London, England – Researchers at Queen Mary University have developed a groundbreaking method for predicting dementia with over 80% accuracy up to nine years before diagnosis. This innovative approach utilizes functional MRI scans to analyze the brain’s default mode network, allowing for early detection of signs of dementia by comparing brain connectivity patterns with genetic and health data from UK Biobank volunteers.
The team, led by Professor Charles Marshall, focused on detecting changes in the brain’s default mode network, which is the first neural network affected by Alzheimer’s disease. By analyzing functional MRI scans from over 1,100 volunteers in the UK Biobank database, the researchers were able to estimate the effective connectivity between different regions of the brain that make up the default mode network.
The researchers created a predictive test that assigns each patient a probability of dementia value based on their brain’s connectivity patterns, compared to patterns indicative of dementia or a healthy brain. This model accurately predicted the onset of dementia up to nine years before an official diagnosis, with an accuracy rate of over 80%. Additionally, the model was able to predict within a two-year margin of error how long it would take for a diagnosis to be made after volunteers developed dementia.
Furthermore, the team investigated whether changes in the default mode network were associated with known risk factors for dementia. Their analysis revealed a strong correlation between genetic risk for Alzheimer’s disease and connectivity changes in the default mode network. Additionally, social isolation was found to potentially increase the risk of dementia through its impact on connectivity in the brain.
The impact of this research could be significant in the development of treatments to prevent the irreversible loss of brain cells that leads to dementia symptoms. By identifying individuals at high risk of dementia years before diagnosis, researchers hope to improve the accuracy of predicting dementia and the timing of future treatments.
Lead author Samuel Ereira emphasized the potential of using these analysis techniques with large datasets to identify individuals at high risk of dementia and understand the environmental factors contributing to this risk. This non-invasive approach could help healthcare professionals better understand the interplay between environment, neurobiology, and disease, not only in dementia but possibly in other neurodegenerative disorders as well.
Hojjat Azadbakht, CEO of AINOSTICS, an AI company collaborating with research teams on brain imaging approaches for early diagnosis of neurological disorders, highlighted the importance of the non-invasive biomarker for dementia developed in this study. The ability to identify individuals who may develop Alzheimer’s disease up to nine years before clinical diagnosis provides a valuable opportunity for early intervention with potential disease-modifying treatments.