Artificial intelligence has enabled a huge breakthrough in the fight against Parkinson’s disease.
Machine learning helped develop a simple new blood test that could predict the debilitating condition seven years before symptoms start to show.
Scientists developed a new test for Parkinson’s using artificial intelligence (AI).
The study of the world’s fastest-growing neurodegenerative disorder which affects nearly 10 million people worldwide was led by researchers at University College London (UCL) and University Medical Centre Goettingen in Germany.
Parkinson’s is a progressive disorder that is caused by the death of nerve cells in a part of the brain, called the substantia nigra, which controls movement.
The research team explained that those nerve cells die or become impaired, losing the ability to produce the chemical dopamine due to the build-up of a protein alpha-synuclein.
There is currently no cure for Parkinson’s disease. Patients are currently treated with dopamine replacement therapy after they have already developed symptoms – such as tremors, slowness of movement and gait, and memory problems.
However, scientists believe early prediction and diagnosis would be valuable for finding treatments that could slow or stop the condition by protecting the dopamine-producing brain cells.
Study senior author Professor Kevin Mills of UCL said: “As new therapies become available to treat Parkinson’s, we need to diagnose patients before they have developed the symptoms. We cannot regrow our brain cells and therefore we need to protect those that we have.
“At present, we are shutting the stable door after the horse has bolted and we need to start experimental treatments before patients develop symptoms.
“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.”
The new study, published in the journal Nature Communications, showed that when a branch of AI, called machine learning, analysed a panel of eight blood-based biomarkers whose concentrations are altered in patients with Parkinson’s, it could provide a diagnosis with 100 percent accuracy. The team then experimented to see whether the test could predict the likelihood that a person would go on to develop Parkinson’s.
They did so by analysing blood from 72 participants with Rapid Eye Movement Behaviour Disorder (iRBD) which results in patients physically acting out their dreams without knowing it. It was already known that around 75 percent to 80 percent of people with iRBD will go on to develop a “synucleinopathy” – 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 machine learning tool analysed the blood of the iRBD patients, it identified that 79 percent had the same profile as someone with Parkinson’s.
The patients were followed over the course of 10 years and the AI predictions have so far matched the clinical conversion rate – with the researchers correctly predicting 16 patients as going on to develop Parkinson’s and being able to do so up to seven years before the onset of any symptoms. The team is now continuing to follow those predicted to develop Parkinson’s, to further verify the accuracy of the test.
Co-first author Dr Michael Bartl, of University Medical Centre Goettingen, said: “By determining eight proteins in the blood, we can identify potential Parkinson’s patients several years in advance. This means that drug therapies could potentially be given at an earlier stage, which could possibly slow down disease progression or even prevent it from occurring.
“We have not only developed a test, but can diagnose the disease based on markers that are directly linked to processes such as inflammation and degradation of non-functional proteins. So these markers represent possible targets for new drug treatments.”
Study co-author Professor Kailash Bhatia, of UCL, and his team are now examining the test’s accuracy by analysing samples from those in the population who are at high risk of developing Parkinson’s.
The researchers are also hoping to secure funding to create a simpler test where a drop of blood can be spotted on a card and posted to the lab to investigate if it can predict Parkinson’s disease even earlier than seven years before the onset of symptoms.
Professor David Dexter, Director of Research at Parkinson’s UK which co-funded the study, said: “This research represents a major step forward in the search for a definitive and patient friendly diagnostic test for Parkinson’s.
“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.”
