earlier and accurate diagnosis is key to unlocking personalised care and support, and, soon, to accessing first-of-a-kind treatments that are on the horizon.”

Eugene Duff, an advanced research fellow at the UK Dementia Research Institute at Imperial College London, added: “This work shows how advanced analysis of brain activity measured using MRI can predict future dementia diagnosis. Early diagnosis of dementia is valuable for many reasons, particularly as improved pharmaceutical treatments become available.”

“Brain activity measures may be complementary to cognitive, blood and other markers for identifying those at risk for dementia. The brain modelling approach they use has the benefit of potentially clarifying the brain processes affected in the early stages of disease. However, the study cohort of diagnosed patients was relatively small (103 cases). Further validation and head-to-head comparisons of predictive markers is needed.”

The study, “Early detection of dementia with default-mode network effective connectivity,” was authored by Sam Ereira, Sheena Waters, Adeel Razi, and Charles R. Marshall.


Denial of responsibility! Web Today 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