Scientists from the Universities of Edinburgh and Dundee are carrying out an ambitious project that could revolutionize the early detection of dementia. With access to over 1.6 million brain scans of patients in Scotland, researchers hope to use artificial intelligence (AI) to predict a person's risk of dementia. The project, called Scan-Dan, is part of a global neuroscience research collaboration known as NEURii.
The team, comprised of 20 researchers, has been given unprecedented permission to analyze a vast amount of anonymous scans collected over a decade between 2008 and 2018 during routine clinical care in Scotland. This is the first time scientists in the UK have had access to such a large amount of data, which could open up new avenues of research into neurodegenerative diseases.
Dementia, including Alzheimer's disease, is characterized by the accumulation of proteins in the brain that damage tissue and lead to cognitive decline. These molecular and cellular changes can begin many years before the onset of symptoms, emphasizing the importance of early detection. Artificial intelligence will play a crucial role in this research. It will enable scientists to analyze patterns and signals in brain scans that can be linked to the early onset of dementia.
Professor Emanuele Trucco, an expert in artificial intelligence and medical imaging at the College of Dundee, is leading the project alongside Professor Will Whiteley from the College of Edinburgh's Center for Clinical Brain Sciences. Trucco stresses that while the exact indicators of dementia are not yet fully known, the large amount of data will allow the identification of patterns associated with the disease. "Even if we're not entirely sure what we're seeing at first, I can still predict whether someone is at risk," explains Trucco.
Getting access to this kind of data has been challenging. NHS Scotland and its Public Benefit and Privacy Panel for Health and Social Care have closely monitored the process, ensuring that all images are fully anonymized and the privacy and public benefit implications are carefully considered. This panel ensures that any proposed research has a clear and valuable purpose for society and that patient confidentiality is a top priority.
One of the main aims of the Scan Dan project is to develop tools that can assist radiologists in the early detection of dementia. The ability to identify at-risk patients early could drastically change the treatment and management of this disease. "Currently, treatments for dementia are expensive, scarce, and of uncertain value," says Whiteley. "If we can collect data from a large group of people at high risk and get their consent to participate in trials, we can start developing more effective new treatments."
The potential importance of this project is already being recognized, especially by those who have experienced the disease first-hand. Willy Gilder, a 71-year-old former journalist who was diagnosed with Alzheimer's three years ago, is a strong advocate of early detection. "If you know you're at risk, you can make changes that will improve the health of your brain," Gilder said. Thanks to his early diagnosis, Gilder has adopted a lifestyle that includes a high level of mental activity, which could slow the progression of the disease. He also pointed to the importance of new treatments under development that could be more effective in the early stages of Alzheimer's disease.
Although the Scan-Dan project is still in its early stages, the researchers hope to better understand the technology's potential by next year and develop a practical product that can be used in clinical medicine within a few years. This type of research positions Scotland and the UK at the forefront of using clinical data to combat neurodegenerative diseases and could represent a significant step towards improving the quality of life of people at risk of dementia.