Blood test using AI could help predict Parkinson’s disease early

A new blood test using artificial intelligence (AI) may be able to predict Parkinson’s disease seven years before symptoms appear in patients.

Parkinson’s disease is a neurodegenerative condition impacting around 10 million people globally, especially older individuals.

It can cause symptoms such as shaking, slow movement, and muscle stiffness in addition to other physical and mental problems, and is rising in prevalence.

Researchers used machine learning to identify eight blood-based biomarkers. Their test provided a diagnosis with 100 per cent accuracy, researchers said.

“By determining eight proteins in the blood, we can identify potential Parkinson’s patients several years in advance,” said Michael Bartl, co-first-author of the study from University Medical Center Göttingen.

“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”.

They also analysed blood from 72 patients with Rapid Eye Movement Behaviour Disorder (iRBD), which is associated with neurodegenerative disorders.

The researchers followed up over ten years to see if the blood test could predict whether these patients would develop Parkinson’s. The test classified 79 per cent of patients as having the same profile as someone with Parkinson’s disease.

The earliest correct identification of a patient that would go on to develop the disease occurred 7.3 years before symptom onset, according to the study.

“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,” said Kevin Mills, senior author from University College London.

“With sufficient funding, we hope that this may be possible within two years”.

The study was published in the journal Nature Communications.

‘Major step forward’

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

“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,” he added.

Ray Chaudhuri, professor of movement disorders and neurology at King’s College London, said that blood tests remain an “unmet need” for Parkinson’s disease.

“If replicated in larger studies”, they could be invaluable in supporting Parkinson’s diagnoses, he said

“Questions however remain about the ethics of predictive diagnosis in relation to proper counselling as well as absence currently, of any disease-modifying treatment”.