A team of 20 researchers from the Universities of Edinburgh and Dundee in the UK are developing an AI software tool that aims to identify early signs of dementia from brain scans during routine medical appointments.

The project is known as Scottish AI in Neuroimaging to predict Dementia and Neurodegenerative Disease (SCAN-DAN).

The team has received approval to use a significant data set of 1.6 million CT and MRI brain scans from Scottish patients, spanning a decade from 2008 to 2018.

The Public Benefit and Privacy Panel for Health and Social Care, part of NHS Scotland, granted this approval.

The researchers will employ AI and machine learning to analyse the brain scans in conjunction with linked health records such as demographics and treatment history.

The analysis will be conducted in a way that preserves patient anonymity, searching for patterns that could indicate an increased risk of developing dementia.

This project aims to create a digital healthcare tool that can be used by radiologists to assess dementia risk while conducting scans for other conditions.

Early diagnosis of diseases such as Alzheimer's could be significantly improved with this tool.

The data will be securely stored in the Scottish National Safe Haven, managed by Public Health Scotland.

The SCAN-DAN project is one of three 'pathfinders' from NEURii, a global research collaboration that comprises Gates Ventures, Eisai, the University of Edinburgh, Health Data Research UK, and LifeArc.

University of Edinburgh Centre for Clinical Brain Sciences professor Will Whiteley is co-leading the SCAN-DAN project.

Whiteley 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 make the development of new treatments easier.

“Working with NEURii really gives us the potential for patient impact – to build something that actually makes it into practice.”