Researchers have leveraged artificial intelligence (AI) to identify a biological signature of Parkinson’s disease, aiming to develop a simple blood test that could detect the condition at least seven years before symptoms appear.
Parkinson’s affects nearly 10 million people across the globe and is the fastest-growing neurodegenerative disorder worldwide. Common symptoms include slowness of movement, tremors, and muscle stiffness. Currently, no drugs can slow or stop Parkinson’s, and the lack of predictive tools hinders the development of preventative treatments. By the time symptoms manifest, significant brain cell damage has already occurred.
Professor Kevin Mills from UCL Great Ormond Street Institute of Child Health, who co-developed the blood test, emphasized the need for early intervention, stating, “We need to start experimental treatments before patients develop symptoms.”
Researchers from University College London and University Medical Centre in Goettingen, Sweden, utilized machine learning to screen blood samples from Parkinson’s patients. They identified eight key proteins, or “biomarkers,” common to those with the disease. The AI tool then analyzed decade-old blood samples from individuals with Rapid Eye Movement Disorder, a condition from which approximately 75% of sufferers develop Parkinson’s.
The AI successfully predicted which patients would develop Parkinson’s up to seven years before symptoms emerged. “By determining eight proteins in the blood, we can identify potential Parkinson’s patients several years in advance,” explained Dr. Michael Bartl at UMC Goettingen. This early detection could allow for drug therapies to be administered sooner, potentially slowing disease progression or preventing it.
Further validation of the test’s accuracy and the development of a clinical version are necessary before it can be widely used. The research was published in Nature Communications.
