Healthcare, UK (Commonwealth Union) – Researchers from UCL and University Medical Center Goettingen, Germany, have developed a groundbreaking blood test that employs artificial intelligence (AI) to forecast the onset of Parkinson’s disease up to seven years prior to the manifestation of symptoms.
Parkinson’s disease, a rapidly growing neurodegenerative disorder, currently affects approximately 10 million individuals worldwide. The disease is characterized by the degeneration of nerve cells in the brain’s substantia nigra region, which is responsible for controlling movement. These nerve cells lose their ability to produce dopamine, an essential chemical, due to the accumulation of a protein called alpha-synuclein.
Currently, Parkinson’s patients are treated with dopamine replacement therapy after exhibiting symptoms such as tremors, slow movement and gait, and memory issues. Researchers believe that early detection and diagnosis would be invaluable in developing treatments that could slow down or halt the progression of Parkinson’s by safeguarding the dopamine-producing brain cells. Professor Kevin Mills, the senior author from UCL Great Ormond Street Institute of Child Health, indicated that when new therapies become available for the treatment of Parkinson’s, we need to diagnose patients prior to them having developed the symptoms. We cannot regrow our brain cells and hence the protection of the cells we have is essential.
“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.”
A study published in Nature Communications revealed the potential of machine learning in diagnosing Parkinson’s disease with 100% accuracy. By analyzing a panel of eight blood-based biomarkers, the AI system could accurately identify patients with Parkinson’s. Furthermore, the research team tested the AI’s ability to predict the likelihood of developing Parkinson’s by analyzing blood samples from 72 patients with Rapid Eye Movement Behaviour Disorder (iRBD), a condition known to be a precursor to Parkinson’s in 75-80% of cases. The machine learning tool identified 79% of iRBD patients as having the same profile as Parkinson’s patients. Over a ten-year follow-up, the AI accurately predicted 16 patients who went on to develop Parkinson’s, up to seven years before symptoms emerged. The team continues to follow up on these patients to verify the test’s accuracy.
Dr Michael Bartl, co-first-author and researcher from the University Medical Center Goettingen, along with Dr Jenny Hällqvist from the UCL Great Ormond Street Institute of Child Health, have discovered a groundbreaking method to identify potential Parkinson’s patients several years prior to the onset of symptoms. By analyzing 8 specific proteins in the blood, early detection becomes possible, enabling potential early-stage drug therapies that could slow down disease progression or even prevent its occurrence altogether.
“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.”
Professor Kailash Bhatia (UCL Queen Square Institute of Neurology and National Hospital for Neurology & Neurosurgery) and his team are currently assessing the precise nature of their test with the evaluation of samples from individuals at high risk of developing Parkinson’s disease. This includes those with specific genetic mutations, such as LRRK2 or GBA, which are associated with Gaucher disease.
The team also aims to secure funding to develop a simpler blood spot test. This test would involve placing a drop of blood on a card, which could be mailed to a lab to investigate its potential to predict Parkinson’s disease even earlier than the current seven-year pre-symptomatic detection window.
This study received backing by an EU Horizon 2020 grant, Parkinson’s UK, the National Institute for Health and Care Research GOSH Biomedical Research Centre (NIHR GOSH BRC), and the Szeben-Peto Foundation.
Professor David Dexter, Director of Research at Parkinson’s UK, indicates that the research, co-funded by Parkinson’s UK, marks a significant advancement in the quest for a definitive and patient-friendly diagnostic test for those with Parkinson’s. Identifying and measuring biological markers in the blood is far less invasive than the increasingly common lumbar puncture used in clinical research.”
