Scientists will analyze thousands of brain scans using AI to develop a tool that can predict a person’s risk of dementia

Scientists and researchers will study hundreds of thousands of brain scans to develop a software tool that they hope will allow them to predict the risk of dementia.

A group of 20 experts will use artificial intelligence (AI) to analyze data from CT and MRI scans in combination with information from medical records. In this way, they hope to find patterns that can indicate the likelihood of the condition developing.

The team aims to create a digital tool that radiologists can use when scanning patients to determine their risk of dementia and diagnose early stages of related diseases.

They believe that isolating a group of patients at high risk of dementia will enable the development of more precise treatments for different forms of the condition, including Alzheimer’s disease.

The team includes data scientists and clinical researchers from the Universities of Edinburgh and Dundee, working together on a global research collaboration called NEURii, which was launched a year ago.

A group of 20 experts will analyze data from CT and MRI scans using AI, along with information from medical records, to find patterns that could indicate the likelihood of the condition developing (archive photo)

Researchers want to create a digital tool that radiologists can use when scanning patients to determine their risk of dementia and diagnose early stages of related diseases (file photo)

They estimate they will analyse up to 1.6 million images during the project, which they will use with approval from the Public Benefit and Privacy Panel for Health and Social Care, part of NHS Scotland (file image)

They estimate that they will analyse around 1.6 million images during the project. They will use these images with the approval of the Public Benefit and Privacy Panel for Health and Social Care, part of NHS Scotland.

The data will be held securely in the Scottish National Safe Haven, which was commissioned by Public Health Scotland to provide a secure platform for the use of electronic NHS data for research.

Professor Will Whiteley, from the University of Edinburgh’s Centre for Clinical Brain Sciences, who is co-leading the project, 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, making it easier to develop new treatments.

‘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 agree to participate in trials, we can really start to develop new treatments.’

Alzheimer’s disease is the most common cause of dementia. The disease can cause anxiety, confusion and loss of short-term memory.

Professor Emanuele Trucco, an expert in AI and medical imaging at the University of Dundee, said: ‘This new dataset will be of great use to neurological researchers.

‘Should we deliver a successful proof of concept, we will have a suite of software tools that can be easily and unobtrusively integrated into routine radiology procedures. These tools support clinical decision-making and signal dementia risk as early as possible.’

Former journalist Willy Gilder, 71, from Edinburgh, was diagnosed with Alzheimer’s three years ago. Welcoming the project, 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 will improve your brain health. Because I was diagnosed early, I know that staying very mentally active, for example, is going to help me.

‘Potential new treatments in development for Alzheimer’s are likely to work in the early stages of the disease, which is why early diagnosis is important.

‘Given the long waiting lists for diagnosis and the relatively low funding for dementia research in general compared to cancer research, a project like this to predict a person’s risk is incredibly important.’