Scientists trial AI-system which could diagnose dementia in one scan

·3-min read

Researchers are trialling an artificial-intelligence system which they believe can diagnose dementia after one brain scan.

Those involved in the work said being able to intervene earlier could help with efforts to slow the disease’s progression and ensure patients have more information on their situation at an earlier stage.

Some 500 patients are expected to take part in the first year of the trial at Addenbrooke’s Hospital in Cambridge and other memory clinics across the country.

The system works by comparing brain scans of people who suspect they might have dementia with those who have already been diagnosed. An algorithm is used to detect patterns in the scans that expert neurologists cannot identify.

Zoe Kourtzi, professor of cognitive computational neuroscience at the Alan Turing Institute and professor of experimental psychology at the University of Cambridge, said early intervention is key.

She told the BBC: “If we intervene early, the treatments can kick in early and slow down the progression of the disease and at the same time avoid more damage.

“And it’s likely that symptoms occur much later in life or may never occur.”

Consultant neurologist Dr Timothy Rittman, from the University of Cambridge, told the BBC the artificial-intelligence system was a “fantastic development”.

He said: “These set of diseases are really devastating for people.

“So when I am delivering this information to a patient, anything I can do to be more confident about the diagnosis, to give them more information about the likely progression of the disease to help them plan their lives is a great thing to be able to do.”

More than 850,000 people in the UK are thought to have dementia, according to the NHS, with the condition affecting one in 14 people over the age of 65, and one in six people aged over 80.

Alzheimer’s Research UK has said predictions from 2014 estimated that one million people here will have dementia by 2025, doubling to two million by 2050.

Dr Laura Phipps, from the charity, said this latest work could help doctors have more confidence when looking at scans and diagnosing patients.

She said: “To diagnose dementia today, doctors need to rely on the interpretation of brain scans and cognitive tests, often over a period of time.

“Machine learning models such as those being developed by Prof Kourtzi could give doctors greater confidence in interpreting scans, leading to a more accurate diagnosis for patients.

“We hope that, in future, such approaches will not only improve how current diagnostic techniques are implemented but open the door to revolutionary new approaches to detect the diseases that cause dementia much earlier. This would have a huge impact on people with dementia and their families.”

She said Prof Kourtzi is also leading a project funded by Alzheimer’s Research UK which combines digital data from apps and wearable items including sleep, cognition, fine motor skills and brain activity to predict diseases like Alzheimer’s up to 20 years earlier.

Our goal is to create a safe and engaging place for users to connect over interests and passions. In order to improve our community experience, we are temporarily suspending article commenting