AI tool aims to predict a person's risk of dementia from brain scans
As part of the NEURii initiative, data scientists and clinical researchers will use brain scans from the entire Scottish population to build a software tool that they hope will be able to predict a person’s risk of dementia.
The project, called Scottish AI in Neuroimaging to predict Dementia and Neurodegenerative Disease (SCAN-DAN), is one of three ‘pathfinders’ from global research collaboration NEURii, which launched a year ago. Comprising global pharmaceutical company Eisai, Gates Ventures, the University of Edinburgh, Health Data Research UK and medical research charity LifeArc, NEURii aims to translate world-class data, neurology and digital sciences into projects that can enhance quality of life for people living with dementia.
Researchers at the Universities of Edinburgh and Dundee will use artificial intelligence and machine learning to analyse a large data set of 1.6 million CT and MRI brain scan images, alongside linked health records, from patients in Scotland from 2008 to 2018 to find patterns that could indicate a person’s risk of developing dementia representing 1.6 million images.
The aim is to build a digital healthcare tool that radiologists can use when scanning for other conditions to determine a person’s dementia risk, and to diagnose early stages of related diseases, such as Alzheimer’s.
Isolating a patient group with a high risk of dementia will enable the development of more precise treatments for various types of dementia, mostly Alzheimer’s and vascular dementia.
Co-lead of the SCAN-DAN project Professor Will Whiteley, Professor of Neurology and Epidemiology at the University of Edinburgh’s Centre for Clinical Brain Sciences and an Associate Director at the British Heart Foundation (BHF) Data Science Centre, said:
“Better use of simple brain scans to predict dementia will lead to better understanding of dementia and potentially earlier diagnosis of its causes, which in turn will make development of new treatments easier.
“Currently 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.
“Working with NEURii really gives us the potential for patient impact – to build something that actually makes it into practice. Often modelling doesn’t go anywhere, but motivation from the NEURii team to develop a useful product really concentrates the mind!”
Former journalist Willy Gilder, 71, from Edinburgh, was diagnosed with Alzheimer’s three years ago. He said:
“We know that 45 per cent of dementia cases are preventable, and The Lancet has published a list of risk factors including smoking, obesity and air pollution.
“If you know you’re at risk, you can make changes that are going to improve your brain health. Because I was diagnosed early, I know that keeping very mentally active, for example, is going to help me.
“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.”
The NEURii collaboration provides funding and expertise to the pathfinder projects to remove barriers to getting digital health tools to market. The research teams are also supported by Edinburgh Innovations, the University of Edinburgh’s commercialisation service.
Professor Emanuele Trucco, an expert in AI and medical imaging at the University of Dundee and SCAN-DAN co-lead, said:
“Scotland and the UK are at the forefront of clinical data research, building on the unique National Health Service patient number – called the CHI number in Scotland, as well as the structure, security and good governance of the Scottish National Safe Haven, amongst other data organisations such as the UK Biobank.
“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.”
The project is backed by the NEURii partner organisations. Dr Ricardo Sáinz Fuertes, Global Director of Digital Health Solutions at Eisai and Programme Director for NEURii, said:
“The spirit of NEURii is to fulfil the promise of data science for healthcare. Within a year, we plan to support SCAN-DAN through to proof of concept by removing obstacles to commercialisation and providing whatever’s needed, be it funding, collaborations or legal or regulatory input.
“We are joining forces globally, in a way that hasn’t been done before, to provide innovative digital projects with the chance of becoming solutions to complex neurodegenerative disorders like dementia.”
The data being analysed in the study will be held safely in the Scottish National Safe Haven, commissioned by Public Health Scotland, which provides a secure platform for the research use of NHS electronic data. Approval comes from the Public Benefit and Privacy Panel for Health and Social Care, a part of NHS Scotland.
