Scottish project leverages AI and real-world data to enhance early dementia diagnosis
The AI initiative utilizes real-world data (RWD) from brain scans to predict dementia risk, aiming to enhance early diagnosis and treatment through the NEURii global research collaboration.
A pioneering project in Scotland is leveraging AI to predict an individual's risk of developing dementia through the analysis of brain scans. This initiative, known as the Scottish AI in Neuroimaging to predict Dementia and Neurodegenerative Disease (SCAN-DAN), is part of the broader NEURii collaboration, which seeks to transform neurology and digital sciences into practical healthcare solutions.
Researchers from the Universities of Edinburgh and Dundee will utilize AI and machine learning to analyze an extensive dataset of 1.6 million anonymized CT and MRI brain scans, collected from the Scottish population between 2008 and 2018. By integrating these scans with linked health records, the project aims to identify patterns that may indicate an individual’s risk of developing dementia, particularly Alzheimer's and vascular dementia.
This initiative is part of NEURii, a global research collaboration that includes organizations such as Eisai, Gates Ventures, the University of Edinburgh, Health Data Research UK, and LifeArc. SCAN-DAN, one of three 'pathfinder' projects under NEURii, seeks to develop a digital healthcare tool that radiologists can use to assess dementia risk during routine scans for other conditions.
Professor Will Whiteley, Professor of Neurology and Epidemiology at the University of Edinburgh and co-lead of the SCAN-DAN project, emphasized the project's potential impact:
"Better use of simple brain scans to predict dementia will lead to better understanding and potentially earlier diagnosis, making the development of new treatments easier. Current treatments for dementia are expensive, scarce, and of uncertain value. If we can collect data from a large group of people at high risk, who then give their consent to take part in trials, we can really start to develop new treatments."
The data will be securely stored in the Scottish National Safe Haven, ensuring compliance with privacy and ethical standards. The project has received approval from NHS Scotland's Public Benefit and Privacy Panel for Health and Social Care.
Professor Emanuele Trucco, an expert in AI and medical imaging at the University of Dundee and SCAN-DAN co-lead, highlighted the importance of this initiative:
"Scotland and the UK are at the forefront of clinical data research… This new data set will be of great use to neurological researchers. And, should we establish a successful proof of concept, we will have a suite of software tools that are smoothly and unobtrusively integrated with routine radiology operations, that assist clinical decision-making and flag the risk of dementia as early as possible."
This project aligns with the growing trend of utilizing RWD and real-world evidence (RWE) in healthcare, as discussed in a recent interview with Ross Cantor, Senior Vice President of Life Sciences at Proscia. Cantor emphasized the importance of digital pathology and AI in generating actionable insights from vast datasets, underscoring the relevance of SCAN-DAN's approach.
Willy Gilder, a 71-year-old former journalist diagnosed with Alzheimer’s three years ago, expressed hope for the project's impact.
“If you know you’re at risk, you can make changes that are going to improve your brain health… There are also treatments coming down the line for Alzheimer’s that are exciting, but they work in the early stages of the disease, which is why early diagnosis is so important. With long waiting lists for diagnosis, as well as relatively low funding for dementia research in general compared to cancer, a project like this to predict a person’s risk is extremely important.”
You may also be interested in:
Generating real-world evidence from digital pathology data: an interview with Ross Cantor, Proscia
