In a novel approach, researchers and scientists will use artificial intelligence to examine 1.6 million brain scans and ultimately develop a tool that can predict a person’s risk of dementia.
The data from CT and MRI scans are analyzed by 20 experts using artificial intelligence to identify patterns that can predict a person’s likelihood of developing such diseases.
The researchers’ goal is to develop a digital tool that will help radiologists examine patients and determine their risk of dementia so that a diagnosis can be made early.
By isolating a group of patients at high risk of dementia, experts say it will be possible to develop more precise treatment methods for different types of the disease, including Alzheimer’s.
How will scientists use AI to determine Alzheimer’s risk?
The team consists of data scientists and clinical researchers from the Universities of Edinburgh and Dundee. They work in a global research collaboration called NEURii, which was founded a year ago.
The scientists have decided to analyse up to 1.6 million images as part of the project. These images have been approved by the Public Benefit and Privacy Panel for Health and Social Care, part of the Scottish National Health Service (NHS).
The data is stored securely in the Scottish National Safe Haven, which Public Health Scotland has commissioned to provide a secure platform for the use of electronic NHS data.
Project co-leader Professor Will Whiteley of the University of Edinburgh’s Centre for Clinical Brain Sciences said: “Better use of simple brain scans to predict dementia will lead to a better understanding of dementia and potentially earlier diagnosis of its causes, which in turn will facilitate the development of new treatments.”
Watch: Gravitas | Digital Dementia: Are you showing the symptoms?
“Currently, treatments for dementia are expensive, rare and their benefits are uncertain. If we can collect data from a large group of people at high risk who then consent to participate in trials, we can really start developing new treatments,” he added.
Professor Emanuele Trucco, an expert in AI and medical imaging at the University of Dundee, said: “This new dataset will be of great benefit to neurological researchers. If we can achieve a successful proof of concept, we will have a suite of software tools that can be seamlessly and unobtrusively integrated into routine radiology workflows, supporting clinical decision-making and flagging dementia risk as early as possible.”
(With contributions from agencies)
)
