AI blood test can predict Parkinson's seven years before diagnosis

Researchers say the test could help identify new treatments to slow or stop the development of the disease

A new test analyses eight blood-based biomarkers, using artificial intelligence to provide a Parkinson’s diagnosis with 100 per cent accuracy, experts say. Getty Images

A new blood test that uses artificial intelligence can predict a person’s risk of Parkinson’s seven years before the onset of symptoms, which could help identify new treatments to slow or stop the development of the disease.

The condition, which is the world’s fastest-growing neurodegenerative disorder, causes involuntary shaking, slow movement and stiff, inflexible muscles due to the death of nerve cells in an area of the brain that controls movement.

That results in the loss of cells’ ability to produce the chemical dopamine, due to the build-up of a protein alpha-synuclein.

Sufferers are currently treated with dopamine replacement therapy after developing symptoms, such as trembling, slowness of movement and gait, and memory problems.

The new blood test, developed by a team led by scientists at University College of London and University Medical Centre Goettingen, analyses eight blood-based biomarkers, whose concentrations are altered in patients with Parkinson’s, using artificial intelligence to provide a diagnosis with 100 per cent accuracy.

The researchers used the test to see if it could predict the probability that a person would go on to develop the disease by analysing blood from 72 patients with Rapid Eye Movement Behaviour Disorder (iRBD).

Around 75-80 per cent sufferers of the condition are known to go on to develop a type of brain disorder caused by the abnormal build-up of a protein called alpha-synuclein in brain cells – including Parkinson’s.

When the AI machine learning tool analysed the blood of these patients, it identified that 79 per cent of the iRBD patients had the same profile as someone with Parkinson’s.

The patients were followed up over the course of ten years and the AI predictions have so far matched the clinical conversion rate – with the team correctly predicting 16 patients as going on to develop Parkinson’s, up to seven years before the onset of any symptoms.

The team are now continuing to follow up on those predicted to develop Parkinson’s, to further verify the accuracy of the test.

The researchers say the new test could help find new treatments that could potentially slow or stop the development of the disease by protecting the dopamine-producing brain cells.

Study senior author Prof Kevin Mills, of the UCL Great Ormond Street Institute of Child Health, said brain cells cannot be regrown once they die, so the ones we have need to be protected.

“At present we are shutting the stable door after the horse has bolted and we need to start experimental treatments before patients develop symptoms," he added.

“Therefore, we set out to use state-of-the-art technology to find new and better biomarkers for Parkinson’s disease and develop them into a test that we can translate into any large NHS laboratory. With sufficient funding, we hope that this may be possible within two years.”

Co-author Dr Michael Bartl from the University Medical Centre Goettingen and Paracelsus-Elena-Klinik Kassel, who co-conducted the research from the clinical side, said the markers could also represent possible targets for new drug treatments.

“This research, co-funded by Parkinson’s UK, represents a major step forward in the search for a definitive and patient friendly diagnostic test for Parkinson’s,” said Prof David Dexter, director of research at Parkinson’s UK.

“Finding biological markers that can be identified and measured in the blood is much less invasive than a lumbar puncture, which is being used more and more in clinical research.

“With more work, it may be possible that this blood based test could distinguish between Parkinson’s and other conditions that have some early similarities, such as Multiple Systems Atrophy or Dementia with Lewy Bodies.

“The findings add to an exciting flurry of recent activity towards finding a simple way to test for and measure Parkinson’s.”