Trial uses AI to rapidly diagnose Alzheimer’s disease

A patient at Addenbrooke’s Hospital has become one of the first people in the country to take part in a trial using Artificial Intelligence (AI) to help diagnose and treat Alzheimer’s disease.

Alzheimer’s disease
Images of a brain scan (Image: CUH NHS Foundation Trust)

Dennis Clark, a 75-year-old retired sales director, was referred onto the QMIN-MC trial after he began exhibiting signs of Alzheimer’s.

The QMIN-MC trial is using a machine learning algorithm developed by Prof Zoe Kourtzi, research lead at the Alan Turing Institute, which trains itself to diagnose patients by looking at MRI brain scans to identify patterns. It then combines these findings with the results of standard memory tests.

MORE FROM ARTIFICIAL INTELLIGENCE

In a statement, Addenbrooke’s consultant and clinical lead for the trial, Dr Timothy Rittman, said: “Traditionally, when we look at patient scans we are looking for patterns to be able to help us exclude things like strokes and brain tumours. The computer can do this much more comprehensively than any human, helping to give us not only a more accurate diagnosis, but also a prognosis as well. With a better prognosis we can identify how quickly a patient is moving away from the normal pattern of the disease and amend their treatment and care accordingly.”

According to Addenbrooke’s, diagnosing Alzheimer’s disease and dementia can take many months as it can require two or three hospital visits and involve a range of CT, PET and MRI scans, plus invasive lumber punctures.

Doctors now hope AI can be used to provide a one-stop diagnosis, enabling patients to begin treatment to reduce the effects of the disease more quickly and give families and friends more time to make longer term preparations.

To date around 80 patients have taken part in trial which was run by Cambridge University Hospitals (CUH), Cambridgeshire and Peterborough NHS Foundation Trust and two NHS trusts in Brighton.

Clark underwent an MRI scan on 21 July and later that same day he and his wife received news that his results were consistent with early onset of Alzheimer’s disease. Clark will now start taking medication to help treat the symptoms of Alzheimer’s disease.

Addenbrooke’s added that the algorithm could be rolled out to thousands more patients across the country if the results of the trial are positive, a step that could save the NHS half a billion pounds over the next five years.